CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application No. (i) 63/108,995 filed 03-Nov-2020, which is incorporated herein by reference.

BACKGROUND

[0002] The present disclosure is generally directed to the fields of communications, software and encoding, including, for example, to methods, architectures, apparatuses, systems directed to multiple access wireless communications, such as non-orthogonal multiple access (NOMA) communications including any of user selection and/or symbol detection

BRIEF DESCRIPTION OF THE DRAWINGS

[0003] A more detailed understanding may be had from the detailed description below, given by way of example in conjunction with drawings appended hereto. Figures in such drawings, like the detailed description, are examples. As such, the Figures (FIGs.) and the detailed description are not to be considered limiting, and other equally effective examples are possible and likely. Furthermore, like reference numerals ("ref") in the FIGs. indicate like elements, and wherein: [0004] FIG. 1A is a system diagram illustrating an example communications system;

[0005] FIG. 1B is a system diagram illustrating an example wireless transmit/receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A;

[0006] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A;

[0007] FIG. 1D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1A;

[0008] FIG. 2 is a diagram illustrating a representative system for NOMA communication;

[0009] FIG. 3 is a diagram illustrating a representative system configuration for NOMA communication;

[0010] FIG. 4 is a diagram illustrating a representative procedure for NOMA selection and symbol detection between a base station (BS) and plural wireless transmit/receive units (WTRUs); [0011] FIG. 5 is a diagram illustrating a representative system for multi-user NOMA selection;

[0012] FIG. 6 is a diagram illustrating a representative procedure for multi-user NOMA selection;

[0013] FIG. 7 is a diagram illustrating another representative procedure for multi-user NOMA selection including a retraining feedback loop; [0014] FIG. 8. is a diagram illustrating a representative deep neural network (DNN) for multi- user NOMA symbol detection;

[0015] FIG. 9. is a diagram illustrating a representative procedure for multi-user NOMA symbol detection;

[0016] FIG. 10 is a diagram illustrating a representative comparison of bit error rate (BER) using different DNN weight sets trained for different numbers of WTRUs;

[0017] FIG. 11 is a diagram illustrating a representative procedure for a BS for NOMA communication;

[0018] FIG. 12 is a diagram illustrating a representative procedure for a WTRU for NOMA communication;

[0019] FIG. 13 is a diagram illustrating a representative procedure for a WTRU to receive a NOMA transmission;

[0020] FIG. 14 is a diagram illustrating a representative procedure for a BS to transmit a NOMA transmission;

[0021] FIG. 15 is a diagram illustrating a representative procedure for a BS for updating a neural network used for selecting WTRUs for a NOMA transmission;

[0022] FIG. 16 is a diagram illustrating a representative procedure for a WTRU for updating a neural network used for selecting WTRUs for a NOMA transmission;

[0023] FIG. 17 is a diagram illustrating a representative procedure for a BS to select WTRUs to receive a NOMA transmission;

[0024] FIG. 18 is a diagram illustrating a representative procedure for a WTRU to receive a NOMA transmission;

[0025] FIG. 19 is a diagram illustrating a representative procedure for a WTRU to receive a multiple access (MA) transmission;

[0026] FIG. 20 is a diagram illustrating a representative procedure for a BS to transmit a MA transmission;

[0027] FIG. 21 is a diagram illustrating a representative procedure for a BS for updating a neural network used for selecting WTRUs for a MA transmission;

[0028] FIG. 21 is a diagram illustrating a representative procedure for a WTRU for updating a neural network used for selecting WTRUs for a MA transmission;

[0029] FIG. 23 is a diagram illustrating a representative procedure for a BS to select WTRUs to receive a MA transmission;

[0030] FIG. 24 is a diagram illustrating a representative procedure for a WTRU to receive a MA transmission; [0031] FIG. 25 is a diagram illustrating a representative procedure for a WTRU to receive a NOMA transmission;

[0032] FIG. 26 is a diagram illustrating a representative procedure for a WTRU to receive a NOMA transmission;

[0033] FIG. 27 is a diagram illustrating a representative procedure for a BS to transmit a NOMA transmission;

[0034] FIG. 28 is a diagram illustrating a representative procedure for a WTRU to receive a MA transmission;

[0035] FIG. 29 is a diagram illustrating a representative procedure for a BS to transmit a MA transmission; and

[0036] FIG. 30 is a diagram illustrating a representative procedure for a WTRU to receive a MA transmission.

DETAILED DESCRIPTION

[0037] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of embodiments and/or examples disclosed herein. However, it will be understood that such embodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components and circuits have not been described in detail, so as not to obscure the following description. Further, embodiments and examples not specifically described herein may be practiced in lieu of, or in combination with, the embodiments and other examples described, disclosed or otherwise provided explicitly, implicitly and/or inherently (collectively "provided") herein. Although various embodiments are described and/or claimed herein in which an apparatus, system, device, etc. and/or any element thereof carries out an operation, process, algorithm, function, etc. and/or any portion thereof, it is to be understood that any embodiments described and/or claimed herein assume that any apparatus, system, device, etc. and/or any element thereof is configured to carry out any operation, process, algorithm, function, etc. and/or any portion thereof.

[0038] Example Communications System

[0039] The methods, apparatuses and systems provided herein are well-suited for communications involving both wired and wireless networks. An overview of various types of wireless devices and infrastructure is provided with respect to FIGs. 1A-1D, where various elements of the network may utilize, perform, be arranged in accordance with and/or be adapted and/or configured for the methods, apparatuses and systems provided herein.

[0040] FIG. 1A is a system diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single- carrier FDMA (SC-FDMA), zero-tail (ZT) unique-word (UW) discreet Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block- filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0041] As shown in FIG. 1A, the communications system 100 may include wireless transmit/receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104/113, a core network (CN) 106/115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and/or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and/or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a "station" and/or a "STA", may be configured to transmit and/or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi- Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and/or other wireless devices operating in an industrial and/or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and/or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a WTRU.

[0042] The communications systems 100 may also include a base station 114a and/or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, e.g., to facilitate access to one or more communication networks, such as the CN 106/115, the Internet 110, and/or the networks 112. By way of example, the base stations 114a, 114b may be any of a base transceiver station (BTS), a Node-B (NB), an eNode-B (eNB), a Home Node-B (HNB), a Home eNode-B (HeNB), a gNode-B (gNB), a NR Node-B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and/or network elements.

[0043] The base station 114a may be part of the RAN 104/113, which may also include other base stations and/or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and/or the base station 114b may be configured to transmit and/or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in an embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and/or receive signals in desired spatial directions.

[0044] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), micro wave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0045] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104/113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and/or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and/or High-Speed Uplink Packet Access (HSUPA).

[0046] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and/or LTE-Advanced (LTE-A) and/or LTE-Advanced Pro (LTE-A Pro). [0047] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0048] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and/or transmissions sent to/from multiple types of base stations (e.g., an eNB and a gNB).

[0049] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 IX, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0050] The base station 114b in FIG. 1A may be a wireless router, Home Node-B, Home eNode- B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish any of a small cell, picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106/115.

[0051] The RAN 104/113 may be in communication with the CN 106/115, which may be any type of network configured to provide voice, data, applications, and/or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106/115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and/or perform high-level security functions, such as user authentication. Although not shown in FIG. 1 A, it will be appreciated that the RAN 104/113 and/or the CN 106/115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104/113 or a different RAT. For example, in addition to being connected to the RAN 104/113, which may be utilizing an NR radio technology, the CN 106/115 may also be in communication with another RAN (not shown) employing any of a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technology.

[0052] The CN 106/115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and/or other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and/or the internet protocol (IP) in the TCP/IP internet protocol suite. The networks 112 may include wired and/or wireless communications networks owned and/or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104/114 or a different RAT.

[0053] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0054] FIG. 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit/receive element 122, a speaker/microphone 124, a keypad 126, a display/touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and/or other elements/peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0055] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input/output processing, and/or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit/receive element 122. While FIG. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, e.g., in an electronic package or chip.

[0056] The transmit/receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in an embodiment, the transmit/receive element 122 may be an antenna configured to transmit and/or receive RF signals. In an embodiment, the transmit/receive element 122 may be an emitter/ detector configured to transmit and/or receive IR, UV, or visible light signals, for example. In an embodiment, the transmit/receive element 122 may be configured to transmit and/or receive both RF and light signals. It will be appreciated that the transmit/receive element 122 may be configured to transmit and/or receive any combination of wireless signals.

[0057] Although the transmit/receive element 122 is depicted in FIG. 1B as a single element, the WTRU 102 may include any number of transmit/receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit/receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0058] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit/receive element 122 and to demodulate the signals that are received by the transmit/receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0059] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker/microphone 124, the keypad 126, and/or the display/touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker/microphone 124, the keypad 126, and/or the display/touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and/or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read- only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0060] The processor 118 may receive power from the power source 134, and may be configured to distribute and/or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0061] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and/or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0062] The processor 118 may further be coupled to other elements/peripherals 138, which may include one or more software and/or hardware modules/units that provide additional features, functionality and/or wired or wireless connectivity. For example, the elements/peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (e.g., for photographs and/or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and/or augmented reality (VR/AR) device, an activity tracker, and the like. The elements/peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and/or a humidity sensor.

[0063] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the uplink (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and/or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include ahalf-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the uplink (e.g., for transmission) or the downlink (e.g., for reception)).

[0064] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0065] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0066] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the uplink (UL) and/or downlink (DL), and the like. As shown in FIG. 1C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface. [0067] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any one of these elements may be owned and/or operated by an entity other than the CN operator.

[0068] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an SI interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation/deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and/or WCDMA.

[0069] The SGW 164 may be connected to each of the eNode-Bs 160a, 160b, 160c in the RAN 104 via the SI interface. The SGW 164 may generally route and forward user data packets to/from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0070] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0071] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and/or wireless networks that are owned and/or operated by other service providers.

[0072] Although the WTRU is described in FIGs. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network. [0073] In representative embodiments, the other network 112 may be a WLAN.

[0074] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a distribution system (DS) or another type of wired/wireless network that carries traffic into and/or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and/or referred to as peer-to-peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.1 le DLS or an 802.1 1z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an "ad-hoc" mode of communication.

[0075] When using the 802.11ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier sense multiple access with collision avoidance (CSMA/CA) may be implemented, for example in in 802.11 systems. For CSMA/CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed/detected and/or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0076] High throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0077] Very high throughput (VHT) STAs may support 20 MHz, 40 MHz, 80 MHz, and/or 160 MHz wide channels. The 40 MHz, and/or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 804-80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse fast fourier transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above-described operation for the 804-80 configuration may be reversed, and the combined data may be sent to a medium access control (MAC) layer, entity, etc.

[0078] Sub 1 GHz modes of operation are supported by 802.11af and 802.11ah. The channel operating bandwidths, and carriers, are reduced in 802.11af and 802.11ah relative to those used in 802.11n, and 802.11ac. 802.11af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV white space (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11 ah may support meter type control/machine-type communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and/or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0079] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and/or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11 ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and/or other channel bandwidth operating modes. Carrier sensing and/or network allocation vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0080] In the United States, the available frequency bands, which may be used by 802.11ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11ah is 6 MHz to 26 MHz depending on the country code.

[0081] FIG. 1D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0082] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 180b may utilize beamforming to transmit signals to and/or receive signals from the WTRUs 102a, 102b, 102c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and/or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and/or gNB 180c). [0083] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, OFDM symbol spacing and/or OFDM subcarrier spacing may vary for different transmissions, different cells, and/or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., including a varying number of OFDM symbols and/or lasting varying lengths of absolute time).

[0084] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and/or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In anon-standalone configuration WTRUs 102a, 102b, 102c may communicate with/connect to gNBs 180a, 180b, 180c while also communicating with/connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non-standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and/or throughput for servicing WTRUs 102a, 102b, 102c.

[0085] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and/or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, and the like. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0086] The CN 115 shown in FIG. 1D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and at least one Data Network (DM) 185a, 185b. While each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and/or operated by an entity other than the CN operator. [0087] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b, e.g., to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and/or the like. The AMF 182 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-APro, and/or non-3GPP access technologies such as Wi- Fi.

[0088] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to aUPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating WTRU IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP -based, non-IP based, Ethernet-based, and the like.

[0089] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, e.g., to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi- homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0090] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and/or wireless networks that are owned and/or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0091] In view of FIGs. 1A-1D, and the corresponding description of FIGs. 1A-1D, one or more, or all, of the functions described herein with regard to any of: WTRUs 102a-d, base stations 114a- b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a- b, SMFs 183a-b, DNs 185a-b, and/or any other element(s)/device(s) described herein, may be performed by one or more emulation elements/devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and/or to simulate network and/or WTRU functions.

[0092] Although, a Network Access Point (NAP) is shown to be a base station, an eNB and/or a gNB, among others, in FIGS. 1A to 1D, it should be understood other network access points are contemplated including 5G and beyond NAPs. For example, a NAP may include a distributed stack (e.g., set of layers) virtualized over any number of devices (e.g., hardware modules) which, in operation, may act as a NAP. For simplicity, the following description NAP and BS may be used interchangeably.

[0093] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and/or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and/or deployed as part of a wired and/or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented/deployed as part of a wired and/or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and/or may performing testing using over-the-air wireless communications.

[0094] The one or more emulation devices may perform the one or more, including all, functions while not being implemented/deployed as part of a wired and/or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and/or a non-deployed (e.g., testing) wired and/or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and/or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and/or receive data. [0095] With non-orthogonal multiple access (NOMA), multiple WTRUs may be co-scheduled and share the same radio resources with respect to time, frequency and/or code domains. In “NOMA: An Information Theoretic Perspective” by P. Xu et al., the concept of NOMA is discussed from an information theoretic perspective, and they conclusion that NOMA may have a better performance as compared with orthogonal multiple access (OMA) in terms of both system sum rate and user individual rate, such as when multipleWTRUs channel gains are distinct.

[0096] Owing to improved user-fairness and improved spectral efficiency, NOMA has become a promising candidate for beyond 5G networks. Different types of NOMA have been proposed in “A survey of NOMA: Current status and open research challenges” by B. Makki et al., such as power domain NOMA, sparse code multiple access (SCMA), pattern division multiple access (PDMA), resource spread multiple access (RSMA), multi-user shared access (MUSA), interleave- grid multiple access (IGMA), Welch-bound equality spread multiple access (WSMA) and interleave division multiple access (IDMA).

[0097] Power domain NOMA is considered a potential NOMA scheme for beyond 5G networks. Also, more recently power domain NOMA has been included in the forthcoming digital TV standard of the Advanced Television Systems Committee (ATSC 3.0). In a power domain NOMA, example, two WTRUs may use the same spectrum, and a WTRU with a higher channel gain uses less power to avoid intra-cluster interference. At the receiver side in power domain NOMA, each WTRU applies a successive interference cancellation (SIC) method to decode an original signal from a superimposed signal.

[0098] In state-of-the-art NOMA systems, SIC assisted detection is employed relying on the simplifying assumption of having perfect CSI at the receiver as in “Layered-division multiplexing: Theory and practice” by L. Zhang et al. However, in the face of channel errors, the SIC assisted detection degrades the performance because of the error propagation nature observed in SIC, which is highly sensitive to the CSI imperfections as in “Fully non-orthogonal communication for massive access” by X. Chen et al. Additionally, as the number of WTRUs in a cluster increases, co-channel interference further degrades the performance owing to both SIC complexity and error propagation as in “Fully non-orthogonal communication for massive access” and “Deep learning- based sum data rate and energy efficiency optimization for MIMO-NOMA systems” by H. Huang et al. This degradation is even more pronounced if the non-linear components introduced by the hardware are considered, which is known to be particularly the case in higher frequency operations (e.g., THz communications).

[0099] Owing to these reasons, it is presently considered as follows that it may be advantageous to employ machine learning techniques so as to jointly model the CSI impairments and SIC detector as well as to develop transmission and decoding schemes that adapt to the joint and mostly intractable channel and device impairments.

[0100] Machine learning (ML) techniques may be applied to solve challenges and problems in wireless communications including NOMA systems. ML provides a data-driven approach to learn information and solve traditionally challenging problems without relying on predetermined models and equations as in, for example, “Non-Orthogonal Multiple Access: Common Myths and Critical Questions” by M. Vaezi et al. In “Deep learning-based sum data rate and energy efficiency optimization for MIMO-NOMA systems” by H. Huang et al., the focus was on encoding/decoding and user clustering as well as power allocation using deep learning techniques. In “Deepsic: Deep soft interference cancellation for multiuser MIMO detection” by N. Shlezinger et al., a deep- learning based SIC receiver for multiuser detection is proposed. However, these works consider static users and they fail to address dynamic NOMA user selection and symbol detection, where dynamicity implies varying channel conditions and/or varying numbers of WTRUs in the network, which are some critical and realistic constraints in practical deployments.

[0101] In certain representative embodiments, deep Q-network (DQN) based NOMA user selection methods, apparatus and systems may exploit WTRUs’ uplink received signals while also (e.g., simultaneously) circumventing downlink CSI requirement that may need to be fedback to the base-station as in conventional systems.

[0102] In certain representative embodiments, methods, apparatus and systems may include a codebook comprising of a plurality of deep neural network (DNN) weight sets which may correspond and/or be associated with different numbers of WTRUs, where, in order to facilitate dynamic NOMA symbol detection by WTRUs in the cluster, a WTRU may invoke specific DNN weight sets for symbol detection. Such an approach may permit the WTRU to avoid having to rely on downlink CSI-RS reception for NOMA symbol detection purposes.

System Model

[0103] FIG. 2 is a diagram illustrating a representative system for NOMA communication. In FIG. 2, a base station (BS) may communicate with a plurality of (e.g., a number N _u ) of WTRUs (e.g., WTRUs) which may be clustered together to receive different beams (e.g., NOMA beams) from the BS. As an example, the WTRUs may be clustered in two different beams as shown in FIG. 2. In certain representative embodiments, the BS and/or the WTRUs may be configured to perform wireless communication using millimeter wave (mmWave) signals. In certain representative embodiments, the NOMA communication may be a downlink communication using mmWave transmissions. FIG. 3 is a diagram illustrating a representative system configuration for NOMA communication. As shown in FIG. 3, a BS (e.g., gNB or other NAP) and the WTRUs may be equipped with N _t and N _r transmit and receive antenna elements (AEs), respectively. The BS and WTRUs may also be facilitated with RF chains, respectively.

[0104] In FIG. 2, the set comprises a plurality of DNN weight sets, where C _k may be used denote to the DNN weight set determined for k number of NOMA WTRUs, and α _k denotes the channel gain of a k ^th WTRU. As shown in FIG. 3, the BS may employ RF analog beamforming using F _RF of size and may transmit N _s symbols using a precoding matrix F _BB of size Any (e.g., each) WTRU may employ RF analog combining using an analog RF combiner matrix W _RF of size and digital combining using a digital baseband combiner matrix W _BB of size

[0105] A downlink received signal vector at the k ^th WTRU may be given by: where s _k is the signal vector of k ^th user, n is the noise vector distributed , and H _k is the channel matrix of size N _r x N _t which may be expressed as: where N _p is the number of paths, α _r and α _t are the antenna array response vectors at the receiver and transmitter, respectively, while is the small scale fading coefficient of k ^th user

[0106] With respect to the downlink communication, the (e.g., any and/or all) WTRUs may share the same time and/or frequency resources. With respect to uplink communication, the (e.g., any and/or all) WTRUs may employ an orthogonal mode of transmission (e.g., single-carrier frequency division multiple access (SC-FDMA) and/or OFDMA). For example, an uplink received signal vector in the n ^th subcarrier at the BS may be given by:

[0107] As described herein, methods, apparatus and systems may advantageously address technical shortcomings and challenges which some certain NOMA-based transmit and receive procedures may experience in the face of user and network dynamicity and varying channel conditions. Certain representative embodiments may offer solutions to address channel errors in NOMA communications wherein SIC assisted detection at the WTRUs (or BS) may suffer from (e.g., substantial) degraded performance. This may be due to the error propagation nature of SIC decoding, which may be highly susceptible to CSI imperfections. Certain representative embodiments may offer solutions to address increases in the number of WTRUs where increases in co-channel interference may erodes performance due to both SIC complexity and error propagation in decoding operations. Certain representative embodiments may offer solutions to address NOMA user selection procedures which may require CSI at the BS, which may impose significant pilot overhead for CSI acquisition in dynamic user settings.

[0108] Certain representative embodiments may include artificial intelligence (Al) based multi- user NOMA selection and symbol detection procedures. A BS may select a (e.g., optimal) number of users for NOMA communication (e.g., a mmWave NOMA downlink transmission) and may not rely on CSI at the BS. DNN weight-based NOMA detection codebooks and/or feedback procedures may be used to send an indication (e.g., index) of DNN weights that any (e.g., each) WTRU may employ for NOMA symbol detection. A neural-network and/or NOMA based downlink signal detection may be employed at any (e.g., each) WTRU.

[0109] Certain representative embodiments may include any of DQN-based NOMA user (e.g., WTRU) scheduling and/or DNN-based downlink signal detection (e.g., at the WTRUs) which may utilize NOMA scheduling information.

[0110] FIG. 4 is a diagram illustrating a representative signaling procedure for multi-user NOMA selection and symbol detection between a base station and user equipment. For example, the procedure may begin by performing, such as at a BS (e.g., gNB or other NAP), training (e.g., offline training) of a neural network (NN) (e.g., a deep Q-network (DQN)) for multi-user NOMA selection, and/or may perform training (e.g., offline training) of a neural network (NN) (e.g., a deep neural network (DNN)) for NOMA symbol detection.

[0111] After training for multi-user NOMA selection and NOMA symbol detection, the BS may receive an uplink signal vector y _ul from a plurality of WTRUs. The DQN may then take the uplink signal vector y _ul as an input and proceed to select the NOMA WTRUs (e.g., from among the WTRUs which transmitted the uplink signal vector y _ul ). The selected NOMA WTRUs (e.g., a combination of WTRUs for downlink transmission) may then be informed by an indication of such selection (e.g., via a downlink control channel). The WTRUs (e.g., each selected NOMA WTRU) may, after being informed of NOMA selection, may reply with an acknowledgement (e.g., ACK) to the BS.

[0112] Upon receiving acknowledgments from the selected NOMA WTRUs (e.g., each selected NOMA WTRU), the BS may select DNN weights for the selected NOMA WTRUs. For example, the BS may select an index corresponding to a set of DNN weights which may be a best fit for the current combination of selected NOMA WTRUs. The BS may the index of the selected set of DNN weights (e.g., codebook index) to the WTRUs. For example, the BS may send the index which corresponds to the selected DNN weights to any (e.g., each) of the selected NOMA WTRUs. Upon being informed of the selected DNN weights (e.g., receiving the index thereof) from the BS, the selected NOMA WTRUs may proceed to use the selected DNN weights for symbol detection. [0113] In some representative embodiments, the signaling procedure in FIG. 4 may proceed further and any of the selected NOMA WTRUs may indicate and/or send a request for updating and/or recalibrating the DNN weights (e.g., the selected set of DNN weights). For example, the BS may be requested (e.g., via an indication) to perform updating and/or recalibrating the DNN weights upon condition that a target threshold is not satisfied (e.g., at any of the selected NOMA WTRUs), such when any of a bit error rate (BER), transmission rate, or overall throughput fails to satisfy (e.g., does not meet) a configured (e.g., preconfigured) threshold value. After being requested to perform updating and/or recalibrating (e.g., from any or a configured number or more of the selected NOMA WTRUs), the BS may send a set (e.g., one or more) training samples. For example, the BS may send the training samples to any (e.g., each) of the WTRUs that have requested retraining. As another example, the BS may send the training samples to any (e.g., each) of the selected NOMA WTRUs. After finishing updating and/or recalibrating of the DNN weights, the WTRUs may send an acknowledgment (e.g., ACK) that retraining is finished to the BS.

DQN-Aided Multi-User NOMA Selection

[0114] In certain representative embodiments, a multi-user NOMA selection procedure may be performed using a DQN and/or may be performed without relying on downlink CSI. The multi- user (e.g., multi -UE) NOMA selection procedure may exploit the received uplink signal vector (e.g., y _ul [n]) of the WTRUs. The WTRUs may employ orthogonal transmission such as in 5G NR (e.g., SC-FDMA or OFDMA) and the BS may receive these transmissions as the uplink received signal vector from the WTRUs. The uplink signal vector (e.g., as received from the WTRUs at the BS) may be utilized for selection of a set of NOMA WTRUs using the DQN. For example, the DQN may take the received uplink signal vector as an input, may perform selection among the WTRUs (e.g., the WTRUs which transmitted the uplink signal vector to the BS) to determine a specific set of plural WTRUs (e.g., to maximize achievable downlink rate and/or minimize achievable BER). For example, to employ the DQN in real time, the DQN may be trained offline using one or more sets of actions, numbers of WTRUs, and corresponding rewards.

[0115] FIG. 5 is a diagram illustrating a representative system for multi-user NOMA selection. As shown in FIG. 5, the system may be generalized as an agent, such as a base station (BS) (e.g., gNB or other NAP), which may perform wireless communication with an environment (e.g., multiple WTRUs). The NAP may be provided with a DQN. The DQN may take a given state (e.g., the uplink signal vector y _ul [n]) as an input and predict an action (e.g., a NOMA WTRU combination N _uc ) as an output. The output NOMA WTRU combination N _uc may include the multiple WTRUs and may be the WTRUs which are to perform NOMA communication with the NAP, such as in a next and/or upcoming transmission time interval (TTI). The TTI may be any of a frame, sub-frame, slot, mini-slot and/or configured number of symbols. The WTRUs indicated by the output NOMA WTRU combination N _uc may be the set of WTRUs which are predicted to be most suitable for the state provided as input to the DQN. The NAP may inform, such as by an explicit or implicit indication, any (e.g., each) of the WTRUs which are included in the NOMA user combination N _uc output from the DQN. The indication may be provided in a transport block, such as a single-bit flag. The WTRUs which may receive the NOMA communication from the NAP may transmit (e.g., feeback) a reward to the NAP. For example, the reward may be a rate such as a downlink bit error rate (BER) and/or transmission rate. The rate may be calculated using a last NOMA communication and/or an average of previous NOMA communications. Upon receiving the reward, the NAP may determine to retrain the DQN.

[0116] FIG. 6 is a diagram illustrating a representative procedure for multi-user NOMA selection. As shown in FIG. 6, the procedure may begin at Step 1 where a DQN may be trained (e.g., offline). For example, training may occur using multiple training states, such as uplink received signal vectors (e.g., y _ul [n]), for a set of NOMA user combinations (e.g., N _uc ). The training uplink received signal vectors may be artificially generated and/or may be generated from historical measurement of actual signals. The set of NOMA user combinations may be artificially generated and/or may include a plurality of different numbers of NOMA users (e.g., WTRUs). Each state-action may be fedback as a reward (e.g., rate) to the DQN. The training of the DQN may result in a DQN policy Q( y _ul , N _uc ) (e.g., DQN weights) being determined at step 1. As an example, the DQN may be trained at the NAP (e.g., gNB) or may be trained elsewhere.

[0117] After training of the DQN, the procedure may continue to Step 2. In some embodiments, Step 2 may be performed in real time at the NAP (e.g., gNB or other NAP). For example, at Step 2, the (e.g., trained) DQN may select a particular combination of NOMA WTRUs when provided with an observed state, such as the uplink received signal vector (e.g., y _ul [n]) from any (e.g., all) WTRUs which transmitted signals (e.g., SC-FDMA or OFDMA) to the NAP, as an input. The DQN may select a particular combination of NOMA WTRUs out of a plurality of NOMA WTRU combinations (e.g., WTRU combinations) using a particular input state at a given time t. The selected combination of NOMA WTRUs may be informed of selection (e.g., NOMA selection) by an explicit and/or implicit indication from the NAP. As an example, the indication may be a single- bit flag.

[0118] Sometime after selecting one or more NOMA combinations (e.g., after performing one or more NOMA transmissions), the procedure may continue to Step 3. At Step 3, the NAP may determine to recalibrate and/or update the DQN weights. The NAP (e.g., gNB or other network access point) may determine that the DQN weights are to be recalibrated and/or updated upon condition that any statistics of the received uplink signal vector have changed. For example, the recalibration and/or updating may be triggered when any of an observed received signal strength (RSS) falls below a threshold value and/or channel disparity (e.g., channel gain difference) exceeds a threshold value.

[0119] After Step 3, the procedure may continue to Step 4. At Step 4, an (e.g., implicit and/or explicit) indication of recalibration and/or updating may be transmitted from the NAP to any (e.g., all) WTRUs, such as via one or more downlink control channels. Any (e.g., each) WTRU upon receiving the indication may send an acknowledgement (e.g., ACK) of the downlink indication for recalibration and/or updating to the BS. Any (e.g., each) WTRU upon receiving the downlink indication may transmit one or more pilot sequences on an uplink signal to the BS. After receiving the pilot sequences from the WTRUs (e.g., all the WTRUs), the BS may then proceed to use these samples to generate one or more input states for retraining the DQN weights.

[0120] FIG. 7 is a diagram illustrating a representative procedure for multi-user NOMA selection including a retraining feedback loop. As shown in FIG. 7, the multi-user NOMA selection procedure may begin with a DQN training phase which may be similar to Step 1 of FIG. 5. During the DQN training phase, the DQN receives, as input, a particular state (e.g., an uplink signal vector y _ul [n]). The DQN may be configured to determine an action (e.g., select a specific NOMA WTRU combination N _uc ) by invoking ε —greedy strategy. Thereafter, the DQN may observes a reward (e.g., sum of achieved rates) corresponding to the determined action. The input states used for training of the DQN may include a continuous space of uplink received signal vectors. The output actions may include multiple different combinations of NOMA WTRUs (e.g., from among a total of N _u WTRUs) for the input states, respectively. The rewards may include the achieved rates (e.g., sums of achieved rates) for the specific combinations of NOMA WTRUs which are selected, respectively. In a setting where there are a plurality of WTRUs (e.g., N _u WTRUs), it should be understood that the DQN may be selecting a specific NOMA WTRU combination N _uc from a total of WTRU combinations.

[0121] As an example, the input states (e.g., uplink signal vectors) used for training the DQN may be obtained by conducting one or more measurement campaigns in real time, such as where an uplink received signal vector (e.g., y _ul [n]) and corresponding reward for each action is measured. As another example, the input states (e.g., uplink signal vectors) used for training the DQN may be artificially generated using machine learning techniques such as Generative Adversarial Networks (GANs). As another example, any combination of input states obtained from measurement campaigning and input states which are artificially generated may be used for training the DQN.

[0122] After the DQN has been trained, the DQN may be used in an inference phase which may be similar to Step 2 of FIG. 5. At a time t after completing training, the NAP may receive an uplink signal vector (e.g., uplink SC-FDMA and/or OFDMA signal vector y _ul ) from any (e.g., all) of the WTRUs. The NAP may input the received uplink signal vector to the DQN and the DQN weights may be applied to the input uplink signal vector. The DQN may then proceed to determine (e.g., obtain) a NOMA WTRU combination N _uc . For example, the DQN may output an index of the determined NOMA WTRU combination N _uc . The output index may be formed as a vector of dimension Nuc with single-bit values indicating whether each WTRU is selected for the NOMA transmission. The NAP may then identify the selected WTRUs based on the output index. The NOMA WTRU combination N _uc that is output by the DQN may be the combination of WTRUs having a highest predicted system throughput (e.g., out of a total NOMA WTRU combinations). While the (e.g., search) complexity of a brute force approach to multi-user NOMA WTRU selection is on the order of the (e.g., search) complexity of the disclosed DQN configuration is on the order of

[0123] After the NOMA WTRU combination N _uc is obtained by the NAP, the NAP may proceed to send a NOMA downlink data transmission to each (e.g., all) of the selected WTRUs (e.g., the WTRUs of the NOMA WTRU combination N _uc ). As shown in FIG. 7, the NAP may determine whether or not retraining of the DQN is necessary which may be similar to Step 3 of FIG. 5. For example, (e.g., continuous or periodic) monitoring of statistics of the received uplink signals may be performed (e.g., at the NAP and/or the WTRUs) to determine whether any deviations (e.g., variance of any of RSSs, channel powers, BERs, throughput rates and/or combinations thereof) have occurred with respect to configured thresholds at the WTRUs. Such deviations may be due to any of power control, mobility, and/or multipath effects.

[0124] The NAP may determine whether any deviations have occurred using a target BER and/or throughput rate at any (e.g., each) of the WTRUs. Upon condition that a deviation is determined to have occurred, the WTRUs may feedback (e.g., via an explicit or implicit indication) that a deviation has occurred to the NAP. Upon receiving such feedback, the NAP may decide to retrain the DQN. The NAP may decide to retrain the DQN upon condition that an indication of the deviation is received from any one of the WTRUs. As another example, the NAP may decide to retrain the DQN upon condition that indications are respectively received from a configured number of more of the WTRUs and/or are respectively received from certain specific WTRUs. Recalibration of the DQN weights may require one or more retraining samples (e.g., one or more uplink signal vectors and corresponding rewards). For example, a number of retraining samples (e.g., a number of pilot symbols) for updating the weights may be determined by a loss function of the DQN for a given failure probability δ and error rate ε _r . The retraining samples may be a sequence of pilot symbols transmitted by the WTRUs, such as where a pilot symbol or sequence thereof transmitted from each WTRU is received collectively as an uplink signal vector.

[0125] As another example, the NAP may determine information about retraining (e.g., any of the number of retraining samples for recalibrating the DQN weights, a size and/or configuration of the pilot sequences that carry the training samples) based on a target (e.g., desired) BER and/or throughput rate at the WTRUs. For example, a target BER and/or throughput rate can be transmitted as feedback by the WTRUs to the NAP. The NAP may then use the received feedback from the WTRU to determine any of a (e.g., required) number of retraining samples, a (e.g., required) pilot sequence size and/or a (e.g., required) configuration of the pilot sequences. The NAP may send (e.g., request) the number of retraining samples, size and/or configuration of the pilot sequences (e.g., which correspond to the desired BER and/or throughput rate) to the WTRUs. Upon receiving the number of retraining samples, size and/or configuration of the pilot sequences, such as in a received request, the WTRUs may proceed to respectively send uplink pilot sequences for retraining the DQN (e.g., recalibrating the DQN eights) to the BS and/or feedback the corresponding reward, such as by ACK/NACK signaling (e.g., ACK if QoS is met; otherwise NACK). Upon receiving the retraining samples and/or rewards, the NAP may proceed to retrain the DQN.

DNN Aided Adaptive Multi-User NOMA Symbol Detection

[0126] In certain representative embodiments, any of the WTRUs may be configured with a DNN. The DNN may perform and/or assist with a multi-user (e.g., multi-UE) NOMA symbol detection procedure. Weights of the DNN (e.g., DNN weights) may be predetermined offline and may then be stored at any (e.g., each) of the WTRUs. Upon receiving a signal vector (e.g., a NOMA data transmission) from the NAP, the WTRU may use the DNN for predicting a symbol from the received signal vector. It should be appreciated that a particular set of DNN weights may have been determined for a specific number of NOMA WTRUs. A particular set of DNN weights may result from training for a particular number of WTRUs and may not be generally applicable and/or accurate for symbol detection from a NOMA transmission for an arbitrary number of WTRUs. Different numbers of WTRUs (e.g., different NOMA WTRU combinations N _uc ) participating in a NOMA transmission may likely experience different interference as well as different signal-to-noise ratios. In some instances, configuring the WTRUs with such a DNN configuration may allow for any or all reliance on CSI estimation and/or pilot overhead to be circumvented.

[0127] For example, if a number of NOMA WTRUs is 2, then interference at a respective WTRU may be due to only the other single WTRU. However, if a number of NOMA WTRUs is 4, then interference at a respective WTRU may be due to contributions from the other 3 WTRUs. DNN weights selected for a 2 WTRU NOMA transmission may not accurately perform symbol detection for a 4 WTRU NOMA transmission due to such changes in interference as the number of WTRUs changes. It should be appreciated that similar shortcomings may exist with respect to other numbers of NOMA WTRUs.

[0128] In certain representative embodiments, training of a DNN may result in plural DNN weights which may include plural DNN weight sets which may be identified by respective indices and may correspond to NOMA transmissions for different numbers of WTRUs. As shown below, for example, upon concluding DNN training, the DNN training may result in DNN weights A which may include a plurality of DNN weight sets which may be identified by respective indices (e.g., ind=1, 2, 3 or 4) and may correspond to NOMA transmissions for different numbers of WTRUs (e.g., N _u =2, 4, 8, or 12). It should be appreciated that other DNN weight sets and numbers of users fall within the scope of the present disclosure.

[0129] FIG. 8 is a diagram illustrating a representative deep neural network (DNN) for multi- user NOMA symbol detection. In FIG. 8, a DNN may include an input layer xi, multiple hidden layers, and an output layer y _j . Each x _i may correspond to input feature (e.g., downlink signal vector), W _i is a weight matrix for the hidden layer (e.g., collectively forming a DNN weight set), b _i is a bias vector, u _i is an input from a hidden layer, and y _i are output features (e.g., predicted NOMA symbols) fro the DNN.

[0130] In certain representative embodiments, any (e.g., all) WTRUs may be configured to select and/or employ different DNN weights (e.g., different DNN weight sets) for symbol detection as there may be different numbers of NOMA WTRUs (e.g., different number of WTRUs participating in a NOMA transmission(s) during respective transmission time intervals). For example, a WTRU may select and/or employ a DNN weight set (e.g., index=1) for 2 NOMA WTRUs (e.g., N _uc =2) for a time period ti , such as transmission time interval (TTI). The same WTRU may select and/or employ another DNN weight set (e.g., index=2) for 4 NOMA WTRUs (e.g., N _uc =4) at another (e.g., subsequent) time period t ₂ , which may also be a TTI. Time periods may be consecutive and/or may have fixed or variable (e.g., dynamic) sizes. The DNN weight set for 2 NOMA WTRUs may be a result of training which is specific to capturing and/or compensating for the interference corresponding to 2-UE NOMA transmission(s) (e.g., downlink signal vector for k= 2). The DNN weight set for 4 NOMA WTRUs may be a result of training which is specific to capturing and/or compensating for the interference corresponding to 4-UE NOMA transmission(s) (e.g., downlink signal vector for k= 2). The DNN weight sets may be configured as a NOMA codebook, where the codebook comprises the different DNN weights trained (e.g., designed) for different NOMA WTRU combinations (e.g., different N _uc values).

[0131] FIG. 9 is a diagram illustrating a representative procedure for multi-user NOMA symbol detection. As shown in FIG. 9, the procedure may begin at Step 1 where the DNN may be trained (e.g., offline). For example, training may occur to determine a plurality of DNN weights (e.g., C _k as in FIG. 2) for different numbers of NOMA WTRUs (e.g., different values of k or N _uc ) using downlink received signals (e.g., and actual symbol vectors carried thereon. The DNN training may use techniques such as generative adversarial networks (GANs). Upon concluding training, the DNN for different numbers of NOMA WTRUs, the DNN weights (e.g., C _k ) may be distributed and/or stored at any (e.g., all) of the WTRUs.

[0132] For example, at Step 1 of FIG. 9, the set may comprise plural DNN weight sets such that the set where weight sets C ₁ , C ₂ , ... , C _N are the DNN weights designed for total NOMA WTRUs, respectively. Any (e.g., each) of the DNN weight sets may be designed offline using a feedforward DNN at the NAP. The training samples for the DNN may be represented as the set where may represent an actual (e.g., transmitted) downlink signal vector and s _k may represent a predicted (e.g., output) symbol vector and may represent an N ^th retraining sample. For example, the training samples may be obtained artificially using GANs, such as where the GANs produce both according to target communication characteristics and/or performance, such as desired system statistics. As another example, the training samples may be obtained by conducting one or more measurement campaigns, such as in the system, and storing the measurements in memory (e.g., at the WTRUs and/or NAP). In another example, the training samples may include any combination of artificially generated samples and measured samples. Feedback of the measured downlink received signals (e.g., to the NAP from the WTRUs may involve additional overhead.

[0133] During training at the NAP, the DNN takes the training samples (e.g., artificially generated and/or actual measured downlink received signal vector as the input and outputs a predicted symbol vector s. Any (e.g., each) DNN weight set may be considered to be optimized upon condition that a difference between a predicted symbol vector and an actual transmitted (e.g., true) symbol vector is minimized. The DNN employs the activation function (AF) in each layer of the DNN where the input of each AF is the output of the preceding layer A loss function LF reflecting the difference between the predicted symbol vector and the actual transmitted symbol vector may be computed as: where is the predicted symbol vector and s _i is the true symbol vector, and R is a regularization parameter to avoid overfitting. Training may continue for different numbers of NOMA WTRUs and may be stored in at the WTRUs (e.g., in a database) in order to generate a codebook (e.g., the set where the DNN weight sets may be indexed accordingly to the number of NOMA WTRUs. The codebook may be shared with and/or distributed to all WTRUs offline.

[0134] After training, the procedure may proceed to Step 2 where the NAP may select an index of the DNN weight set (e.g., C _k ) for NOMA transmission. During the inference phase, the NAP may identify the NOMA WTRU combination N _uc and the selected index may correspond to the NOMA WTRU combination N _uc which is determined by the DQN, such as at Step 2 of FIG. 5 (e.g., C _k for k= N _uc ). The index of the DNN weight set may also be selected without the use of the DQN to determine the NOMA WTRU combination N _uc . The NAP may select the index of the DNN for each time period t for NOMA transmission (e.g., NOMA TTI). As another example, the NAP may perform such selection after a configured number of time periods have elapsed (e.g., every two or more TTIs). The NAP may then send the selected index to the combination of WTRUs for a NOMA transmission for time period t. In certain representative embodiments, the WTRUs which are not selected for the NOMA transmission may be scheduled for orthogonal multiple access (OMA) transmission. For example, the NOMA WTRU combination N _uc may receive NOMA transmissions during the TTI whereas the unselected WTRUs may be scheduled for OMA transmissions during the TTI.

[0135] The WTRUs may receive the indication of the selected index (e.g., for the time period t) from the NAP. The WTRUs may also receive one or plural NOMA transmissions (e.g., during the time period t (e.g., TTI). Using the DNN weight set corresponding to the received index, the WTRUs may input a received NOMA transmission (e.g., to the DNN. The DNN, by way of the DNN weight set corresponding to the received index, may output symbols (e.g., a DNN predicted symbol vector) for the WTRUs of the NOMA WTRU combination N _uc , respectively. For example, any WTRU (e.g., each WTRU of the NOMA WTRU combination N _uc ) may receive one or more symbols (e.g., one or more DNN predicted symbols) as an output from the DNN.

[0136] In certain embodiments, the NAP may identify a NOMA WTRU combination N _uc and no DNN weight set may exist for the NOMA WTRU combination N _uc (e.g., no C _k is present at the NAP and/or WTRUs for k= N _uc ). Upon such condition, the NAP may select an index of a DNN weight set which is closest to the identified NOMA WTRU combination N _uc . The selected index may correspond to a number of WTRUs which may be greater than or less than the NOMA WTRU combination N _uc . A retraining procedure may be indicated or requested in order to train a new DNN weight set and/or recalibrate an existing DNN weight set which may then be indexed to the NOMA WTRU combination N _uc .

[0137] After the DNN has output a predicted symbol vector, any (e.g., each) WTRU of the NOMA WTRU combination N _uc may send an ACK/NACK report at Step 3 of FIG. 9. For example, any WTRU may send an ACK/NACK report at the end of the time period t (e.g., the NOMA TTI). The ACK/NACK report may include a BER and/or a throughput rate, such as for any of the NOMA transmission time period, a period of time for which the selected DNN weight set has been used, and/or another configured period of time. The NAP may receive ACK/NACK reports from the WTRUs (e.g., any, each or all of the WTRUs of the NOMA WTRU combination N _uc ).

[0138] In certain representative embodiments, the NAP may determine to perform retraining the DNN and/or for recalibrating any of the DNN weight sets and/or a (e.g., any) WTRU may trigger the NAP to perform retraining the DNN and/or for recalibrating any of the DNN weight sets. A NACK report may (or may not) include an indication for retraining the DNN and/or for recalibrating the selected DNN weight set. The NAP may determine to proceed to Step 4 of FIG. 9 with respect to information regarding any one TTI (e.g., a current TTI) and/or plural TTIs (e.g., a time period larger than a TTI or certain configured TTIs). For example, the NAP may proceed to Step 4 upon condition that any of a BER of any WTRU exceeding a threshold value, a sum of BERs of any (e.g., all) WTRUs exceeding a threshold value, a throughput of any WTRU dropping below a threshold value, a sum of throughputs of any (e.g., all) WTRUs dropping below a threshold value, a NACK being received, a frequency of received NACKs exceeding a threshold vale, a number of NACKs exceeding a threshold value, an indication for retraining the DNN and/or for recalibrating the selected DNN weight set being received, and/or any combination thereof.

[0139] After determining that retraining and/or recalibration is to be performed at Step 4 of FIG.

9, the NAP may proceed to send pilot symbols (e.g., pilot sequences) for retraining and/or recalibrating. The NAP may send pilot symbols to any (e.g., all) of the WTRUs. For example, the pilot symbols and/or number thereof sent to each WTRU may be specific to the respective WTRU. In some instances, retraining the DNN and/or recalibrating the DNN weight sets may require only a few training samples since each corresponding WTRU may be assumed to already have a codebook of DNN weight sets that were previously trained as closest fits for any (e.g., each) of the NOMA WTRU combinations. [0140] As another example, after determining that retraining and/or recalibration is to be performed at Step 4 of FIG. 9, any (e.g., all) of the WTRUs may feedback the received downlink signal vector to the BS for retraining. The received downlink signal vector may be quantized prior to being fedback to the BS. The BS may then perform retraining of the DNN and/or recalibration of the DNN weight sets. The BS may further generate differential values based on each the DNN weight set before and after recalibration. The BS may then send the differential values rather than the entire recalibrated weight set to the WTRUs and may include an index of the DNN weight set to which the differential values pertain (e.g., for each DNN weight set that is recalibrated). Upon receiving the differential values, the WTRUs may each use the differential values to update the

DNN weights to recreate the recalibrated weight set generated at the BS.

Example DNN Weight Set for Multi-UE NOMA Symbol Detection

[0141] The set may include of different DNN weight sets determined offline for different numbers of NOMA WTRUs. As shown below, the set may define trained DNN weight sets for a 2-layer and 8-node DNN architecture. The trained DNN weight sets may be stored in memory at the BS. The trained DNN weight sets may be shared with the WTRUs offline or may be downloaded online by the WTRUs. For example, the set may define trained DNN weight sets for a 2-layer and 8-node DNN architecture as shown below:

[0142] As an example, a number of NOME WTRUs (e.g., N _u ) which may be scheduled by the

NAP for NOMA transmission during inference may be 4 and the NAP may select the DNN weight set corresponding to N _u = 4. The index of 2 may be associated with N _u = 4 and this index may be explicitly or implicitly indicated to the WTRUs. Upon receiving such indication, any (e.g., each) of the WTRUs may initiate the DNN weight set corresponding to N _u = 4 for symbol detection.

[0143] As another example, a number of NOME WTRUs (e.g., N _u ) which may be scheduled by the NAP for NOMA transmission during inference may be 11 and the NAP may select one of the

DNN weight sets corresponding to a N _u which is closest to 11, such as N _u = 12. The index of 4 may be associated with N _u = 12 and this index may be explicitly or implicitly indicated to the

WTRUs. Upon receiving such indication, any (e.g., each) of the WTRUs may initiate the DNN weight set corresponding to N _u = 12 for symbol detection. Thereafter, such as after receiving a NOMA transmission from the NAP, any of the WTRUs may send an indication and/or request for retraining and/or recalibrating a DNN weight set, such as when a target threshold is not satisfied. This is referred to as transfer learning.

Example Simulation Results

[0144] FIG. 10 is a diagram illustrating a representative comparison of bit error rate (BER) using different DNN weight sets trained for different numbers of NOMA WTRUs. FIG. 10 illustrates various BERs as a function of signal-to-noise ratio (SNR) where DNN weight sets are trained for the specific numbers (e.g., sets) of NOMA WTRUs. It can be seen in FIG. 10 that a DNN weight set specifically trained for Nu = 2 NOMA WTRUs (e.g., 2 WTRUs sharing a same beam) achieves superior BER performance. A DNN weight set specifically designed for Nu = 3 NOMA WTRUs (e.g., 3 WTRUs sharing a same beam) achieves a similar BER performance. When the DNN weights trained for Nu = 3 NOMA WTRUs is invoked for a Nu = 2 NOMA transmission, a poor BER performance results. This may be due to the change in channel statistics from that of the trained samples. For example, retraining of the DNN may become necessary for recalibrating the DNN weights, and a number of training samples may depend on the variation in the channel statistics. Therefore, FIG. 10 demonstrates that it may be generally beneficial to train the set may include of different DNN weight sets determined offline for different numbers of NOMA WTRUs. The NAP may select the specific DNN weights depending on the number of NOMA WTRUs selected, such as output by the DQN and/or configured otherwise (e.g., per time interval).

[0145] FIG. 11 is a diagram illustrating a representative procedure for a BS for NOMA communication. As shown in FIG. 11, a DNN may be trained (e.g., offline training) for different numbers of WTRUs (e.g., different NOMA WTRU combinations N _uc ) participating in a NOMA transmission using training samples which maybe represented as the set where may be an actual (e.g., transmitted) downlink signal vector and s _k may be a predicted (e.g., output) symbol vector.

[0146] At a time t, the BS (e.g., NAP) may identify a set of users scheduled for NOMA transmission. For example, the BS may use the trained DQN to determine a NOMA WTRU combination N _uc . The WTRUs (e.g., WTRUs) may be scheduled for an upcoming (e.g., next) TTI. NOMA transmission of one or plural transport blocks may be scheduled for the TTI. The transport blocks may have a fixed or a dynamic size. Using the set of users scheduled for the NOMA transmission, a corresponding DNN weight set may be selected. An index associated with the selected DNN weight set may be communicated to the WTRUs. The index may be sent prior to the TTI or may be sent in a manner which overlaps with the TTI.

[0147] After performing NOMA transmission (e.g., after the TTI), the BS may receive an ACK/NACK from the WTRUs (e.g., the NOMA WTRU combination N _uc ) for the NOMA transmission. Upon condition that a predetermined number of ACKs are received, such as from one or more (e.g., all) WTRUs of the NOMA WTRU combination N _uc , the BS may identify a set of users scheduled for another NOMA transmission (e.g., a next TTI at time t=t+l) and the procedure may repeat as shown in FIG. 11. Upon condition that a predetermined number of NACKs are received or a predetermined number of NACKs with a retraining indication (e.g., retraining request) are received, the BS may determine that retraining of the DNN weights is to be performed. The BS may send an ACK to the WTRUs that retraining of the DNN (e.g., recalibrate the selected DNN weight set used for the NOMA transmission during the TTI) is to be performed. After determining that retraining is to be performed, the BS may proceed to transmit pilot sequences to any (e.g., each) of the WTRUs. The pilot sequences (e.g., pilot symbols) may be specific to each of the WTRUs.

[0148] In certain representative embodiments, the WTRUs may feedback the received pilot sequences to the BS. The BS may perform retraining of the DNN using the transmitted pilot sequences (e.g., and the received pilot sequences at the WTRUs (e.g., s _k ). After retraining, the BS may make the recalibrated weight set available to the WTRUs. For example, the BS may transmit the recalibrated weight set to the WTRUs and may also transmit an index of the recalibrated weight set. The WTRUs may transmit an ACK that the recalibrated weight set has been received.

[0149] In certain representative embodiments, any of the WTRUs may perform retraining of the DNN. For example, the BS may have to provide the transmitted pilot sequences (e.g., or an index thereof such as in a case where the pilot sequences are previously known the WTRUs. The transmitted pilot sequences (e.g., and the received pilot sequences (e.g., s _k ) may then be used to retrain the DNN. Upon concluding retraining, the WTRUs may send an ACK to the BS which may indicate that the selected weight set has been recalibrated. Upon receiving the ACK, the BS may proceed to continue to schedule another NOMA transmission.

[0150] FIG. 12 is a diagram illustrating a representative procedure for a WTRU for NOMA communication. As shown in FIG. 12, at a time t, a WTRU may receive an indication of a DNN weight set (e.g., DNN weight set index) to be used for NOMA communication (e.g., for a TTI). For example, the received indication may be used to select a DNN weight set index (e.g., from among the set which will be used for symbol detection in at least a next NOMA communication.

[0151] The WTRU may receive a downlink signal vector (e.g., from the BS (e.g., as part of or as the NOMA transmission), such as using configured resources for the NOMA transmission. The downlink signal vector may be received at the time t. For example, the time t may be a configured period (e.g., TTI). The WTRU may apply the DNN weight set which corresponds to the received DNN weight set index to the DNN and may determine one or more symbols (e.g., s _k ) using the received downlink signal vector (e.g., as an input to the DNN.

[0152] After determining (e.g., outputting from the DNN) the transmitted symbols, the WTRU may proceed to determine whether any transmission parameter requirements were met or not by the symbols determined by the DNN for the NOMA communication. For example, the WTRU may calculate whether a bit error rate of the determined symbols (e.g., in at least the TTI) satisfies a predetermined threshold and/or whether a throughput rate of the determined symbols (e.g., in at least the TTI) satisfies a predetermined threshold. Upon condition that the transmission parameter requirements were met, the WTRU may be configured to wait (e.g., at time t=t+l) for another NOMA communication (e.g., in a next TTI) and/or wait for another indication of a DNN weight set (e.g., DNN weight set index) to be used for NOMA communication to be received from the BS. The WTRU may also send an ACK to the BS, such as in response to determining the symbols using the DNN. The ACK may correspond to the NOMA communication or to multiple NOMA communications (e.g., TTIs individually or collectively). The ACK may indicate that any (e.g., all) quality -of-service (QoS) parameters configured for the NOMA transmission are satisfied.

[0153] Upon condition that any of the transmission parameter requirements have not been met, the WTRU may send a NACK to the BS, such as in response to determining the symbols using the DNN. The NACK may correspond to the NOMA communication or to multiple NOMA communications (e.g., TTIs individually or collectively). For example, the WTRU may send an indication for a retraining request to the BS (e.g., upon condition that any of the transmission parameter requirements have not been met). As another example, the WTRU may send a NACK to the BS and the NACK may include the indication for a retraining request. As another example, the indication for the retraining request may indicate the selected DNN weight set to be recalculated. After sending the indication for the retraining request to the BS, the WTRU and BS may proceed to perform retraining and/or recalibration as explained elsewhere herein.

[0154] FIG. 13 is a diagram illustrating a representative procedure 1300 for a WTRU to receive a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 13, the procedure 1300 may include the WTRU receiving (e.g., from a BS) information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among a plurality of NOMA symbol detection codewords at 1310. For example, the information indicating the NOMA symbol detection codeword may be an index associated with one of the plural NOMA symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the NOMA symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the NOMA detection codebook. At 1320, the WTRU may receive (e.g., from the BS) a NOMA transmission and may detect, using a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword, a symbol stream associated with the WTRU from the NOMA transmission. For example, the indicated NOMA symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received NOMA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol streams to obtain information associated with itself (e.g., transmitted data) from the NOMA transmission. After 1320, the WTRU may, on condition that an error occurs in the detection of the symbol stream associated with the WTRU from the NOMA transmission, send (e.g., to the BS) an (e.g., first) uplink transmission which includes information indicating a negative acknowledgement (NACK) associated with the NOMA transmission at 1330. For example, the feedback of the NACK from the WTRU to the BS may enable the BS to perform further processing to adapt the NOMA transmission procedures as described herein.

[0155] In certain representative embodiments, the WTRU may, prior to receiving the indicated NOMA symbol detection codeword at 1310, send (e.g., to the BS) an (e.g., second) uplink transmission to the BS. For example, the BS may use this uplink transmission for (e.g., adaptively) selecting which WTRUs are to perform NOMA communication as described herein. For example, this uplink transmission may be a SC-FDMA or OFDMA transmission from the WTRU to the BS. [0156] In certain representative embodiments, the indicated NOMA symbol detection codeword may be associated with a particular number of respective WTRUs related to the NOMA transmission. For example, the BS may select a combination of WTRUs which are intended to receive the NOMA transmission (e.g., a symbol stream therein) and may inform the respective WTRUs of the NOMA symbol detection codeword which is associated with the selected WTRU combination.

[0157] In certain representative embodiments, each of the NOMA symbol detection codewords may include or serve as an index to a particular weight set with which the neural network at the WTRU may be configured.

[0158] In certain representative embodiments, the information indicating the NOMA symbol detection codeword may be associated with a transmission time interval (TTI) for the NOMA transmission. For example, the TTI may be any of a slot, subframe, frame or a period of milliseconds.

[0159] In certain representative embodiments, the NACK (or ACK) associated with the NOMA transmission may be associated with any of one or more transport blocks of the NOMA transmission, a slot, a subframe, a frame and/or another TTI in which the NOMA transmission occurs.

[0160] In certain representative embodiments, the (e.g., first) uplink transmission may include information indicating a retraining request associated with the indicated NOMA symbol detection codeword. For example, the NACK fedback from the WTRU may serve as the retraining request. As another example, the WTRU may determine (e.g., based on the output of the neural network) that the indicated NOMA symbol detection codeword was unsatisfactory and may indicate that retraining of the BS may (e.g., should) be performed.

[0161] In certain representative embodiments, retraining of the neural network (e.g., to update the weight set corresponding to the indicated NOMA symbol detection codeword) may be performed at any of the BS and/or the WTRU.

[0162] For example, the WTRU may receive (e.g., in response to or after the retraining request) a downlink transmission which includes one or more pilot symbols (e.g., from the BS). The WTRU may proceed to send (e.g., to the BS) another (e.g., third) uplink transmission which includes measurement information associated with measuring the one or more pilot symbols. Thereafter, the WTRU may receive an updated weight set corresponding to the indicated NOMA symbol detection codeword. The updated weight set may be a set of differential values used to modify the indicated NOMA symbol detection codeword.

[0163] As another example, the WTRU may receive (e.g., in response to or after the retraining request) a downlink transmission which includes one or more pilot symbols (e.g., from the BS). The WTRU may proceed to perform processing to update the indicated NOMA symbol detection codeword using the one or more pilot symbols (e.g., measurements of the pilot symbols). [0164] In certain representative embodiments, the WTRU may receive (e.g., from the BS) control information and/or scheduling information which indicates a TTI of the NOMA transmission. For example, the control and/or scheduling information may indicate the NOMA symbol detection codeword associated with the TTI.

[0165] FIG. 14 is a diagram illustrating a representative procedure 1400 for a BS to transmit a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 14, the procedure 1400 may include the BS sending, to a plurality of WTRUs (e.g., a selected combination of WTRUs), information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among the plurality of NOMA symbol detection codewords at 1410. At 1420, the BS may send, to the plurality of WTRUs, the NOMA transmission which includes a plurality of symbol streams associated with the indicated NOMA symbol detection codeword at 1420. After 1420, the BS may receive a plurality of first uplink transmissions associated with the NOMA transmission, any of which may respectively include information indicating a negative acknowledgement (NACK) associated with the NOMA transmission on condition that an error occurs in the detection of one of the symbol streams using (e.g., at a WTRU) a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword at 1430.

[0166] In certain representative embodiments, the BS may perform retraining as described herein using the NACKs received from the WTRUs. In other embodiments, the BS may use the NACKs in combination with other feedback information to perform retraining as described herein.

[0167] FIG. 15 is a diagram illustrating a representative procedure 1500 for a BS for updating a neural network used for selecting WTRUs for a NOMA transmission. As shown in FIG. 15, the procedure 1500 may include the BS determining a set of WTRUs, associated with a NOMA transmission, from among a plurality of WTRUs using a neural network (e.g., a DQN) with a plurality of received uplink transmissions from the plurality of WTRUs as inputs to the neural network at 1510. For example, the set of WTRUs may be a combination of WTRUs which are selected by the neural network from among the plurality of WTRUs. At 1520, the BS may send, to the set of WTRUs, information indicating a NOMA symbol detection codeword associated with the NOMA transmission. For example, the information indicating the NOMA symbol detection codeword may be an index associated with one of the plural NOMA symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the NOMA symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the NOMA detection codebook. At 1530, the BS may send, to the set of WTRUs, the NOMA transmission which includes a plurality of symbol streams associated with the set of WTRUs. At 1540, the BS may receive, from the set of WTRUs, feedback information associated with the NOMA transmission. For example, respective feedback information, from one of the WTRUs in the set of WTRUs, may include ACK and/or NACK information for the NOMA transmission. As another example, the respective feedback information may include any of RSS, power, bit error rate, rate and/or other feedback as described herein. At 1550, the BS may, on condition that a threshold is not satisfied by the feedback information, send, to the plurality of WTRUs (e.g., all of the WTRUs from which the set of WTRUs were selected), an update (e.g., recalibration) request. For example, the update request may be associated with and/or include information indicating a configuration for a number of pilot symbols which the BS may use for recalibrating (e.g., updating the neural network). As an example, the BS may determine the number of pilot symbols using the feedback information associated with the NOMA transmission. After sending the update request at 1550, the BS may receive, from the plurality of WTRUs, a plurality of pilot symbols (e.g., as configured) at 1560. For example, the BS may receive a pilot symbol sequence from a respective WTRU which is made up of the indicated number of pilot symbols per the update request. At 1570, the BS may perform updating (e.g., recalibration) of the neural network (e.g., DQN) using the plurality of pilot symbols received at 1560. For example, the updating of the neural network may be performed as described herein. As an example, the trained DQN weights in step 1 of FIG. 5 may be updated on the basis of the received pilot symbols at 1560.

[0168] In certain representative embodiments, the feedback information received from a WTRU at 1540 may include information indicating an ACK and/or a NACK associated with the NOMA transmission. For example, whether to perform an update may be determined by the BS on the basis of the threshold including a threshold number of NACKs associated with the NOMA transmission.

[0169] In certain representative embodiments, the feedback information received from a WTRU at 1540 may include information indicating a rate (e.g., BER) associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold BER for the NOMA transmission.

[0170] In certain representative embodiments, the feedback information received from a WTRU at 1540 may include information indicating an RSS associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold RSS associated with the NOMA transmission.

[0171] In certain representative embodiments, the feedback information received from a WTRU at 1540 may include information indicating a power measurement associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold power associated with the NOMA transmission.

[0172] In certain representative embodiments, a determination (e.g., by the BS) of the number of the pilot symbols included in the downlink transmission may be based on a target rate. For example, the target rate may be indicated by the WTRU. For example, the WTRU may include the target rate in the feedback information at 1540.

[0173] In certain representative embodiments, the pilot symbols received at 1560 may include one or more reference signals.

[0174] In certain representative embodiments, the determination of the set of WTRUs at 1510 may use single carrier-frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals) as the inputs to the neural network at the BS.

[0175] FIG. 16 is a diagram illustrating a representative procedure 1600 for a WTRU for updating a neural network used for selecting WTRUs for a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 16, the procedure 1600 may include the WTRU receiving, from the BS, information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among a plurality of NOMA symbol detection codewords at 1610. At 1620, the WTRU may receive, from the BS, the NOMA transmission and detect, using a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword, a symbol stream associated with the WTRU from the NOMA transmission. After 1620, the WTRU may proceed to send, to the BS, feedback information associated with the NOMA transmission at 1630. For example, the feedback information may include ACK/NACK information associated with the NOMA transmission and/or other feedback information as described herein. At 1640, the WTRU may receive, from the BS, information indicating an update (e.g., recalibration) request. For example, the update request may be associated with and/or include a configuration of pilot symbols to be used by the BS for updating (e.g., recalibration). After receiving the update request, the WTRU may send, to the base station, a plurality of pilot symbols associated with the update request at 1650.

[0176] In certain representative embodiments, the feedback information at 1630 may include information indicating an ACK and/or a NACK associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold number of NACKs associated with the NOMA transmission.

[0177] In certain representative embodiments, the feedback information received at 1630 may include information indicating a rate (e.g., BER) associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold BER for the NOMA transmission.

[0178] In certain representative embodiments, the feedback information at 1630 may include information indicating an RSS associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold RSS associated with the NOMA transmission.

[0179] In certain representative embodiments, the feedback information received at 1630 may include information indicating a power measurement associated with the NOMA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold power associated with the NOMA transmission.

[0180] In certain representative embodiments, a determination (e.g., by the BS) of the number of the pilot symbols included in the downlink transmission may be based on a target rate. For example, the target rate may be indicated by the WTRU. For example, the WTRU may include the target rate in the feedback information at 1630.

[0181] In certain representative embodiments, the pilot symbols transmitted at 1650 may include one or more reference signals.

[0182] In certain representative embodiments, the WTRU may send one or more single carrier- frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals) prior to receiving the NOMA symbol detection codeword at 1610.

[0183] FIG. 17 is a diagram illustrating a representative procedure 1700 for a BS to select WTRUs to receive a NOMA transmission. As shown in FIG. 17, the procedure 1700 may include the BS receiving a plurality of uplink transmissions from a plurality of WTRUs at 1710. For example, the uplink transmissions may be one or more single carrier-frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals). At 1720, the BS may determine a set of WTRUs, associated with a non-orthogonal multiple access (NOMA) transmission, from among the plurality of WTRUs using a neural network with the plurality of received uplink transmissions as inputs to the neural network. For example, the BS may select the set (e.g., combination) of WTRUs using a DQN as described herein. After 1720, the BS may send, to the determined set of WTRUs, information indicating a NOMA symbol detection codeword associated with the NOMA transmission at 1730. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. At 1740, after sending the information indicating the NOMA symbol detection codeword at 1730, the BS may send, to the determined set of WTRUs, the NOMA transmission which includes a plurality of symbol streams associated with the determined set of WTRUs.

[0184] In certain representative embodiments, the BS may determine the NOMA symbol detection codeword from among the plurality of NOMA symbol detection codewords using the determined set of WTRUs. For example, a NOMA symbol detection codeword may be selected by the BS which is associated with a number of WTRUs which is closest to the number of WTRUs in the determined set of WTRUs.

[0185] In certain representative embodiments, the BS may receive feedback information associated with the NOMA transmission from the determined set of WTRUs after 1740.

[0186] In certain representative embodiments, the feedback information associated with the NOMA transmission from at least one WTRU of the determined set of WTRUs may include information indicating an update request associated with the NOMA symbol detection codeword. [0187] In certain representative embodiments, the BS may determine that a plurality of neural network weights associated with the NOMA symbol detection codeword are to be updated based on the feedback information associated with the NOMA transmission.

[0188] In certain representative embodiments, the BS may, on condition it is determined that the plurality of neural network weights associated with the NOMA symbol detection codeword are to be updated, send one or more pilot symbols to the at least one WTRU of the determined set of WTRUs. For example, the number of pilot symbols may be determined using the feedback information from the WTRUs.

[0189] In certain representative embodiments, the BS may receive (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs. For example, the BS may perform processing to update the plurality of neural network weights associated with the NOMA symbol detection codeword using the (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs.

[0190] In certain representative embodiments, the BS may send, to the WTRUs (e.g., the determined set of WTRUs), information indicating the plurality of updated neural network weights associated with the NOMA symbol detection codeword. For example, the BS may send differential values which the WTRUs may use to update the respective NOMA symbol detection codeword.

[0191] FIG. 18 is a diagram illustrating a representative procedure 1800 for a WTRU to receive a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. The procedure 1800 may include the WTRU sending, to the BS, an uplink transmission at 1810. For example, the uplink transmission may be one or more single carrier-frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals). At 1820, the WTRU may receive, from the BS, information indicating a NOMA symbol detection codeword associated with a NOMA transmission. After 1820, the WTRU may receive, from the BS, the NOMA transmission at 1830. For example, the NOMA transmission may include respective symbol streams for the WTRUs which received the NOMA symbol detection codeword at 1820. At 1840, the WTRU may detect, using a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword, a symbol stream associated with the WTRU from the NOMA transmission which includes a plurality of symbol streams associated with a set of WTRUs.

[0192] In certain representative embodiments, the NOMA symbol detection codeword may be selected by the BS which is associated with a number of WTRUs which is closest to the number of WTRUs in the determined set of WTRUs.

[0193] In certain representative embodiments, the WTRU may send feedback information associated with the NOMA transmission to the BS after 1840.

[0194] In certain representative embodiments, the feedback information associated with the NOMA transmission from the WTRU may include information indicating an update request associated with the NOMA symbol detection codeword.

[0195] In certain representative embodiments, the BS may determine that a plurality of neural network weights associated with the NOMA symbol detection codeword are to be updated based on the feedback information from the WTRU at 1840. [0196] In certain representative embodiments, the BS may, on condition it is determined that the plurality of neural network weights associated with the NOMA symbol detection codeword are to be updated, send one or more pilot symbols to the WTRU. For example, the number of pilot symbols may be determined using the feedback information from the WTRU.

[0197] In certain representative embodiments, the WTRU may send (e.g., second) feedback information associated with the one or more pilot symbols received from the BS. For example, the BS may perform processing to update the plurality of neural network weights associated with the NOMA symbol detection codeword using the (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs. [0198] In certain representative embodiments, the WTRU may receive information indicating the plurality of updated neural network weights associated with the NOMA symbol detection codeword. For example, the BS may send differential values which the WTRU may use to update the respective NOMA symbol detection codeword.

[0199] In certain representative embodiments, the WTRU may perform processing to update the plurality of neural network weights associated with the NOMA symbol detection codeword using the one or more pilot symbols from the BS. For example, the updating may occur at the WTRU without feedback of the received pilot symbols to the BS.

[0200] In certain representative embodiments, a transmitter (e.g., a base station) may use a set of radio resources (e.g., time, frequency and/or code) to send the MA transmission. Those skilled in the art will understand that any multiple access scheme (e.g., NOMA, SC-FDMA, OFDMA and the like) may be used to send the MA transmission. As examples, the NOMA transmission may include any of a power domain NOMA transmission, a SCMA transmission, a PDMA transmission, a RSMA transmission, a MUSA transmission, a IGMA transmission, a WSMA transmission and/or an IDMA transmission. As examples, the OMA transmission may include an OFDMA transmission.

[0201] FIG. 19 is a diagram illustrating a representative procedure 1900 for a WTRU to receive a multiple access (MA) transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein.

[0202] As shown in FIG. 19, the procedure 1900 may include the WTRU receiving (e.g., from a BS) information indicating a symbol detection codeword, associated with a MA transmission, from among a plurality of symbol detection codewords at 1910. For example, the information indicating the symbol detection codeword may be an index associated with one of the plural symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs and/or the MA transmission). As another example, the information indicating the symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the symbol detection codebook. At 1920, the WTRU may receive (e.g., from the BS) the MA transmission and may detect, using a neural network configured with a weight set associated with the indicated symbol detection codeword, a symbol stream associated with the WTRU from the MA transmission. For example, the indicated symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received MA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol streams to obtain information associated with itself from the MA transmission. After 1920, the WTRU may, on condition that an error occurs in the detection of the symbol stream associated with the WTRU, send (e.g., to the BS) an (e.g., first) uplink transmission which includes information indicating a negative acknowledgement (NACK) associated with the MA transmission at 1930. For example, the feedback of the NACK from the WTRU to the BS may enable the BS to perform further processing to adapt a next MA transmission using procedures as described herein.

[0203] In certain representative embodiments, the WTRU may, prior to receiving the indicated symbol detection codeword at 1310, send (e.g., to the BS) an (e.g., second) uplink transmission to the BS. For example, the BS may use this uplink transmission for (e.g., adaptively) selecting which WTRUs are to perform MA communication as described herein. For example, this uplink transmission may use a transmission scheme different than that used for the MA transmission.

[0204] In certain representative embodiments, the indicated symbol detection codeword may be associated with a particular number of respective WTRUs related to the MA transmission. For example, the BS may select a combination of WTRUs which are intended to receive the MA transmission (e.g., a symbol stream therein) and may inform the respective WTRUs of the symbol detection codeword which is associated with the selected WTRU combination.

[0205] In certain representative embodiments, each of the symbol detection codewords may be respectively associated with (e.g., serve as an index to) a particular weight set with which the neural network at the WTRU may be configured.

[0206] In certain representative embodiments, the information indicating the symbol detection codeword may be associated with a transmission time interval (TTI) for the MA transmission. For example, the TTI may be any of a slot, subframe, frame or a period of milliseconds. [0207] In certain representative embodiments, the NACK (or ACK) associated with the MA transmission may be associated with any of one or more transport blocks of the transmission, a slot, a subframe, a frame and/or another TTI in which the MA transmission occurs.

[0208] In certain representative embodiments, the (e.g., first) uplink transmission may include information indicating a retraining request associated with the indicated symbol detection codeword. For example, the NACK feedback from the WTRU may serve as the retraining request. As another example, the WTRU may determine (e.g., based on the output of the neural network) that the indicated symbol detection codeword was unsatisfactory and may indicate that retraining of the BS may (e.g., should) be performed.

[0209] In certain representative embodiments, retraining of the neural network (e.g., to update the weight set corresponding to the indicated symbol detection codeword) may be performed at any of the BS and/or the WTRU.

[0210] For example, the WTRU may receive (e.g., in response to or after the retraining request) a downlink transmission which includes one or more pilot symbols (e.g., from the BS). The WTRU may proceed to send (e.g., to the BS) another (e.g., third) uplink transmission which includes measurement information associated with measuring the one or more pilot symbols. Thereafter, the WTRU may receive an updated weight set corresponding to the indicated symbol detection codeword. The updated weight set may be a set of differential values used to modify the indicated symbol detection codeword.

[0211] As another example, the WTRU may receive (e.g., in response to or after the retraining request) a downlink transmission which includes one or more pilot symbols (e.g., from the BS). The WTRU may proceed to perform processing to update the indicated symbol detection codeword using the one or more pilot symbols (e.g., measurements of the pilot symbols).

[0212] In certain representative embodiments, the WTRU may receive (e.g., from the BS) control information and/or scheduling information which indicates a TTI of the MA transmission. For example, the control and/or scheduling information may indicate the symbol detection codeword associated with the TTI.

[0213] FIG. 20 is a diagram illustrating a representative procedure 2000 for a BS to transmit a MA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 20, the procedure 2000 may include the BS sending, to a plurality of WTRUs (e.g., a selected combination of WTRUs), information indicating a symbol detection codeword, associated with a transmission, from among the plurality of symbol detection codewords at 2010. At 2020, the BS may send, to the plurality of WTRUs, the transmission which includes a plurality of symbol streams associated with the indicated symbol detection codeword at 2020. After 2020, the BS may receive a plurality of first uplink transmissions associated with the MA transmission, any of which may respectively include information indicating a negative acknowledgement (NACK) associated with the MA transmission on condition that an error occurs in the detection of one of the symbol streams using a neural network configured with a weight set associated with the indicated symbol detection codeword at 2030.

[0214] In certain representative embodiments, the BS may perform retraining as described herein using the NACKs received from the WTRUs. In other embodiments, the BS may use the NACKs in combination with other feedback information to perform retraining as described herein.

[0215] FIG. 21 is a diagram illustrating a representative procedure 2100 for a BS for updating a neural network used for selecting WTRUs for a MA transmission. As shown in FIG. 21, the procedure 2100 may include the BS determining a set of WTRUs, associated with a transmission, from among a plurality of WTRUs using a neural network (e.g., a DQN) with a plurality of received uplink transmissions from the plurality of WTRUs as inputs to the neural network at 2110. For example, the set of WTRUs may be a combination of WTRUs which are selected by the neural network from among the plurality of WTRUs. At 2120, the BS may send, to the set of WTRUs, information indicating a symbol detection codeword associated with the MA transmission. For example, the information indicating the symbol detection codeword may be an index associated with one of the plural symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the detection codebook. At 2130, the BS may send, to the set of WTRUs, the MA transmission which includes a plurality of symbol streams associated with the set of WTRUs. At 2140, the BS may receive, from the set of WTRUs, feedback information associated with the MA transmission. For example, respective feedback information, from one of the WTRUs in the set of WTRUs, may include ACK and/or NACK information for the MA transmission. As another example, the respective feedback information may include any of RSS, power, bit error rate, rate and/or other feedback as described herein. At 2150, the BS may, on condition that a threshold is not satisfied by the feedback information, send, to the plurality of WTRUs (e.g., all of the WTRUs from which the set of WTRUs were selected), an update (e.g., recalibration) request. For example, the update request may be associated with and/or include information indicating a configuration for a number of pilot symbols which the BS may use for recalibrating (e.g., updating the neural network). As an example, the BS may determine the number of pilot symbols using the feedback information associated with the MA transmission. After sending the update request at 2150, the BS may receive, from the plurality of WTRUs, a plurality of pilot symbols (e.g., as configured) at 2160. For example, the BS may receive a pilot symbol sequence from a respective WTRU which is made up of the indicated number of pilot symbols per the update request. At 2170, the BS may perform updating (e.g., recalibration) of the neural network (e.g., DQN) using the plurality of pilot symbols received at 2160. For example, the updating of the neural network may be performed as described herein. As an example, the trained DQN weights in step 1 of FIG. 5 may be updated on the basis of the received pilot symbols at 2160.

[0216] In certain representative embodiments, the feedback information received from a WTRU at 2140 may include information indicating an ACK and/or a NACK associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold number of NACKs associated with the MA transmission.

[0217] In certain representative embodiments, the feedback information received from a WTRU at 2140 may include information indicating a rate (e.g., BER) associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold BER for the MA transmission.

[0218] In certain representative embodiments, the feedback information received from a WTRU at 2140 may include information indicating an RSS associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold RSS associated with the MA transmission.

[0219] In certain representative embodiments, the feedback information received from a WTRU at 2140 may include information indicating a power measurement associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold power associated with the MA transmission.

[0220] In certain representative embodiments, a determination (e.g., by the BS) of the number of the pilot symbols included in the downlink transmission may be based on a target rate. For example, the target rate may be indicated by the WTRU. For example, the WTRU may include the target rate in the feedback information at 2140.

[0221] In certain representative embodiments, the pilot symbols received at 2160 may include one or more reference signals. [0222] In certain representative embodiments, the determination of the set of WTRUs at 2110 may use single carrier-frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals) as the inputs to the neural network at the BS.

[0223] FIG. 22 is a diagram illustrating a representative procedure 2200 for a WTRU for updating a neural network used for selecting WTRUs for a MA transmission. For example, the WTRU 102 may be configured to store, or otherwise be provided with, store a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU 102 as described herein. As shown in FIG. 22, the procedure 2200 may include the WTRU 102 receiving, from the BS 202, information indicating a symbol detection codeword, associated with a transmission, from among a plurality of symbol detection codewords at 2210. At 2220, the WTRU 102 may receive, from the BS 202, the MA transmission and detect, using a neural network configured with a weight set associated with the indicated symbol detection codeword, a symbol stream associated with the WTRU from the MA transmission. After 2220, the WTRU 102 may proceed to send, to the BS 202, feedback information associated with the MA transmission at 2230. For example, the feedback information may include ACK/NACK information associated with the MA transmission and/or other feedback information as described herein. At 2240, the WTRU 102 may receive, from the BS 202, information indicating an update (e.g., recalibration) request. For example, the update request may be associated with and/or include a configuration of pilot symbols to be used by the BS 202 for updating. After receiving the update request, the WTRU 102 may send, to the BS 202, a plurality of pilot symbols associated with the update request at 2250.

[0224] In certain representative embodiments, the feedback information at 2230 may include information indicating an ACK and/or a NACK associated with the MA transmission. For example, whether to perform updating may be determined by the BS 202 on the basis of the threshold including a threshold number of NACKs associated with the MA transmission.

[0225] In certain representative embodiments, the feedback information received at 2230 may include information indicating a rate (e.g., BER) associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold BER for the MA transmission.

[0226] In certain representative embodiments, the feedback information at 2230 may include information indicating an RSS associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold RSS associated with the MA transmission.

[0227] In certain representative embodiments, the feedback information received at 2230 may include information indicating a power measurement associated with the MA transmission. For example, whether to perform updating may be determined by the BS on the basis of the threshold including a threshold power associated with the MA transmission.

[0228] In certain representative embodiments, a determination (e.g., by the BS) of the number of the pilot symbols included in the downlink transmission may be based on a target rate. For example, the target rate may be indicated by the WTRU. For example, the WTRU may include the target rate in the feedback information at 2230.

[0229] In certain representative embodiments, the pilot symbols transmitted at 2250 may include one or more reference signals.

[0230] In certain representative embodiments, the WTRU may send one or more single carrier- frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals) prior to receiving the symbol detection codeword at 2210. For example, these transmissions prior to 2210 may be used by the BS to select the symbol detection codeword as described herein.

[0231] FIG. 23 is a diagram illustrating a representative procedure 2300 for a BS to select WTRUs to receive a MA transmission. As shown in FIG. 23, the procedure 2300 may include the BS receiving a plurality of uplink transmissions from a plurality of WTRUs at 2310. For example, the uplink transmissions may be one or more single carrier-frequency division multiple access (SC-FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals). At 2320, the BS may determine a set of WTRUs, associated with a MA transmission, from among the plurality of WTRUs using a neural network with the plurality of received uplink transmissions as inputs to the neural network. For example, the BS may select the set (e.g., combination) of WTRUs using a DQN as described herein. After 2320, the BS may send, to the determined set of WTRUs, information indicating a symbol detection codeword associated with the MA transmission at 2330. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. At 2340, after sending the information indicating the symbol detection codeword at 2330, the BS may send, to the determined set of WTRUs, the MA transmission which includes a plurality of symbol streams associated with the determined set of WTRUs. [0232] In certain representative embodiments, the BS may determine the symbol detection codeword from among the plurality of symbol detection codewords using the determined set of WTRUs. For example, a symbol detection codeword may be selected by the BS which is associated with a number of WTRUs which is closest to the number of WTRUs in the determined set of WTRUs.

[0233] In certain representative embodiments, the BS may receive feedback information associated with the MA transmission from the determined set of WTRUs after 2340.

[0234] In certain representative embodiments, the feedback information associated with the MA transmission from at least one WTRU of the determined set of WTRUs may include information indicating an update request associated with the symbol detection codeword.

[0235] In certain representative embodiments, the BS may determine that a plurality of neural network weights associated with the symbol detection codeword are to be updated based on the feedback information associated with the MA transmission.

[0236] In certain representative embodiments, the BS may, on condition it is determined that the plurality of neural network weights associated with the symbol detection codeword are to be updated, send one or more pilot symbols to the at least one WTRU of the determined set of WTRUs. For example, the number of pilot symbols may be determined using the feedback information from the WTRUs.

[0237] In certain representative embodiments, the BS may receive (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs. For example, the BS may perform processing to update the plurality of neural network weights associated with the symbol detection codeword using the (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs.

[0238] In certain representative embodiments, the BS may send, to the WTRUs (e.g., the determined set of WTRUs), information indicating the plurality of updated neural network weights associated with the symbol detection codeword. For example, the BS may send differential values which the WTRUs may use to update the respective symbol detection codeword.

[0239] FIG. 24 is a diagram illustrating a representative procedure 2400 for a WTRU to receive a MA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. The procedure 2400 may include the WTRU sending, to the BS, an uplink transmission at 2410. For example, the uplink transmission may be one or more single carrier-frequency division multiple access (SC- FDMA) or orthogonal frequency division multiple access (OFDMA) transmissions (e.g., of data and/or signals). At 2420, the WTRU may receive, from the BS, information indicating a symbol detection codeword associated with a MA transmission. After 2420, the WTRU may receive, from the BS, the MA transmission at 2430. For example, the MA transmission may include respective symbol streams for the WTRUs which received the symbol detection codeword at 2420. At 2440, the WTRU may detect, using a neural network configured with a weight set associated with the indicated symbol detection codeword, a symbol stream associated with the WTRU from the MA transmission which includes a plurality of symbol streams associated with a set of WTRUs.

[0240] In certain representative embodiments, the symbol detection codeword may be selected by the BS which is associated with a number of WTRUs which is closest to (e.g., greater than) the number of WTRUs in the determined set of WTRUs.

[0241] In certain representative embodiments, the WTRU may send feedback information associated with the MA transmission to the BS after 2440.

[0242] In certain representative embodiments, the feedback information associated with the MA transmission from the WTRU may include information indicating an update request associated with the symbol detection codeword.

[0243] In certain representative embodiments, the BS may determine that a plurality of neural network weights associated with the symbol detection codeword are to be updated based on the feedback information from the WTRU at 2440.

[0244] In certain representative embodiments, the BS may, on condition it is determined that the plurality of neural network weights associated with the symbol detection codeword are to be updated, send one or more pilot symbols to the WTRU. For example, the number of pilot symbols may be determined using the feedback information from the WTRU.

[0245] In certain representative embodiments, the WTRU may send (e.g., second) feedback information associated with the one or more pilot symbols received from the BS. For example, the BS may perform processing to update the plurality of neural network weights associated with the symbol detection codeword using the (e.g., second) feedback information associated with the one or more pilot symbols from the at least one WTRU of the determined set of WTRUs.

[0246] In certain representative embodiments, the WTRU may receive information indicating the plurality of updated neural network weights associated with the symbol detection codeword. For example, the BS may send differential values which the WTRU may use to update the respective symbol detection codeword. [0247] In certain representative embodiments, the WTRU may perform processing to update the plurality of neural network weights associated with the symbol detection codeword using the one or more pilot symbols from the BS. For example, the updating may occur at the WTRU without feedback of the received pilot symbols to the BS.

[0248] FIG. 25 is a diagram illustrating a representative procedure 2500 for a WTRU to receive a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 25, the procedure 2500 may include the WTRU receiving (e.g., from a BS) information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among a plurality of NOMA symbol detection codewords at 2510. For example, the information indicating the NOMA symbol detection codeword may be an index associated with one of the plural NOMA symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the NOMA symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the NOMA detection codebook. At 2520, the WTRU may receive (e.g., from the BS) a NOMA transmission and may detect, using a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword, a symbol stream associated with the WTRU from the NOMA transmission. For example, the indicated NOMA symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received NOMA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol stream to obtain information associated with itself (e.g., transmitted) from the NOMA transmission. After 2520, the WTRU may, on condition that an error occurs in the detection of the symbol stream associated with the WTRU from the NOMA transmission, send (e.g., to the BS) a first uplink transmission which includes information indicating a negative acknowledgement (NACK) associated with the NOMA transmission at 2530. At 2540, after sending the first uplink transmission, the WTRU may receive (e.g., from the BS) a downlink transmission which includes one or more pilot symbols. After 2540, the WTRU may update the weight set of the neural network associated with the indicated NOMA detection codeword using measurement information associated with the one or more pilot symbols. For example, the weight set updating may be performed using the techniques described herein. [0249] FIG. 26 is a diagram illustrating a representative procedure 2600 for a WTRU to receive a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 26, the procedure 2600 may include the WTRU receiving (e.g., from a BS) information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among a plurality of NOMA symbol detection codewords at 2610. For example, the information indicating the NOMA symbol detection codeword may be an index associated with one of the plural NOMA symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the NOMA symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the NOMA detection codebook. At 2620, the WTRU may receive (e.g., from the BS) a NOMA transmission and may detect, using a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword, a symbol stream associated with the WTRU from the NOMA transmission. For example, the indicated NOMA symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received NOMA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol streams to obtain information associated with itself (e.g., transmitted data) from the NOMA transmission. After 2620, the WTRU may, after detecting the symbol stream associated with the WTRU from the NOMA transmission, send (e.g., to the BS) an (e.g., first) uplink transmission which includes information indicating a negative acknowledgement (NACK) associated with the NOMA transmission at 2630. For example, the feedback of the NACK from the WTRU to the BS may enable the BS to perform further processing to adapt the NOMA transmission procedures as described herein.

[0250] FIG. 27 is a diagram illustrating a representative procedure 2700 for a BS to transmit a NOMA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, a plurality of NOMA symbol detection codewords. Each of the NOMA symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 27, the procedure 2700 may include the BS sending, to a plurality of WTRUs (e.g., a selected combination of WTRUs), information indicating a NOMA symbol detection codeword, associated with a NOMA transmission, from among the plurality of NOMA symbol detection codewords at 2710. At 2720, the BS may send, to the plurality of WTRUs, the NOMA transmission which includes a plurality of symbol streams associated with the indicated NOMA symbol detection codeword. After 2720, the BS may receive a plurality of first uplink transmissions associated with the NOMA transmission, any of which may respectively include information indicating an acknowledgement (ACK) associated with the NOMA transmission on condition that a respective one of the symbol streams was detected using (e.g., at a WTRU) a neural network configured with a weight set associated with the indicated NOMA symbol detection codeword at 2730.

[0251] FIG. 28 is a diagram illustrating a representative procedure 2800 for a WTRU to receive a MA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 28, the procedure 2800 may include the WTRU receiving (e.g., from a BS) information indicating a symbol detection codeword, associated with a MA transmission, from among a plurality of symbol detection codewords at 2810. For example, the information indicating the symbol detection codeword may be an index associated with one of the plural symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the symbol detection codebook. At 2820, the WTRU may receive (e.g., from the BS) a MA transmission and may detect, using a neural network configured with a weight set associated with the indicated symbol detection codeword, a symbol stream associated with the WTRU from the MA transmission. For example, the indicated symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received MA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol streams to obtain information associated with itself (e.g., transmitted data) from the MA transmission. After 2820, the WTRU may, after detecting the symbol stream associated with the WTRU from the MA transmission, send (e.g., to the BS) an (e.g., first) uplink transmission which includes information indicating an acknowledgement (ACK) associated with the MA transmission at 2830. For example, the feedback of the ACK from the WTRU to the BS may enable the BS to perform further processing to adapt the MA transmission procedures as described herein. [0252] FIG. 29 is a diagram illustrating a representative procedure 2900 for a BS to transmit a MA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 29, the procedure 2900 may include the BS sending, to a plurality of WTRUs (e.g., a selected combination of WTRUs), information indicating a symbol detection codeword, associated with a MA transmission, from among the plurality of symbol detection codewords at 2910. At 2920, the BS may send, to the plurality of WTRUs, the MA transmission which includes a plurality of symbol streams associated with the indicated symbol detection codeword. After 2920, the BS may receive a plurality of first uplink transmissions associated with the MA transmission, any of which may respectively include information indicating an acknowledgement (ACK) associated with the MA transmission on condition that a respective one of the symbol streams was detected using (e.g., at a WTRU) a neural network configured with a weight set associated with the indicated symbol detection codeword at 2930.

[0253] FIG. 30 is a diagram illustrating a representative procedure 3000 for a WTRU to receive a MA transmission. For example, the WTRU may be configured to store, or otherwise be provided with, store a plurality of symbol detection codewords. Each of the symbol detection codewords may be used to respectively configure a neural network, such as the neural network of FIG. 8, to output a symbol stream corresponding to the WTRU as described herein. As shown in FIG. 30, the procedure 3000 may include the WTRU receiving (e.g., from a BS) information indicating a symbol detection codeword, associated with a MA transmission, from among a plurality of symbol detection codewords at 3010. For example, the information indicating the NOMA symbol detection codeword may be an index associated with one of the plural NOMA symbol detection codewords (e.g., a weight set corresponding to a particular combination of WTRUs). As another example, the information indicating the NOMA symbol detection codeword may be a weight set which may be used to configure the neural network at the WTRU. In some embodiments, the weight set may be a differential weight set which may be used to update the symbol detection codebook. At 3020, the WTRU may receive (e.g., from the BS) a MA transmission and may detect, using a neural network configured with a weight set associated with the indicated symbol detection codeword, a symbol stream associated with the WTRU from the MA transmission. For example, the indicated symbol detection codeword may be used to configure a deep neural network as described herein. The configured neural network may then take the received MA transmission (e.g., as an input) and may proceed to output one or more symbol streams. The WTRU may perform processing on the output symbol streams to obtain information associated with itself (e.g., transmitted data) from the MA transmission. After 3020, the WTRU may, on condition that an error occurs in the detection of the symbol stream associated with the WTRU from the MA transmission, send (e.g., to the BS) a first uplink transmission which includes information indicating a negative acknowledgement (NACK) associated with the MA transmission at 3030. At 3040, after sending the first uplink transmission, the WTRU may receive (e.g., from the BS) a downlink transmission which includes one or more pilot symbols. After 3040, the WTRU may update the weight set of the neural network associated with the indicated NOMA detection codeword using measurement information associated with the one or more pilot symbols. For example, the weight set updating may be performed using the techniques described herein.

[0254] In certain representative embodiments, a wireless transmit/receive unit (WTRU) may implement a method of non-orthogonal multiple access (NOMA) communication. The method may include receiving, by the WTRU, an indication of a deep neural network (DNN) weight set for a NOMA transmission. The WTRU may receive, from a base station (BS) or network entity (NE), the NOMA transmission (e.g., as scheduled). The WTRU may proceed to apply the DNN weight set to a DNN, input the received NOMA transmission (e.g., to the DNN), and obtain a symbol vector output from the DNN (e.g., to which the indicated DNN weight set is applied and the received NOMA transmission is input).

[0255] For example, the WTRU may obtain the symbol vector from the DNN without inputting channel state information (CSI) to the DNN.

[0256] For example, the indication of the DNN weight set may be for the NOMA transmission in a predetermined time period (e.g., associated with a slot, subframe, frame or other TTI).

[0257] For example, the WTRU may send (e.g., to the BS or NE) feedback information which is configured for a predetermined time period. As an example, the feedback information may indicate one or more transmission parameters (e.g., associated with the NOMA transmission and/or a next NOMA transmission).

[0258] For example, the transmission parameters may include any of a received signal strength of the NOMA transmission, a bit error rate of the NOMA transmission, a throughput rate of a signal in the NOMA transmission intended for the WTRU, a sum rate of the NOMA transmission, a quality -of-service measurement, and/or a combination thereof.

[0259] For example, the WTRU may send feedback information after the NOMA transmission and/or an indication to update the DNN weight set.

[0260] For example, the WTRU may receive a retraining indication to perform retraining of the DNN. After, the WTRU may receive a plurality of pilot symbols from the BS or NE, and may obtain an updated (e.g., recalibrated) DNN weight set from the DNN to which the pilot symbols are input.

[0261] For example, the pilot symbols may be reference signals, such as channel state information reference signals (CSI-RS).

[0262] For example, the WTRU may store and/or refer to a plurality of DNN weight sets which are respectively identified by a plurality of indices (e.g., a codebook). The WTRU may select the DNN weight set from the plurality of stored DNN weight sets based on a comparison of the received indication with an index associated with the DNN weight set.

[0263] In certain representative embodiments, a base station (BS) may implement a method of NOMA communication with a plurality of wireless transmit/receive units (WTRUs). The method may include obtaining, by the BS, a set of WTRUs for a NOMA transmission from among a plurality of WTRUs using a neural network (NN). After, the BS may proceed to send, to the set of WTRUs, an indication of a deep neural network (DNN) weight set to be used by the set of WTRUs. For example, the DNN weight may be applied to a DNN (e.g., at the WTRU) to obtain a symbol vector (e.g., associated with the respective WTRU). The BS may send the NOMA transmission to the obtained set of WTRUs. For example, the symbol vector may be obtainable from inputting the NOMA transmission to the DNN (e.g., at the WTRU) to which the DNN weight set is applied.

[0264] For example, the BS may obtain the set of WTRUs for the NOMA transmission using the NN without inputting channel state information (CSI) to the NN.

[0265] For example, the indication of the DNN weight set may be for the NOMA transmission in a predetermined time period (e.g., associated with a slot, subframe, frame or other TTI).

[0266] For example, the BS may obtain an uplink signal vector using a plurality of transmissions received from the plurality of WTRUs, and input the uplink signal vector to a NN. After, the BS may obtain, from the NN to which the uplink signal vector is input, information associated with the set of WTRUs for the NOMA transmission from among the plurality of WTRUs.

[0267] For example, the plurality of transmissions from the plurality of WTRUs may be orthogonal multiple access (OMA) transmissions.

[0268] For example, the BS may receive a control channel transmission including an indication to perform retraining of the DNN. After, the BS may transmit a plurality of pilot symbols (e.g., reference signals) to the plurality of WTRUs for retraining the DNN.

[0269] For example, the plurality of pilot symbols transmitted to the plurality of WTRUs may include one or more pilot symbols which are specific to a respective WTRU of the plurality of WTRUs. [0270] For example, the plurality of pilot symbols may include channel state information reference signals (CSI-RS).

[0271] For example, the BS may obtain information regarding the received NOMA symbol vector obtained by the set of WTRUs. After, the BS may determine whether to perform retraining of the DNN based on an actual symbol vector transmitted in the NOMA transmission and the information regarding the received NOMA symbol vector. On condition that retraining is to be performed, the BS may transmit an indication to perform retraining of the DNN and a plurality of pilot symbols to the plurality of WTRUs for retraining the DNN.

[0272] For example, the plurality of pilot symbols transmitted to the plurality of WTRUs may include one or more pilot symbols (e.g., reference signals) which are specific to a respective WTRU of the plurality of the WTRUs.

[0273] For example, the plurality of pilot symbols may include channel state information reference signals (CSI-RS).

[0274] In certain representative embodiments, the DNN may be a deep Q-network (DQN).

[0275] In certain representative embodiments, a network entity executing a network function may be configured to operate in conjunction with any of the WTRU and/or a BS to perform multiple access communications (e.g., NOMA transmission and symbol sequence detection) as described herein.

[0276] Conclusion

[0277] Although features and elements are provided above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. The present disclosure is not to be limited in terms of the particular embodiments described in this application, which are intended as illustrations of various aspects. Many modifications and variations may be made without departing from its spirit and scope, as will be apparent to those skilled in the art. No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly provided as such. Functionally equivalent methods and apparatuses within the scope of the disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing descriptions. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is to be understood that this disclosure is not limited to particular methods or systems. [0278] The foregoing embodiments are discussed, for simplicity, with regard to the terminology and structure of infrared capable devices, i.e., infrared emitters and receivers. However, the embodiments discussed are not limited to these systems but may be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves such as acoustic waves. [0279] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting. As used herein, the term "video" or the term "imagery" may mean any of a snapshot, single image and/or multiple images displayed over a time basis. As another example, when referred to herein, the terms "user equipment" and its abbreviation "UE", the term "remote" and/or the terms "head mounted display" or its abbreviation "HMD" may mean or include (i) a wireless transmit and/or receive unit (WTRU); (ii) any of a number of embodiments of a WTRU; (iii) a wireless-capable and/or wired-capable (e.g., tetherable) device configured with, inter alia, some or all structures and functionality of a WTRU; (iii) a wireless-capable and/or wired-capable device configured with less than all structures and functionality of a WTRU; or (iv) the like. Details of an example WTRU, which may be representative of any WTRU recited herein, are provided herein with respect to FIGs. 1 A-1D. As another example, various disclosed embodiments herein supra and infra are described as utilizing a head mounted display. Those skilled in the art will recognize that a device other than the head mounted display may be utilized and some or all of the disclosure and various disclosed embodiments can be modified accordingly without undue experimentation. Examples of such other device may include a drone or other device configured to stream information for providing the adapted reality experience.

[0280] In addition, the methods provided herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer- readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, WTRU, terminal, base station, RNC, or any host computer.

[0281] Variations of the method, apparatus and system provided above are possible without departing from the scope of the invention. In view of the wide variety of embodiments that can be applied, it should be understood that the illustrated embodiments are examples only, and should not be taken as limiting the scope of the following claims. For instance, the embodiments provided herein include handheld devices, which may include or be utilized with any appropriate voltage source, such as a battery and the like, providing any appropriate voltage.

[0282] Moreover, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices that include processors are noted. These devices may include at least one Central Processing Unit ("CPU") and memory. In accordance with the practices of persons skilled in the art of computer programming, reference to acts and symbolic representations of operations or instructions may be performed by the various CPUs and memories. Such acts and operations or instructions may be referred to as being "executed," "computer executed" or "CPU executed."

[0283] One of ordinary skill in the art will appreciate that the acts and symbolically represented operations or instructions include the manipulation of electrical signals by the CPU. An electrical system represents data bits that can cause a resulting transformation or reduction of the electrical signals and the maintenance of data bits at memory locations in a memory system to thereby reconfigure or otherwise alter the CPU's operation, as well as other processing of signals. The memory locations where data bits are maintained are physical locations that have particular electrical, magnetic, optical, or organic properties corresponding to or representative of the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs and that other platforms and CPUs may support the provided methods.

[0284] The data bits may also be maintained on a computer readable medium including magnetic disks, optical disks, and any other volatile (e.g., Random Access Memory (RAM)) or non-volatile (e.g., Read-Only Memory (ROM)) mass storage system readable by the CPU. The computer readable medium may include cooperating or interconnected computer readable medium, which exist exclusively on the processing system or are distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories and that other platforms and memories may support the provided methods.

[0285] In an illustrative embodiment, any of the operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer-readable instructions may be executed by a processor of a mobile unit, a network element, and/or any other computing device.

[0286] There is little distinction left between hardware and software implementations of aspects of systems. The use of hardware or software is generally (but not always, in that in certain contexts the choice between hardware and software may become significant) a design choice representing cost versus efficiency tradeoffs. There may be various vehicles by which processes and/or systems and/or other technologies described herein may be effected (e.g., hardware, software, and/or firmware), and the preferred vehicle may vary with the context in which the processes and/or systems and/or other technologies are deployed. For example, if an implementer determines that speed and accuracy are paramount, the implementer may opt for a mainly hardware and/or firmware vehicle. If flexibility is paramount, the implementer may opt for a mainly software implementation. Alternatively, the implementer may opt for some combination of hardware, software, and/or firmware.

[0287] The foregoing detailed description has set forth various embodiments of the devices and/or processes via the use of block diagrams, flowcharts, and/or examples. Insofar as such block diagrams, flowcharts, and/or examples include one or more functions and/or operations, it will be understood by those within the art that each function and/or operation within such block diagrams, flowcharts, or examples may be implemented, individually and/or collectively, by a wide range of hardware, software, firmware, or virtually any combination thereof. In an embodiment, several portions of the subject matter described herein may be implemented via Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), digital signal processors (DSPs), and/or other integrated formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein, in whole or in part, may be equivalently implemented in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and/or writing the code for the software and or firmware would be well within the skill of one of skill in the art in light of this disclosure. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein may be distributed as a program product in a variety of forms, and that an illustrative embodiment of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually carry out the distribution. Examples of a signal bearing medium include, but are not limited to, the following: a recordable type medium such as a floppy disk, a hard disk drive, a CD, a DVD, a digital tape, a computer memory, etc., and a transmission type medium such as a digital and/or an analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).

[0288] Those skilled in the art will recognize that it is common within the art to describe devices and/or processes in the fashion set forth herein, and thereafter use engineering practices to integrate such described devices and/or processes into data processing systems. That is, at least a portion of the devices and/or processes described herein may be integrated into a data processing system via a reasonable amount of experimentation. Those having skill in the art will recognize that a typical data processing system may generally include one or more of a system unit housing, a video display device, a memory such as volatile and non-volatile memory, processors such as microprocessors and digital signal processors, computational entities such as operating systems, drivers, graphical user interfaces, and applications programs, one or more interaction devices, such as a touch pad or screen, and/or control systems including feedback loops and control motors (e.g., feedback for sensing position and/or velocity, control motors for moving and/or adjusting components and/or quantities). A typical data processing system may be implemented utilizing any suitable commercially available components, such as those typically found in data computing/communication and/or network computing/communication systems.

[0289] The herein described subject matter sometimes illustrates different components included within, or connected with, different other components. It is to be understood that such depicted architectures are merely examples, and that in fact many other architectures may be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively "associated" such that the desired functionality may be achieved. Hence, any two components herein combined to achieve a particular functionality may be seen as "associated with" each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated may also be viewed as being "operably connected", or "operably coupled", to each other to achieve the desired functionality, and any two components capable of being so associated may also be viewed as being "operably couplable" to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and/or physically interacting components and/or wirelessly interactable and/or wirelessly interacting components and/or logically interacting and/or logically interactable components.

[0290] With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity.

[0291] It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as "open" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "includes" should be interpreted as "includes but is not limited to," etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, where only one item is intended, the term "single" or similar language may be used. As an aid to understanding, the following appended claims and/or the descriptions herein may include usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim including such introduced claim recitation to embodiments including only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an" (e.g., "a" and/or "an" should be interpreted to mean "at least one" or "one or more"). The same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number (e.g., the bare recitation of "two recitations," without other modifiers, means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). In those instances where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and/or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase "A or B" will be understood to include the possibilities of "A" or "B" or "A and B." Further, the terms "any of followed by a listing of a plurality of items and/or a plurality of categories of items, as used herein, are intended to include "any of," "any combination of," "any multiple of," and/or "any combination of multiples of the items and/or the categories of items, individually or in conjunction with other items and/or other categories of items. Moreover, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, the term "number" is intended to include any number, including zero. And the term "multiple", as used herein, is intended to be synonymous with "a plurality".

[0292] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0293] As will be understood by one skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily recognized as sufficiently describing and enabling the same range being broken down into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed herein may be readily broken down into a lower third, middle third and upper third, etc. As will also be understood by one skilled in the art all language such as "up to," "at least," "greater than," "less than," and the like includes the number recited and refers to ranges which can be subsequently broken down into subranges as discussed above. Finally, as will be understood by one skilled in the art, a range includes each individual member. Thus, for example, a group having 1-3 cells refers to groups having 1, 2, or 3 cells. Similarly, a group having 1-5 cells refers to groups having 1, 2, 3, 4, or 5 cells, and so forth.

[0294] Moreover, the claims should not be read as limited to the provided order or elements unless stated to that effect. In addition, use of the terms "means for" in any claim is intended to invoke 35 U.S.C. §112, ¶ 6 or means-plus-function claim format, and any claim without the terms "means for" is not so intended.