TECHNICAL FIELD

The present disclosure relates to wireless communications, and in particular, to prediction-based beam management.

BACKGROUND

The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile wireless devices (WD), as well as communication between network nodes and between wireless devices.

One of the features of NR, compared to previous generations of wireless networks, is the ability to operate in higher frequencies (e.g., above 10 GHz). The available large transmission bandwidths in these frequency ranges can potentially provide large data rates. However, as carrier frequency increases, both pathloss and penetration loss increase. To maintain the coverage at the same level, highly directional beams are required to focus the radio transmitter energy in a particular direction on the receiver. However, large radio antenna arrays, at both receiver and transmitter sides, are needed to create such highly direction beams.

To reduce hardware costs, large antenna arrays for high frequencies use timedomain analog beamforming. The idea of analog beamforming is to share a single radio frequency chain between many (or, potentially, all) of the antenna elements. A limitation of analog beamforming is that it may only be possible to transmit radio energy using one beam (in one direction) at a given time.

The above limitation may require the network (NW) and wireless device (WD) to perform beam management procedures to establish and maintain suitable transmitter (Tx) / receiver (Rx) beam-pairs. For example, beam management procedures can be used by a transmitter to sweep a geographic area by transmitting reference signals on different candidate beams, during non-overlapping time intervals, using a predetermined pattern. And by measuring the quality of these reference signals at the receiver side, the best transmit and receive beams can be identified.

NR Beam management procedures

Beam management procedures in NR may be defined by a set of Open Systems Interconnection (OSI) Layer 1/Layer 2 (L1/L2) procedures that establish and maintain suitable beam pairs for transmitting and/or receiving data (for example, as defined in 3GPP Technical Report 38.802 V14.2.0, “Study on New Radio Access Technology Physical Layer Aspects”, September 2017). A beam management procedure may include one or more of the following sub-procedures: beam determination, beam measurements, beam reporting, and beam sweeping.

In the case of downlink transmission from the network to the wireless device, a Pl, P2, and/or P3 beam management procedure may be performed (e.g., according to 3GPP Technical Report 38.802 V14.2.0, “Study on New Radio Access Technology Physical Layer Aspects”, September 2017) to overcome the challenges of establishing and maintaining the beam pairs when, for example, a wireless device moves or some blockage in the environment requires changing the beams:

Pl : The Pl procedure may be used to enable wireless device measurement on different transmission/reception point (TRP) Tx beams to support the selection of TRP Tx beams/wireless device Rx beam(s). For example, during an initial access procedure, a network node (e.g., a gNB) transmits synchronization signal block (SSB) beams in different directions, e.g., to cover the whole cell. Each wireless device measures a signal quality on corresponding SSB reference signals to detect and select the appropriate SSB beam(s). FIG. 1 is a diagram of an example SSB beam selection as part of an initial access procedure according to a Pl scenario. In the example of FIG. 1, the network node transmits different SSB beams to cover the whole cell. The WD(s) measure(s) RSRP on different SSB beams and select(s) one of the SSB indices that is above the specified threshold(s).

For beamforming at TRP, SSB beam selection may include an intra-/inter- TRP Tx beam sweep from a set of different beams.

For beamforming at a wireless device, SSB beam selection may include a wireless device Rx beam sweep from a set of different beams. P2: The P2 procedure may be used to enable wireless device measurement on different TRP Tx beams, e.g., to determine whether to change inter/intra-TRP Tx beam(s). P2 may apply to a smaller set of beams for beam refinement than in the Pl scenario. P2 may be considered a special case of Pl.

For example, in connected mode the network node may configure the wireless device with different channel state information reference signals (CSI-RSs) and transmits each CSI-RS on a corresponding beam. The wireless device may then measure the quality of each CSI-RS beam on its current Rx beam and may send feedback about the quality of the measured beam(s). Thereafter, based on this feedback, the network node may determine which beam(s) may be used in future transmissions, and may indicate these determined beam(s) to the wireless device. FIG. 2 is a diagram of an example CSI-RS Tx beam selection in downlink according to a P2 scenario. In the example of FIG. 2, the network node configures and transmits WD specific CSI-RS on (most likely) narrower beams. The WD(s) perform(s) the Ll-RSRP measurements on different CSI-RSs using its Rx beam(s) and report(s) back up to four highest RSRP values and corresponding CSI-RS index value(s).

P3 may be used to enable wireless device measurement on the same TRP Tx beam to change wireless device Rx beam in the case where wireless device uses beamforming.

For example, in connected mode, P3 can be used by the wireless device to find the best Rx beam for corresponding Tx beam. In this case, the network node may keep one CSI-RS Tx beam at a time, and the wireless device may perform the sweeping and measurements on its own Rx beams for that specific Tx beam. The wireless device may then find the best corresponding Rx beam based on the measurements, and may use it in subsequent receptions when the network node indicates the use of that Tx beam. FIG. 3 is a diagram of an example wireless device Rx beam selection for corresponding CSI-RS Tx beam in the downlink (DL) according to a P3 scenario. In the example of FIG. 3, the network node maintains and transmits the selected CSI-RS beam for a period of time. The WD(s) perform(s) the Ll-RSRP measurements on its different Rx beam(s) to find the suitable one(s) for selected CSI-RS beam(s).

Quasi Co-Location (QCL) QCL is used to infer channel characteristics/statistics experienced by a target reference signal from a source reference signal, where the latter is known to the receiver. More specifically, two antenna ports are said to be quasi co-located if properties of the channel over which a symbol on one antenna port is conveyed can be inferred from the channel over which a symbol on the other antenna port is conveyed (e.g., as described in 3GPP Technical Report 38.802 V14.2.0, “Study on New Radio Access Technology Physical Layer Aspects”, September 2017). In NR, these signals are assumed to be transmitted from different antenna ports of the same TRP or from different TRP physical antennas.

A wireless device may be preconfigured (e.g., based on a technical specification), and/or a network node may signal to a wireless device that two or more antenna ports are QCL. If the wireless device knows that two antenna ports are QCL with respect to a certain parameter, the wireless device may estimate that parameter based on a source signal transmitted from a first antenna port and may use it to estimate the target signal from a second antenna port. Typically, the first antenna port is represented by a measurement reference signal (RS) such as CSLRS and the second antenna port is represented by a demodulation reference signal (DMRS).

For example, if antenna ports A and B are QCL with respect to, for example, average delay, the wireless device may estimate the average delay from the source RS received from antenna port A and may assume that the target RS received from antenna port B has the same average delay. This a-priori information may be useful for a wireless device when demodulating a signal sent from antenna port B.

There are 4 QCL types defined in NR (e.g., as described in Clause 5.1.5 of 3GPP Technical Specification 38.214 V16.7.0, “NR; Physical layer procedures for data”, September, 2021) comprising the following channel properties:

QCL-Type A: {Doppler shift, Doppler spread, average delay, delay spread} QCL-Type B: {Doppler shift, Doppler spread} QCL-Type C: {Doppler shift, average delay} QCL-Type D: {Spatial Rx parameter}

NR QCL-Type A is similar to QCL-Type A specified for LTE. QCL-Type B and QCL-Type C include a subset of the channel statistical properties defined for QCL-Type A. QCL-Type D is defined with respect to spatial Rx parameters and introduced to facilitate beamforming operation and beam management (BM) procedures in NR Frequency Range 2 (FR2). Although no explicit definition in the specification is provided, the general understanding is that spatial QCL, i.e., QCL type D, implies that both the source RS and the target RS can be received with the same beamforming (spatial) filter at the receiver side.

Transmission Configuration Indication (TCI)

In the NR downlink, QCL relationships between different signals can be either explicitly mentioned in the specification or dynamically indicated to the wireless device via, e.g., control signaling. For the latter case, dynamic use of QCL may be enabled by the introduction of transmission configuration indication (TCI) states.

Each TCLState contains parameters for configuring a QCL relationship between the following:

• one or (optionally) two downlink reference signals and

• the DMRS ports of the Physical Downlink Shared Channel (PDSCH) or Physical Downlink Control Channel (PDCCH), or the CSI-RS port(s) of a CSLRS resource.

In the context of beam management, a TCI indication may be used for dynamic beam selection using the QCL type-D.

Each QCL-Info information element identifies one of the downlink reference signals and configures the QCL type associated to it. The source reference signal corresponds to either a CSI-RS or and SSB and the QCL-type can be set to one of QCL types A-D. For example, the NR standard (e.g., 3GPP Technical Specification 38.331 V16.1.0, “Radio Resource Control (RRC) protocol specification”, July 2020) defines the TCLstate information element as follows:

TCI-State information element

- ASN1 START

- TAG-TCI-STATE-START

TCI-State ::= SEQUENCE ) tci-Stateld TCI-Stateld, qcl-Typel QCL-Info, qcl-Type2 QCL-Info

OPTIONAL, — Need R

QCL-Info ::= SEQUENCE { cell ServCelllndex OPTIONAL, - Need R bwp-Id BWP-Id OPTIONAL, - Cond CSI-RS-

Indicated referencesignal CHOICE { csi-rs NZP-CSI-RS-Resourceld, ssb SSB -Index

}, qcl-Type ENUMERATED {typeA, typeB, typeC, typeD},

}

- TAG-TCI-STATE-STOP

- ASN1STOP

To reduce TCI signaling overhead, a wireless device may be configured with a pool of TCI states via the PDSCH-Config element with corresponding ici-slalll). which is defined as a list of TCI-state elements as shown in following. The pool of Radio Resource Control (RRC) configured parameters may then be used to indicate a QCL relation between two reference signals by means of RRC configuration, media access control (MAC) control element (CE), or downlink control information (DCI) depending on which type of reference signal(s) is/are utilized.

The NR standard (e.g., 3GPP Technical Specification 38.331 V16.1.0, “Radio Resource Control (RRC) protocol specification”, July 2020) defines the PDSCH- Config information element as follows:

PDSCH-Config information element

ASN1 START

- TAG-PDSCH-CONFIG-START PDSCH-Config ::= SEQUENCE { dataScramblingldentityPDSCH INTEGER (0..1023) dmrs-DownlinkForPDSCH-MappingTypeA SetupRelease { DMRS- DownlinkConfig } dmrs-DownlinkForPDSCH-MappingTypeB SetupRelease { DMRS- DownlinkConfig } tci-StatesToAddModList SEQUENCE (SIZE(l..maxNrofFCI-

States)) OF TCI-State tci-StatesToReleaseList SEQUENCE (SIZE(E.maxNrofTCI-States))

OF TCI-Stateld

When a wireless device is configured with the pool of TCI states, there may be two different ways to indicate the QCL relations for PDSCH DMRS depending on whether tci-PresentlnDCI is configured or not (e.g., as described in Clause 5.1.5 of 3GPP Technical Specification 38.214 V16.7.0, “NR; Physical layer procedures for data”, September, 2021).

When the wireless device is not configured with the tci-PresentlnDCI or configured but its value is not set to ‘enable’, and the wireless device has received the MAC CE activation command, then the wireless device may assume that the TCI state of the PDSCH DM-RS is the same as TCI state of PDCCH DMRS carrying corresponding scheduling DCI. However, before the wireless device receives the MAC CE activation command, the wireless device may assume that PDSCH DMRS is QCL' with the SSB antenna ports determined during initial access.

If the tci-PresentlnDCI is configured, and its value is set to ‘enable’, the wireless device may receive a MAC CE activation command to map a sub-set of up to 8 TCI states from the RRC list of TCI pool that are relevant for future PDSCH transmissions. The wireless device may be expected to continuously track and update the channel properties for the active TCI states by measurements and analysis of the source RSs indicated by each TCI state. One of these 8 TCI states may be indicated as the actual TCI state to be assumed at PDSCH reception by means of a codepoint in DCI signaling.

DCI based TCI indication may reduce the switching time of the QCL relation and make it more dynamic, which may be relevant when the TCI state of PDSCH and corresponding scheduling PDCCH are to be different. However, in practice, the wireless device may still need some time to apply the TCI state change because, for example, of the required time to decode DCI and adjust RX beam. For this reason, based on whether tci-PresentlnDCI is configured or not and whether the offset between PDSCH reception and corresponding scheduling DCI are less or more than timeDurationForQCL different rules may be applied (for example, as described in clause 5.1.5 of 3GPP Technical Specification 38.214 V16.7.0, “NR; Physical layer procedures for data”, September, 2021).

For PDCCH DMRS, a subset of the configured TCI-state elements in PDSCH- config are selected in the CORESET configuration element, i.e., ControlResourceSet, and MAC CE command is used to activate one of these down selected TCI states. This effectively quasi co-locates the antenna ports of the source reference signal, identified by the activated TCI state QCL-info, with the target reference signal, i.e., the PDCCH DMRS, antenna ports. The QCL relation indicated in the tci-state is applied 3 ms after the Hybrid Automatic Repeat Request (HARQ) Acknowledgement (ACK) feedback for the transport block (TB) on which a corresponding MAC CE is received.

If only one tci-state is configured in the CORESET, then that state is used as default TCI state for reception of PDCCH.

ControlResourceSet information element

- ASN1 START

- TAG-CONTROLRESOURCESET-START

ControlResourceSet ::= SEQUENCE ) controlResourceSetld ControlResourceSetld, tci-StatesPDCCH-ToAddList SEQUENCE(SIZE (L.maxNrofFCI- StatesPDCCH)) OF TCI-Stateld OPTIONAL, - Cond NotSIBl-initialBWP tci-StatesPDCCH-ToReleaseList SEQUENCE(SIZE (1..maxNrofFCL

StatesPDCCH)) OF TCI-Stateld OPTIONAL, - Cond NotSIBl-initialBWP tci-PresentlnDCI ENUMERATED {enabled} OPTIONAL,

- Need S tci-PresentDCLl-2-rl6 INTEGER (1..3)

OPTIONAL, - Need S

}

- TAG-CONTROLRESOURCESET-STOP

- ASN1STOP

The maximum number of TCI states that can be configured for PDSCH and PDCCH are as follow: maxNrofTCI-StatesPDCCH INTEGER : := 64 maxNrofTCI-States INTEGER ::= 128 -- Maximum number of TCI states. maxNroffCI-States-1 INTEGER ::= 127 -- Maximum number of TCI states minus 1.

Machine Learning (ML) for beam prediction

A wireless device may be configured to predict future beam values based on historical values. Based on received device data from measurement reports, the network may learn, for example, which sequences of signal quality measurements (e.g., Reference Signal Receive Power (RSRP) measurements) lead to large signal quality drop events (e.g., turning around the corners as shown in FIG. 4, which depicts a scenario in which two wireless devices move on similar paths). This learning procedure may be enabled, for example, by dividing periodically reported RSRP data into a training and prediction window. For example, in FIG. 4, two wireless devices move and turn around the same corner. A first wireless device 2a, marked by dashed line, is the first to turn around the corner and consequently experiences a large signal quality drop. Prediction may be used to mitigate the drop of a second wireless device 2b by using learning from the first wireless device 2a’ s experiences, e.g., by a network node 4.

The learning may be performed by feeding RSRP in , . . . , t _n into a machine learning model (e.g., a neural network), which model may predict the RSRP in Z _n +i, Z„+2, etc. After the model is trained, the network may download the model to the wireless device, which then predicts future signal quality values using the model. The signal quality prediction may then be used, for example, to avoid radio-link failure, e.g., caused by inter-frequency handover, may be used to set handover/reselection parameters, and/or may be used to change a wireless device scheduler priority, for example, to schedule the wireless device when the expected signal/beam quality is predicted to be good.

Existing systems, however, lack effective configurations for indicating beam switching to be performed by the wireless device.

SUMMARY

When performing a beam switch for a wireless device, in the current NR specification, an indication of a new QCL relation may need to be signalled from the network/network node to the wireless device. The new QCL relation becomes active after a fixed offset time, where the offset time depends on the method used and the conditions (e.g., of the environment and/or network), as explained above. In some existing systems, regardless of the rules applied based on each wireless device condition, the timing offset may be fixed and cannot be changed by the network. Using a fixed offset as described above may lead to signalling congestion. For example, if many wireless devices need to switch beams at similar times, this may result in a relatively large number of switching indications needing to be sent at similar times, which may exceed a signalling capacity of the network. Another problem may arise for fast moving wireless devices, wherein beam switches may need to be signalled very frequently, which may also result in a relatively large signalling overhead, and which may also exceed a signalling capacity of the network.

Some embodiments advantageously solve at least a portion of one or more of the problems described above by providing methods, systems, and apparatuses for artificial intelligence (AI)/ML based beam prediction utilizing enhanced signaling, such as enhanced QCL relation and/or TCI indication signaling. The new/enhanced signaling may be tailored for AI-/ML-based algorithms that may be capable of performing predictions or forecasting into the future.

In some embodiments, a network node is configured to communicate with a wireless device and receives at least one measurement report from the wireless device, each of the at least one measurement report being associated with a plurality of beams. The network node determines, based on the at least one measurement report, a plurality of beam switching instances, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window. The network node transmits, to the wireless device, an indication of the plurality of beam switching instances. The indication indicates the wireless device to switch to the at least one corresponding beam during the corresponding time window for the beam switching instances.

In some embodiments, a wireless device is configured to communicate with a network node. The wireless device transmits at least one measurement report to the network node, each of the at least one measurement report being associated with a plurality of beams. The wireless device receives, from the network node, an indication of a plurality of beam switching instances, each of the plurality of beam switching instances being determined based on the at least one measurement report, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window. The wireless device switches, based on the indication, the at least one corresponding beam during the corresponding time window.

According to another aspect of the present disclosure, a network node is provided. The network node is configured to receive a first channel measurement report associated with the first wireless device and at least one beam, determine a first beam based on the first channel measurement report, determine a first time window for switching from an active beam to the first beam based on the first channel measurement report, and to transmit, to the first wireless device, a first beam switching indication indicating the first time window and the first beam. The network node is configured to, optionally, responsive to transmitting the first beam switching indication, receive signaling from the first wireless device using the first beam during the first time window.

According to some embodiments of this aspect, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device, at least one additional beam associated with at least one additional wireless device in the first cell, and reference signaling received by the first wireless device. According to some embodiments of this aspect, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. According to some embodiments of this aspect, the network node is configured with a machine learning model for predicting beam quality metrics, and the network node is further configured to determine a first beam quality metric of the first beam using the machine learning model based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device, uplink signal quality information associated with the network node, and traffic information associated with at least one neighboring cell.

According to some embodiments of this aspect, the determining of the first beam quality metric is further based on at least one of speed information associated with the first wireless device, a traffic pattern associated with the first wireless device, location information associated with the first wireless device, capability information associated with the first wireless device, and spatial information associated with the first wireless device. According to some embodiments of this aspect, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model.

According to some embodiments of this aspect, the network node is further configured to determine at least one additional beam beams for switching based on at least one of the first measurement report and the machine learning model, to determine at least one additional time window for performing at least one switch to the at least one additional beam based on at least one of the first measurement report and the machine learning model, where the first indication transmitted to the first wireless device further indicates the at least one additional time window and the at least one additional beam, and optionally, responsive to transmitting the first indication, receive additional signaling from the first wireless device using the at least one additional beam during the at least one additional time window.

According to some embodiments of this aspect, the network node is further configured to receive a second measurement report associated with a second wireless device, determine a second beam of the second plurality of beams for switching based on at least one of the first measurement report, the second measurement report, and the machine learning model, determine a second time window for performing a switch to the second beam based on at least one of the first measurement report, the second measurement report, and the machine learning model, transmit, to the second wireless device, a second indication indicating the second time window and the second beam, and optionally, responsive to transmitting the second indication, receive signaling from the second wireless device using the second beam during the second time window.

According to some embodiments of this aspect, the machine learning model is trained for a plurality of beams in the first cell based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell, component carriers associated with the first cell, speed information associated with at least one wireless device of the first cell, traffic pattern information associated with at least one wireless device of the first cell, location information associated with at least one wireless device of the first cell, capability information associated with at least one wireless device of the first cell, and spatial information associated with at least one wireless device of the first cell, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell, and at least one historical beam switching pattern associated with at least one wireless device of the first cell.

According to some embodiments of this aspect, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. According to some embodiments of this aspect, the first indication is a transmission configuration indication (TCI). According to some embodiments of this aspect, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RS SI), a channel quality indicator (CQI), and an interference plus noise estimate.

According to some embodiments of this aspect, the first time offset value is restricted to being not less than a legacy fixed time offset value. According to some embodiments of this aspect, the network node is further configured to compare a first metric of the first beam with a corresponding metric of the active beam, and only transmits the first indication when a difference between the first metric of the first beam and the corresponding metric of the active beam exceeds a preconfigured threshold. According to some embodiments of this aspect, the network node is further configured to determine a probability value associated with the first beam, the first probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam, and only transmits the first indication when the probability value exceeds a preconfigured threshold.

According to some embodiments of this aspect, the network node is further configured to detect an increase in network congestion, and increase the preconfigured threshold based on the detected increase in network congestion. According to some embodiments of this aspect, the network node is further configured to transmit to the wireless device radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, where the first beam switching indication indicates the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. According to some embodiments of this aspect, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device during a plurality of corresponding time instances.

According to another aspect of the present disclosure, a method implemented in a network node is provided. The method includes receiving a first channel measurement report associated with the first wireless device and at least one beam, determining a first beam based on the first channel measurement report, determining a first time window for switching from an active beam to the first beam based on the first channel measurement report, and transmitting, to the first wireless device, a first beam switching indication indicating the first time window and the first beam. Optionally, responsive to transmitting the first beam switching indication, the method further includes receiving signaling from the first wireless device using the first beam during the first time window.

According to some embodiments of this aspect, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device, at least one additional beam associated with at least one additional wireless device in the first cell, and reference signaling received by the first wireless device. According to some embodiments of this aspect, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. According to some embodiments of this aspect, the network node is configured with a machine learning model for predicting beam quality metrics, and the method further includes determining a first beam quality metric of the first beam using the machine learning model based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device, uplink signal quality information associated with the network node, and traffic information associated with at least one neighboring cell.

According to some embodiments of this aspect, the determining of the first beam quality metric is further based on at least one of speed information associated with the first wireless device, a traffic pattern associated with the first wireless device, location information associated with the first wireless device, capability information associated with the first wireless device, and spatial information associated with the first wireless device. According to some embodiments of this aspect, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model.

According to some embodiments of this aspect, the method further includes determining at least one additional beam beams for switching based on at least one of the first measurement report and the machine learning model, determining at least one additional time window for performing at least one switch to the at least one additional beam based on at least one of the first measurement report and the machine learning model, where the first indication transmitted to the first wireless device further indicates the at least one additional time window and the at least one additional beam, and optionally, responsive to transmitting the first indication, receiving additional signaling from the first wireless device using the at least one additional beam during the at least one additional time window.

According to some embodiments of this aspect, the method further includes receiving a second measurement report associated with a second wireless device, determining a second beam of the second plurality of beams for switching based on at least one of the first measurement report, the second measurement report, and the machine learning model, determining a second time window for performing a switch to the second beam based on at least one of the first measurement report, the second measurement report, and the machine learning model, transmitting, to the second wireless device, a second indication indicating the second time window and the second beam, and optionally, responsive to transmitting the second indication, receiving signaling from the second wireless device using the second beam during the second time window.

According to some embodiments of this aspect, the machine learning model is trained for a plurality of beams in the first cell based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell, component carriers associated with the first cell, speed information associated with at least one wireless device of the first cell, traffic pattern information associated with at least one wireless device of the first cell, location information associated with at least one wireless device of the first cell, capability information associated with at least one wireless device of the first cell, and spatial information associated with at least one wireless device of the first cell, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell, and at least one historical beam switching pattern associated with at least one wireless device of the first cell. According to some embodiments of this aspect, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. According to some embodiments of this aspect, the first indication is a transmission configuration indication (TCI). According to some embodiments of this aspect, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RS SI), a channel quality indicator (CQI), and an interference plus noise estimate.

According to some embodiments of this aspect, the first time offset value is restricted to being not less than a legacy fixed time offset value. According to some embodiments of this aspect, the method further includes comparing a first metric of the first beam with a corresponding metric of the active beam, and only transmitting the first indication when a difference between the first metric of the first beam and the corresponding metric of the active beam exceeds a preconfigured threshold.

According to some embodiments of this aspect, the method further includes determining a probability value associated with the first beam, the first probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam, and only transmitting the first indication when the probability value exceeds a preconfigured threshold.

According to some embodiments of this aspect, the method further includes detecting an increase in network congestion, and increasing the preconfigured threshold based on the detected increase in network congestion. According to some embodiments of this aspect, the method further includes transmitting to the wireless device radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, where the first beam switching indication indicates the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. According to some embodiments of this aspect, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device during a plurality of corresponding time instances. According to another aspect of the present disclosure, a wireless device is provided. The wireless device is configured to transmit to a network node a first channel measurement report associated with the first wireless device and at least one beam. The wireless device is configured to receive, responsive to the transmission of the first channel measurement report, a first beam switching indication, the first beam switching indication indicating a first beam and a first time window for switching. The wireless device is configured to switch from an active beam to the first beam for signaling during the first time window. The wireless device is configured to optionally, transmit and/or cause transmission to the network node of signaling using the first beam during the first time window.

According to some embodiments of this aspect, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device, at least one additional beam associated with at least one additional wireless device in the first cell, and reference signaling received by the first wireless device. According to some embodiments of this aspect, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. According to some embodiments of this aspect, at least one of the first beam and the first time window is determined based on a machine learning model, the machine learning model being configured to determine a first beam quality metric of the first beam based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device, uplink signal quality information associated with the wireless device, and traffic information associated with at least one neighboring cell.

According to some embodiments of this aspect, the first beam quality metric is further determined based on at least one of speed information associated with the first wireless device, a traffic pattern associated with the first wireless device, location information associated with the first wireless device, capability information associated with the first wireless device, and spatial information associated with the first wireless device. According to some embodiments of this aspect, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model. According to some embodiments of this aspect, the first indication further indicates at least one additional time window and the at least one additional beam for switching, the at least one additional beam being determined based on at least one of the first measurement report and the machine learning model, and the at least one additional time window being determined based on at least one of the first measurement report and the machine learning model, and the wireless device is further configured to, optionally, responsive to receiving the first indication, transmit additional signaling using the at least one additional beam during the at least one additional time window.

According to some embodiments of this aspect, the machine learning model is trained for a plurality of beams in the first cell based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell, component carriers associated with the first cell, speed information associated with at least one wireless device of the first cell, traffic pattern information associated with at least one wireless device of the first cell, location information associated with at least one wireless device of the first cell, capability information associated with at least one wireless device of the first cell, and spatial information associated with at least one wireless device of the first cell, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell, and at least one historical beam switching pattern associated with at least one wireless device of the first cell. According to some embodiments of this aspect, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. According to some embodiments of this aspect, the first indication is a transmission configuration indication (TCI). According to some embodiments of this aspect, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RS SI), a channel quality indicator (CQI), and an interference plus noise estimate. According to some embodiments of this aspect, the first time offset value is restricted to being not less than a legacy fixed time offset value. According to some embodiments of this aspect, the first indication is only received when a difference between a first metric of the first beam and a corresponding metric of the active beam exceeds a preconfigured threshold.

According to some embodiments of this aspect, the first indication is only received when a probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam exceeds a preconfigured threshold. According to some embodiments of this aspect, the preconfigured threshold is increased based on a detected increase in network congestion. According to some embodiments of this aspect, the wireless device is further configured to receive radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, the first beam switching indication indicating the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. According to some embodiments of this aspect, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device during a plurality of corresponding time instances.

According to another aspect of the present disclosure, a method implemented in a first wireless device is provided. The method includes transmitting to the network node a first channel measurement report associated with the first wireless device and at least one beam, receiving, responsive to the transmission of the first channel measurement report, a first beam switching indication, where the first beam switching indication indicates a first beam and a first time window for switching. The method further includes switching from an active beam to the first beam for signaling during the first time window. The method further includes, optionally, transmitting signaling to the network node using the first beam during the first time window.

According to some embodiments of this aspect, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device, at least one additional beam associated with at least one additional wireless device in the first cell, and reference signaling received by the first wireless device. According to some embodiments of this aspect, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. According to some embodiments of this aspect, at least one of the first beam and the first time window is determined based on a machine learning model, the machine learning model being configured to determine a first beam quality metric of the first beam based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device, uplink signal quality information associated with the wireless device, and traffic information associated with at least one neighboring cell.

According to some embodiments of this aspect, the first beam quality metric is further determined based on at least one of speed information associated with the first wireless device, a traffic pattern associated with the first wireless device, location information associated with the first wireless device, capability information associated with the first wireless device, and spatial information associated with the first wireless device. According to some embodiments of this aspect, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model. According to some embodiments of this aspect, the first indication further indicates at least one additional time window and the at least one additional beam for switching, the at least one additional beam being determined based on at least one of the first measurement report and the machine learning model, and the at least one additional time window being determined based on at least one of the first measurement report and the machine learning model, and the method optionally further includes, responsive to receiving the first indication, transmitting additional signaling using the at least one additional beam during the at least one additional time window.

According to some embodiments of this aspect, the machine learning model is trained for a plurality of beams in the first cell based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell, component carriers associated with the first cell, speed information associated with at least one wireless device of the first cell, traffic pattern information associated with at least one wireless device of the first cell, location information associated with at least one wireless device of the first cell, capability information associated with at least one wireless device of the first cell, and spatial information associated with at least one wireless device of the first cell, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell, and at least one historical beam switching pattern associated with at least one wireless device of the first cell.

According to some embodiments of this aspect, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. According to some embodiments of this aspect, the first indication is a transmission configuration indication (TCI). According to some embodiments of this aspect, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RSSI), a channel quality indicator (CQI), and an interference plus noise estimate. According to some embodiments of this aspect, the first time offset value is restricted to being not less than a legacy fixed time offset value. According to some embodiments of this aspect, the first indication is only received when a difference between a first metric of the first beam and a corresponding metric of the active beam exceeds a preconfigured threshold. According to some embodiments of this aspect, the first indication is only received when a probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam exceeds a preconfigured threshold. According to some embodiments of this aspect, the preconfigured threshold is increased based on a detected increase in network congestion. According to some embodiments of this aspect, the wireless device is further configured to receive radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, the first beam switching indication indicating the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. According to some embodiments of this aspect, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device during a plurality of corresponding time instances.

BRIEF DESCRIPTION OF THE DRAWINGS

A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

FIG.l is a schematic diagram of an example network configuration using beam selection;

FIG. 2 is a schematic diagram of another example network configuration using beam selection;

FIG. 3 is a schematic diagram of yet another example network configuration using beam selection;

FIG. 4 an illustration of an example wireless device scenario; FIG. 5 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

FIG. 6 is a block diagram of a network node in communication with a wireless device over a wireless connection according to some embodiments of the present disclosure;

FIG. 7 is a flowchart of an example process in a network node for prediction-based beam management according to some embodiments of the present disclosure; and

FIG. 8 is a flowchart of an example process in a wireless device for prediction-based beam management according to some embodiments of the present disclosure;

FIG. 9 is a flowchart of another example process in a network node for prediction-based beam management according to some embodiments of the present disclosure;

FIG. 10 is a flowchart of another example process in a wireless device for prediction-based beam management according to some embodiments of the present disclosure;

FIG. 11 is a diagram of an example signaling configuration for some embodiments of the present disclosure; and

FIG. 12 is a diagram of an example machine learning model according to some embodiments of the present disclosure.

DETAILED DESCRIPTION

Before describing in detail exemplary embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to prediction-based beam management. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.

In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and/or wireless connections.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multi -standard radio (MSR) radio node such as MSR BS, multi-cell/multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a wireless device such as a wireless device or a radio network node.

In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The wireless device herein can be any type of wireless device capable of communicating with a network node or another wireless device over radio signals, such as wireless device. The wireless device may also be a radio communication device, target device, device to device (D2D) wireless device, machine type wireless device or wireless device capable of machine to machine communication (M2M), low-cost and/or low-complexity wireless device, a sensor equipped with wireless device, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device, etc.

Also, in some embodiments the generic term “radio network node” is used. It can be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell/multicast Coordination Entity (MCE), relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH). In one or more embodiments, the term “beam” may refer to the network node transmitting different SSBs in different physical directions, and hence the set of SSBs may correspond to different beams. A beam may be identified by the SSB identifier/index. Alternatively, a CSI-RS resource may be repeatedly transmitted, and for each transmission the network node may transmit the resource in a different physical direction. The CSI-RS resource index (CRI) may be used to indicate a certain “beam”, i.e., a CSI-RS resource from the set of CSI-RS resources. “Beams” are not defined in 3GPP specifications, which instead define SSB indices and CRIs. In the present disclosure, the term “beams” may be used to refer to SSB indices and/or CRIs. However, this terminology is not intended to limit the embodiments and techniques described herein to only these type of reference signals.

In one or more embodiments, the term “switching” (e.g., “beam switching” or “switching a beam/beams” or “switching to/from a beam/beams”) may refer to one or more of turning on and/or turning off one or more beams, redirecting transmissions intended for a beam/beams to another beam/beams, turning one or more beams on and turning one or more beams off, activating/deactivating certain beams during certain time intervals, increasing/decreasing power on one or more beams, etc. However, this terminology is not intended to limit the embodiments and techniques described herein to only these type of reference signals.

Note that although terminology from one particular wireless system, such as, for example, 3 GPP LTE and/or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

Note further, that functions described herein as being performed by a wireless device or a network node may be distributed over a plurality of wireless devices and/or network nodes. In other words, it is contemplated that the functions of the network node and wireless device described herein are not limited to performance by a single physical device and, in fact, can be distributed among several physical devices.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

Referring again to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 5 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and/or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first wireless device (WD) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second wireless device 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of wireless devices 22a, 22b (collectively referred to as wireless devices 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole wireless device is in the coverage area or where a sole wireless device is connecting to the corresponding network node 16. Note that although only two wireless devices 22 and three network nodes 16 are shown for convenience, the communication system may include many more wireless devices 22 and network nodes 16.

Also, it is contemplated that a wireless device 22 can be in simultaneous communication and/or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a wireless device 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, wireless device 22 can be in communication with an eNB for LTEZE-UTRAN and a gNB for NR/NG-RAN.

A network node 16 (eNB or gNB) is configured to include a beam prediction unit 24 which is configured to perform one or more network node 16 functions as described herein such as with respect to predicting beam qualities associated with future time windows, e.g., using a machine learning model generated using historical/previous beam quality and time information and/or based on other metrics such as network traffic, signal quality, etc. A wireless device 22 is configured to include a beam measurement reporting unit 26 which is configured to perform one or more wireless device 22 functions as described herein such as with respect to the measuring of beams (e.g., beam quality) and/or reporting the measurements and/or corresponding time values to the network (e.g., to network node 16).

Example implementations, in accordance with an embodiment, of the wireless device 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 6.

The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 28 enabling it to communicate with the wireless device 22. The hardware 28 may include a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a wireless device 22 located in a coverage area 18 served by the network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves (e.g., beams).

In the embodiment shown, the hardware 28 of the network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and/or read from) the memory 40, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Thus, the network node 16 further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by network node 16. Processor 38 corresponds to one or more processors 38 for performing network node 16 functions described herein. The memory 40 is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and/or processing circuitry 36, causes the processor 38 and/or processing circuitry 36 to perform the processes described herein with respect to network node 16. For example, processing circuitry 36 of the network node 16 may include beam prediction unit 24 which is configured to perform one or more network node 16 functions as described herein such as with respect to predicting beam qualities associated with future time windows, e.g., using a machine learning model generated using historical/previous beam quality and time information and/or based on other metrics such as network traffic, signal quality, etc.

The communication system 10 further includes the wireless device 22 already referred to. The wireless device 22 may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a network node 16 serving a coverage area 18 in which the wireless device 22 is currently located. Coverage area 18 is also referred to herein as “cell 18”. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves (e.g., beams). The hardware 44 of the wireless device 22 further includes processing circuitry 50. The processing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and/or read from) memory 54, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Thus, the wireless device 22 may further comprise software 56, which is stored in, for example, memory 54 at the wireless device 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the wireless device 22. The software 56 may be executable by the processing circuitry 50. The software 56 may include a client application 58. The client application 58 may be operable to provide a service to a human or non-human user via the wireless device 22.

The processing circuitry 50 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by wireless device 22. The processor 52 corresponds to one or more processors 52 for performing wireless device 22 functions described herein. The wireless device 22 includes memory 54 that is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 56 and/or the client application 58 may include instructions that, when executed by the processor 52 and/or processing circuitry 50, causes the processor 52 and/or processing circuitry 50 to perform the processes described herein with respect to wireless device 22. For example, the processing circuitry 50 of the wireless device 22 may include beam measurement reporting unit 26 which is configured to perform one or more wireless device 22 functions as described herein such as with respect to the measuring of beams (e.g., beam quality) and/or reporting the measurements and/or corresponding time values to the network (e.g., to network node 16).

In some embodiments, the inner workings of the network node 16 and wireless device 22 may be as shown in FIG. 6 and independently, the surrounding network topology may be that of FIG. 5.

The wireless connection 32 between the wireless device 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and/or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency, signal/beam power, signal/beam quality, noise, and other factors on which the one or more embodiments improve.

Although FIGS. 5 and 6 show various “units” such as beam prediction unit 24 and beam measurement reporting unit 26 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

FIG. 7 is a flowchart of an example process in a network node 16 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the beam prediction unit 24), processor 38, and/or radio interface 30. Network node 16 is configured to receive (Block S100) at least one measurement report from the wireless device 22, each of the at least one measurement report being associated with a plurality of beams. The network node 16 is further configured to determine (Block SI 02), based on the at least one measurement report, a plurality of beam switching instances, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window. The network node 16 is further configured to transmit (Block SI 04), to the wireless device 22, an indication of the plurality of beam switching instances, the indication indicating the wireless device 22 to switch to the at least one corresponding beam during the corresponding time window.

In some embodiments, determining the plurality of beam switching instances includes generating a prediction model based on the at least one measurement report, determining, using the prediction model, a plurality of beam quality predictions and corresponding time values, and determining, for each of the plurality of beam switching instances, the at least one corresponding beam to switch to and the corresponding time window based on the plurality of beam quality predictions and corresponding time values.

In some embodiments, determining the at least one corresponding beam to switch to includes selecting, for each corresponding time window, a maximum from the plurality of beam quality predictions.

FIG. 8 is a flowchart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of wireless device 22 such as by one or more of processing circuitry 50 (including the beam measurement reporting unit 26), processor 52, and/or radio interface 46. Wireless device 22 is configured to transmit (Block SI 06) at least one measurement report to the network node 16, each of the at least one measurement report being associated with a plurality of beams. The wireless device 22 is configured to receive (Block SI 08), from the network node 16, an indication of a plurality of beam switching instances, each of the plurality of beam switching instances being determined based on the at least one measurement report, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window. The wireless device 22 is configured to switch (Block SI 10) based on the indication, the at least one corresponding beam during the corresponding time window.

In some embodiments, the plurality of beam switching instances is determined based at least on generating a prediction model based on the at least one measurement report, determining, using the prediction model, a plurality of beam quality predictions and corresponding time values, and determining, for each of the plurality of beam switching instances, where the at least one corresponding beam to switch to and the corresponding time window are based on the plurality of beam quality predictions and corresponding time values.

In some embodiments, the plurality of beam switching instances are associated with a trajectory of the wireless device.

FIG. 9 is a flowchart of another example process in a network node 16 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the beam prediction unit 24), processor 38, and/or radio interface 30. Network node 16 is configured to receive (Block SI 12) a first channel measurement report associated with the first wireless device 22 and at least one beam. Network node 16 is configured to determine (Block SI 14) a first beam based on the first channel measurement report. Network node 16 is configured to determine (Block SI 16) a first time window for switching from an active beam to the first beam based on the first channel measurement report. Network node 16 is configured to transmit and/or cause transmission of (Block SI 18), to the first wireless device 22, a first beam switching indication, indicating the first time window and the first beam. Network node 16 is configured to, optionally, responsive to transmitting the first beam switching indication, receive (Block S120) signaling from the first wireless device 22 using the first beam during the first time window.

In some embodiments, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device 22, at least one additional beam associated with at least one additional wireless device 22 in the first cell 18, and reference signaling received by the first wireless device 22. In some embodiments, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. In some embodiments, the network node 16 is configured with a machine learning model for predicting beam quality metrics, and the network node 16 is further configured to determine a first beam quality metric of the first beam using the machine learning model based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device 22, uplink signal quality information associated with the network node 16, and traffic information associated with at least one neighboring cell.

In some embodiments, the determining of the first beam quality metric is further based on at least one of speed information associated with the first wireless device 22, a traffic pattern associated with the first wireless device 22, location information associated with the first wireless device 22, capability information associated with the first wireless device 22, and spatial information associated with the first wireless device 22. In some embodiments, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model.

In some embodiments, the network node 16 is further configured to determine at least one additional beam beams for switching based on at least one of the first measurement report and the machine learning model determine at least one additional time window for performing at least one switch to the at least one additional beam based on at least one of the first measurement report and the machine learning model, where the first indication transmitted to the first wireless device 22 further indicates the at least one additional time window and the at least one additional beam, and optionally, responsive to transmitting the first indication, receive additional signaling from the first wireless device 22 using the at least one additional beam during the at least one additional time window.

In some embodiments, the network node 16 is further configured to receive a second measurement report associated with a second wireless device 22, determine a second beam of the second plurality of beams for switching based on at least one of the first measurement report, the second measurement report, and the machine learning model, determine a second time window for performing a switch to the second beam based on at least one of the first measurement report, the second measurement report, and the machine learning model, transmit, to the second wireless device 22, a second indication indicating the second time window and the second beam, and optionally, responsive to transmitting the second indication, receive signaling from the second wireless device 22 using the second beam during the second time window.

In some embodiments, the machine learning model is trained for a plurality of beams in the first cell 18 based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell 18, component carriers associated with the first cell 18, speed information associated with at least one wireless device 22 of the first cell 18, traffic pattern information associated with at least one wireless device 22 of the first cell 18, location information associated with at least one wireless device 22 of the first cell 18, capability information associated with at least one wireless device 22 of the first cell 18, and spatial information associated with at least one wireless device 22 of the first cell 18, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell 18, and at least one historical beam switching pattern associated with at least one wireless device 22 of the first cell 18.

In some embodiments, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. In some embodiments, the first indication is a transmission configuration indication (TCI). In some embodiments, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RS SI), a channel quality indicator (CQI), and an interference plus noise estimate.

In some embodiments, the first time offset value is restricted to being not less than a legacy fixed time offset value. In some embodiments, the network node 16 is further configured to compare a first metric of the first beam with a corresponding metric of the active beam, and only transmits the first indication when a difference between the first metric of the first beam and the corresponding metric of the active beam exceeds a preconfigured threshold.

In some embodiments, the network node 16 is further configured to determine a probability value associated with the first beam, the first probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam, and only causing transmission of the first indication when the probability value exceeds a preconfigured threshold.

In some embodiments, the network node 16 is further configured to detect an increase in network congestion, and increase the preconfigured threshold based on the detected increase in network congestion. In some embodiments, the network node 16 is further configured to transmit to the wireless device 22 radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, where the first beam switching indication indicates the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. In some embodiments, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device 22 during a plurality of corresponding time instances.

FIG. 10 is a flowchart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of wireless device 22 such as by one or more of processing circuitry 50 (including the beam measurement reporting unit 26), processor 52, and/or radio interface 46. Wireless device 22 is configured to transmit (Block SI 22) to the network node 16 a first channel measurement report associated with the first wireless device 22 and at least one beam. Wireless device 22 is configured to receive (Block S124), responsive to the transmission of the first channel measurement report, a first beam switching indication, where the first beam switching indication indicates a first beam and a first time window for switching. Wireless device 22 is configured to switch (Block S126) from an active beam to the first beam for signaling during the first time window. Wireless device 22 is configured to optionally, transmit (Block SI 28) to the network node 16 signaling using the first beam during the first time window.

In some embodiments, the first channel measurement report includes at least one channel quality metric associated with at least one of the first beam, the active beam, at least one additional beam associated with the first wireless device 22, at least one additional beam associated with at least one additional wireless device 22 in the first cell 18, and reference signaling received by the first wireless device 22. In some embodiments, the first indication indicates the first time window by indicating at least one of a first time offset value associated with the first time window, a first symbol number associated with the first time window, and a first slot index associated with the first time window, a subframe number associated with the first time window, a system frame number associated with the first time window, and an absolute time associated with the first time window. In some embodiments, at least one of the first beam and the first time window is determined based on a machine learning model, where the machine learning model is configured to determine a first beam quality metric of the first beam based on at least one of the first channel measurement report, at least one additional channel measurement report associated with at least one additional wireless device 22, uplink signal quality information associated with the wireless device 22, and traffic information associated with at least one neighboring cell.

In some embodiments, the first beam quality metric is further determined based on at least one of speed information associated with the first wireless device 22, a traffic pattern associated with the first wireless device 22, location information associated with the first wireless device 22, capability information associated with the first wireless device 22, and spatial information associated with the first wireless device 22. In some embodiments, the machine learning model includes at least one of a decision tree model, a random forest model, a feed forward neural network model, an autoregressive model, a convolutional neural network model, a Long Short-term memory (LSTM) model, and a reinforcement learning model. In some embodiments, the first indication further indicates at least one additional time window and the at least one additional beam for switching, where the at least one additional beam is determined based on at least one of the first measurement report and the machine learning model, and where the at least one additional time window is determined based on at least one of the first measurement report and the machine learning model, and the wireless device 22 is further configured to, optionally, responsive to receiving the first indication, transmit additional signaling using the at least one additional beam during the at least one additional time window.

In some embodiments, the machine learning model is trained for a plurality of beams in the first cell 18 based on at least one of at least one input including at least one of a reference signal received power (RSRP) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a reference signal received quality (RSRQ) associated with the plurality of beams during at least one of a previous N-slots and a current slot, a signal to interference and noise ratio (SINR) associated with the plurality of beams during at least one of a previous N-slots and a current slot, location information associated with the first cell 18, component carriers associated with the first cell 18, speed information associated with at least one wireless device 22 of the first cell 18, traffic pattern information associated with at least one wireless device 22 of the first cell 18, location information associated with at least one wireless device 22 of the first cell 18, capability information associated with at least one wireless device 22 of the first cell 18, and spatial information associated with at least one wireless device 22 of the first cell 18, and at least one training output label including at least one of at least one historical beam switching pattern associated with at least one transmission and reception point associated with the first cell 18, and at least one historical beam switching pattern associated with at least one wireless device 22 of the first cell 18.

In some embodiments, the first indication is indicated by at least one of a downlink control indication (DCI) and a medium access control (MAC) control element (CE) command. In some embodiments, the first indication is a transmission configuration indication (TCI). In some embodiments, the first channel measurement report includes at least one of a signal to interference and noise ratio (SINR), a reference signal received quality (RSRQ), a reference signal received power (RSRP), a received signal strength indicator (RS SI), a channel quality indicator (CQI), and an interference plus noise estimate. In some embodiments, the first time offset value is restricted to being not less than a legacy fixed time offset value. In some embodiments, the first indication is only received when a difference between a first metric of the first beam and a corresponding metric of the active beam exceeds a preconfigured threshold. In some embodiments, the first indication is only received when a probability value corresponding to a probability that a first metric of the first beam will exceed a corresponding metric of the active beam exceeds a preconfigured threshold. In some embodiments, the preconfigured threshold is increased based on a detected increase in network congestion. In some embodiments, the wireless device 22 is further configured to receive radio resource control (RRC) signaling indicating a plurality of time offset values associated with a plurality of corresponding index values, where the first beam switching indication indicates the first time window by indicating a first index value associated with a first time offset value of the plurality of time offset values. In some embodiments, the first channel measurement report is associated with a plurality of measurements performed by the first wireless device 22 during a plurality of corresponding time instances.

Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for prediction-based beam management.

One or more network node 16 functions described below may be performed by one or more of hardware 28, radio interface 30, antennas 34, processing circuitry 36, memory 40, processor 38, and/or beam prediction unit 24. One or more wireless device 22 functions described below may be performed by one or more of hardware 44, radio interface 46, antennas 48, processing circuitry 50, memory 54, processor 52, and/or beam measurement reporting unit 26.

Some embodiments provide for an enhanced TCI indication framework by utilizing an Al based beam management algorithm, including, for example, a flexible TCI switch time offset (compared to fixed timing rules in existing 3GPP standards) may indicate the prediction of beam switch to the wireless device 22, e.g., by utilizing an Al-based BM algorithm, and/or an indication of several TCI switch instances (e.g., consecutive state switches), where each instance may be accompanied with a different time offset, and/or where these set of switches may be indicated within the same signaling indication message and/or in multiple signaling indication messages.

One or more embodiments described herein may provide a more flexible and more efficient beam switching signaling, e.g., for AI-/ML-assisted beam management, as compared to existing systems/standards.

A flexible TCI switch time offset may aid in distributing of PDCCH/MAC CE (carrying the indication signaling) load(s) for beam switches over slots, since not all wireless devices 22 (e.g., wireless devices 22 located on a moving bus or train) may need to receive the TCI switch simultaneously (in same slot). This may reduce higher layer processing load in the network node 16 (e.g., a gNB) and may aid in allowing the wireless device 22 to have more time to prepare for beam switch (for synchronization, etc.) as compared to techniques used in existing systems.

An indication of several TCI state switches with the same DCI and/or MAC CE command may aid in reducing the signaling overhead, e.g., by avoiding the need to transmit a separate signaling for each beam switching instance, as compared to existing techniques.

Although some of the embodiments and examples described herein relate to Al and/or ML techniques, the flexible TCI switch time offset and indication of several TCI state switches is not limited to Al-based solutions and may apply to other beam management solutions/scenarios.

The techniques described herein include receiving measurement reports at the network node 16, from one or more wireless devices 22, the reports being associated with multiple beams. The measurement report(s) provided by the wireless devices 22 (e.g., as generated by beam measurement reporting unit 26 of each wireless device 22) may include one or multiple Ll-RSRP values for each given beam, where each such value may correspond to a measurement at a certain point in time. Hence, the measurement reports may contain the time evolution of the Ll-RSRP for a set of beams for one or more wireless devices 22.

The measurement reports may be input into a beam switching algorithm (e.g., implemented by beam prediction unit 24) that predicts future beam switching events for one or more wireless devices 22. Such algorithms may also take as input other information sources, such as wireless device 22 uplink (UL) signal quality information estimated at the network node, traffic information from neighboring cells, the interference state of the cell/network, and/or other information.

The output of the beam switching prediction algorithm may provide information about when a beam switch is likely needed for a wireless device 22 to, for example, maintain good performance (e.g., a signal to noise ratio (SNR) or RSRP measurements above a certain threshold). The algorithm may indicate one or more beams, with corresponding time windows, for the wireless device 22. Hence, the output of these prediction algorithms, with associated confidence intervals, may include:

A prediction or forecasting of signal quality of one or more beams in certain (future) time windows according to defined criteria, e.g., strongest beam (e.g., where “strongest” beam(s) may refer to the beam(s) with the highest receive power, signal-to-noise ratio, quality, and/or throughput, etc., compared to other beams and/or those beam/beams with quality/power/noise/interference/etc. characteristics above/below one or more thresholds, which thresholds may be defined by the network node 16, e.g., in an indication/control signal sent to wireless device 22 and/or may be preconfigured in the wireless device 22). The signal qualities may be used to derive the suitable beam in each time-window, e.g., the strongest beam. The confidence intervals may include estimates of the //-th order moments of the signal qualities for each predicted beam, in each predicted time-window; o Signal qualities may include/may be based on Signal to Interference plus Noise Ratio (SINR), RSRQ, RSRP, Received Signal Strength Indicator (RSSI), channel quality indicator (CQI), and/or other interference, quality, power, and/or noise estimates/measurements; and o In addition to the strongest beam prediction, the decision to perform a beam switch may be based on other criteria, e.g., a threshold, such as the relation between the RSRP of the currently active beam and the RSRP of the subsequent, predicted beam. For example, if the algorithm predicts that the RSRP of a different beam will be larger than the RSRP of the current beam plus the threshold in some future time window, then the network node 16 may recommend a beam switch at that point in future;

A prediction or forecasting of the strongest beam(s) in each time-window. If the beams have similar probabilities in being the strongest (e.g., the beams’ have probability values which are within a particular range, probability values above a threshold, probability values which differ by a values less than a threshold, etc.), this may imply that the prediction is highly uncertain (e.g., above a predefined certainty threshold), and may be used to determine whether to use a legacy procedure or a prediction-based TCI indication. o A beam switch threshold may also be associated with a probability p, which may be used, e.g., to recommend a beam switch if the difference in strongest beam probability between the predicted best beam and current beam is larger than a certain threshold p.

The forecasted output of the ML-model implemented by network node 16 is defined with respect to a certain time-window, including, for example, subframe number, slot index, and/or system frame number. Alternatively, the forecasted output could be defined with respect to an absolute time using Coordinated Universal Time (UTC). For each time-window forecast, it may be possible to estimate the time when using each of these beams is most beneficial (e.g., when each of these beams provides one or more better beam characteristics compared to the other beams).

The forecast for each time-window may then be used as an activation time stamp and a deactivation time stamp for a given beam. These time stamps may be represented as an offset from a reference point in time, e.g., the time when the inference was made. The time stamp may include an activation time stamp.

Example ML models for predicting the future signal quality values include, but are not limited to, decision tree models, random forest models, feed forward neural network models, autoregressive models, convolutional neural network models. The time-window for forecast may be used as an input to the model, or the network node may train a separate model for each potential future time-window (one model predicts Z+l, another model predicts /+2, etc.).

One or more embodiments described herein provide an (implementation based) algorithm that predicts future beam switches that may correspond to specific changes in the NR standard, which are captured in one or more of the following examples.

Example 1: Indication of TCI state switch with flexible timing offset

The TCI state switch may be indicated to the wireless device 22 with a flexible switching time offset. For example, in some embodiments, if the wireless device 22 has indicated that it supports this new type of signaling, then the network node may transmit a message to the wireless device 22 to switch to a new active TCI state at a certain point in time which may be dynamically indicated (e.g., instead of using a fixed time offset). In addition, the legacy NR specification may have a further restriction that the signaled time offset cannot be smaller than the existing (legacy) offset. In some embodiments of the present disclosure, the network node 16 may select the TCI state switch time instances based on a confidence in the forecasted value, for example, the network node 16 may only include the switch instances if the new beam is stronger than the previous beam by a certain threshold value. The value may be determined by network node 16 information, such as if the network/network node experiences congestion, then it may be beneficial to reduce the signaling overhead regarding the TCI states.

The timing offset may be determined based on the prediction according to an algorithm (e.g., an AI/ML algorithm implemented by network node 16), as described herein.

The timing offset for PDCCH may be provided in the MAC CE activation command, and/or in any other suitable command, such as RRC signaling, e.g., including new RRC parameters associated with TCI-state information element (IE), e.g., a tci-symbolOffset parameter and a tci-slotOffset parameter in the TCI-State information element in RRC configuration, for example:

TCI-State-rell8 SEQUENCE { tci-Stateld TCI-Stateld, tci- symbol Offset INTEGER (0 .13) tci-slotOffset INTEGER (0..32) qcl-Typel QCL-Info, qcl-Type2 QCL-Info OPTIONAL, - Need R

QCL-Info ::= SEQUENCE { cell ServCelllndex OPTIONAL, - Need R bwp-Id BWP-Id OPTIONAL, - Cond CSI-RS-

Indicated referencesignal CHOICE { csi-rs NZP-CSI-RS-Resourceld, ssb S SB -Index

}, qcl-Type ENUMERATED {typeA, typeB, typeC, typeD},

Timing offsets may also be defined as fixed values, e.g., as a table of fixed values.

A timing offset for a channel (e.g., the PDSCH) may be indicated in the corresponding signaling (e.g., the DCI) that schedules the channel, or in any other suitable signaling. Different bit pattem(s) of the codepoint may be interpreted by a corresponding table, e.g., a predetermined table defined in the standard, or may be defined with signaling, such as RRC signaling.

Example 2: Indication of several TCI state switches with the same signaling instance

More than one TCI state switches may be simultaneously (or near simultaneously) indicated to the wireless device 22 in one or more messages, where one or more of these switches may be associated with a flexible switching time offset. For example, in some embodiments, if the wireless device 22 has indicated that it supports this new type of signaling, then the network node 16 may transmit a message to the wireless device 22 to switch to multiple new active TCI states, for example, each at certain points in time. The first switch, e.g., occurring first in time, A, may be treated as a special case, for example, and may follow the legacy timing offset, while the subsequent indicated switches (e.g., TCI state and time stamp/offset) may be dynamically indicated, e.g., given by information in the message, as described herein.

The time offsets may be configured by higher layers from the network/network node 16 to the wireless device 22. Hence, the beam switches may occur at semi-statically configured points in time (offsets). In this case, only the two or more TCI states may be signaled dynamically to the wireless device 22, e.g., as obtained from the AI/ML method implemented by the network node 16.

The TCI framework may include the indication of several TCI-states, e.g., with corresponding time stamps, which may be based on the prediction obtained according to the AI/ML-assisted method techniques described herein.

The signaling may be implemented using, for example, RRC signaling and/or introducing new RRC parameters, such as in the TCI-state IE fields, e.g., introducing information elements, such as:

TCI-StateList ::= SEQUENCE (SIZE (l..maxNrofTCI-State-rell8)) OF TCI-State-rell8

The TCI-StateList may be a list of different tci-states, e.g., each with different time stamps, each indicating different configurations, etc.

Several TCI fields may be included in signaling, such as a DCI signal/message, from the network node 16 to the wireless device 22. Each field of the signaling may indicate one or more beam switches and/or time values. For example, the DCI may indicate the switching of corresponding beam(s) (e.g., PDSCH beams) at indicated point(s) in time.

Alternatively, or additionally, the TCI field in the DCI may contain a number (e.g., up to 8) of TCI code points. A TCI code point may contain multiple TCI states, where each TCI state may include an indication to the wireless device 22 to switch to that TCI state at the indicated point in time. Hence, even if the wireless device 22 is configured with multiple TCI states simultaneously or near simultaneously, only one of them may be used at a time.

Each TCI code point may be associated with a time offset. Therefore, when that TCI code point is indicated in the signaling (e.g., the DCI) transmitted from the network node 16 and received at the wireless device 22, the wireless device 22 may be instructed/indicates to switch to the TCI state in that TCI code point, and the wireless device 22 may be instructed/indicated to not use the legacy offset but instead use the indicated time offset associated with the code point, as described herein.

Some or all of the TCI fields in the signaling (e.g., the DCI) may be used to indicate the timing offset of beam switching for corresponding beam switches (e.g., PDCCH beam switches).

Example 3: Beam switching prediction algorithm

The prediction of beam switching (or beam switching pattem(s)) may be conducted using AI/ML models/agents in the network node 16 and/or the wireless device 22. Such models may include supervised learning, unsupervised learning, and/or reinforcement learning, although other learning and/or prediction models may be used without deviating from the scope of the present disclosure.

In some embodiments (using, e.g., beam prediction unit 24 and historical beam and timing data stored in memory 40), a supervised learning model, such as a random forest, Long Short-term memory (LSTM), feed forward neural network, etc., may be trained to learn the pattern of up to N beam switching instances for a given wireless device 22 connected to a given TRP.

The input and output of such learning agent may be the same for both training and inference stages, or may be different.

The input features for the AI/ML agent/model implemented by network node 16 may include, e.g.:

• Measurements related to beam management processes, which may include, e.g., RSRP, RSRQ, SINR, etc., with corresponding beam indices, and may be associated with, e.g.: o One or more previous slots (e.g., N previous slots), o A current slot, and/or o Predicted measurement(s) of future slot(s);

• Deployment information, which may include, e.g., cell ID, component carrier indices, x-y coordinates of the cells, nodes, neighbors, etc. associated with beam switching instances; • Context information of the wireless device 22, which may include, e.g., speeds, traffic patterns, x-y coordinates, wireless device 22 capabilities, etc.;

• Spatial information for the wireless device 22, such as beams that the wireless device is/was connected to, including, e.g., AoA, DoA, etc.

The AI/ML model outputs (and the training output labels) may include, e.g.: o Beam switching pattem(s) for given TRPs of the beam(s) under consideration, including, e.g., indices of the beams that are switched at each switching instance, a corresponding time stamp, etc. This prediction may be applied for a single wireless device 22 and/or for other wireless devices 22, e.g., wireless devices 22 that may be connected to the same TRP (e.g., network node 16) at a subsequent time. This output may also be associated with one or more slots or slot numbers, e.g., a pair of two output branches may include one or more associated slot number(s) and one or more beam(s) to switch to.

A predictive model may be provided whereby the network node 16 may predict future/sub sequent beams (and/or beam indices), and corresponding time stamps for one or several beam switching instances for the corresponding TRP(s). The timestamps may be, e.g., an offset from the moment prediction is done, and/or may include another time value, e.g., a time value from which an offset may be determined.

The target beams for prediction may be SSB beams and/or CSI-RS beams, though the present disclosure is not so limited and may be implemented in any applicable beamforming configuration.

In some embodiments, a reinforcement learning agent (e.g., implemented by beam prediction unit 24) may be used to make an educated/estimated guess/action as to when and where to switch beams. Because this may be a time-related problem, in some embodiments, it may be undesirable to use a highly complex/computationally intensive model, such as a Deep Q-Leaming (DQN) type of reinforcement learning. Instead, an alpha-zero type of reinforcement learning, e.g., where timely steps are considered, and/or a guided tree-based decision, may be used in some embodiments to produce an optimal/semi-optimal decision. This reinforcement learning agent may be characterized by an action, state, and reward tuple, for example, or by any other suitable data structure. For example, the reinforcement learning may have N episodes, M steps, K periods which each action span over:

Actions:

1. At given period k, shift by single step of +1 or -1, to the next or previous beam; OR

2. Jump by +b or -b beams at every k.

States:

1. Beam measurement, as described herein;

2. Contextual information, deployment information, spatial information, etc.; and/or

3. Abstraction information, e.g., load/traffic information associated with the network/serving cell/network node 16/neighbor cells/wireless devices 22/etc.

Rewards:

1. SINR, RSRP, RSRQ, or similar measurements of beam and/or link quality;

2. Throughput or similar measurements; and/or

3. Weighted sum(s) of SINR, throughput, etc.

In some embodiments, a shielding agent may be utilized which compares the action of reinforcement learning and action with the baseline solution to aid in improving the performance of the reinforcement learning agent by comparing the reward of the baseline (or legacy) solution with the reward of the reinforcement learning actions.

FIG. 11 is a diagram of an example signaling configuration for some embodiments of the present disclosure. A wireless device 22 moves in space according to the trajectory shown in FIG. 11. The network node 16 transmits (Step SI 30) a plurality of SSB beams to the wireless device 22 over time as the wireless device 22 moves along the trajectory (Steps 132a-d). At Step 132a, WD 22 receives one or more SSB beams at a first location along the trajectory. At Step S132b, WD 22 receives one or more SSB beams at a second location along the trajectory. At Step S132c, WD 22 receives one or more SSB beams at a third location along the trajectory. At Step S132d, WD 22 receives one or more SSB beams at a fourth location along the trajectory. At time Z=3, the wireless device 22 may generate/cause transmission of one or more Ll-RSRP reports (Step S134) to the network node 16, which may store (Step S136) the reports in a Ll-RSRP history database, e.g., stored in memory 40 of network node 16. The machine learning model of the network node 16, e.g., as implemented by beam prediction unit 24, may use the Ll-RSRP report history to predict (Step S138) a TCI state switch for the wireless device 22 to occur X slots subsequent to the present slot. The network node 16 transmits (Step S140) to a wireless device 22 a MAC CE with TCI state switch command(s) to execute after the offset of X slots from the present slot.

FIG. 12 depicts an example machine learning model according to some embodiments of the present disclosure. At time Z=0, the wireless device 22 connects to the network node 16. The network node 16 may configure the wireless device 22 to perform measurements on a set of time-frequency resources (e.g., on a number of beams). The network node 16 may perform the machine learning model inference based on the values observed during the observation period t=0 to t=3. At time t=4, the network node 16 predicts beam signal quality values of future time instances (e.g., t=5, t=6, etc.). This prediction may include a confidence interval of predicted signal quality estimates.

Some Examples:

Example Al . A network node 16 configured to communicate with a wireless device 22, the network node 16 configured to, and/or comprising a radio interface and/or comprising processing circuitry 36 configured to: receive at least one measurement report from the wireless device 22, each of the at least one measurement report being associated with a plurality of beams; determine, based on the at least one measurement report, a plurality of beam switching instances, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window; and transmit, to the wireless device 22, an indication of the plurality of beam switching instances, the indication indicating the wireless device 22 to switch to the at least one corresponding beam during the corresponding time window.

Example A2. The network node 16 of Example Al, wherein determining the plurality of beam switching instances includes: generating a prediction model based on the at least one measurement report; determining, using the prediction model, a plurality of beam quality predictions and corresponding time values; and determining, for each of the plurality of beam switching instances, the at least one corresponding beam to switch to and the corresponding time window based on the plurality of beam quality predictions and corresponding time values.

Example A3. The network node 16 of Example A2, wherein determining the at least one corresponding beam to switch to includes selecting, for each corresponding time window, a maximum from the plurality of beam quality predictions.

Example Bl. A method implemented in a network node 16 that is configured to communicate with a wireless device 22, the method comprising: receiving at least one measurement report from the wireless device 22, each of the at least one measurement report being associated with a plurality of beams; determining, based on the at least one measurement report, a plurality of beam switching instances, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window; and transmitting, to the wireless device 22, an indication of the plurality of beam switching instances, the indication indicating the wireless device 22 to switch to the at least one corresponding beam during the corresponding time window.

Example B2. The method of Example Bl, wherein determining the plurality of beam switching instances includes: generating a prediction model based on the at least one measurement report; determining, using the prediction model, a plurality of beam quality predictions and corresponding time values; and determining, for each of the plurality of beam switching instances, the at least one corresponding beam to switch to and the corresponding time window based on the plurality of beam quality predictions and corresponding time values.

Example B3. The method of Example B2, wherein determining the at least one corresponding beam to switch to includes selecting, for each corresponding time window, a maximum from the plurality of beam quality predictions.

Example Cl . A wireless device 22 configured to communicate with a network node 16, the wireless device 22 configured to, and/or comprising a radio interface and/or processing circuitry 50 configured to: transmit at least one measurement report to the network node 16, each of the at least one measurement report being associated with a plurality of beams; receive, from the network node 16, an indication of a plurality of beam switching instances, each of the plurality of beam switching instances being determined based on the at least one measurement report, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window; and switch, based on the indication, to at least one corresponding beam during the corresponding time window.

Example C2. The wireless device 22 of Example Cl, wherein the plurality of beam switching instances is determined based at least on: generating a prediction model based on the at least one measurement report; determining, using the prediction model, a plurality of beam quality predictions and corresponding time values; and determining, for each of the plurality of beam switching instances, the at least one corresponding beam to switch to and the corresponding time window based on the plurality of beam quality predictions and corresponding time values.

Example C3. The wireless device 22 of any one of Examples Cl and/or C2, wherein the plurality of beam switching instances are associated with a trajectory of the wireless device 22.

Example DI . A method implemented in a wireless device 22 that is configured to communicate with a network node 16, the method comprising: transmitting at least one measurement report to the network node 16, each of the at least one measurement report being associated with a plurality of beams; receiving, from the network node 16, an indication of a plurality of beam switching instances, each of the plurality of beam switching instances being determined based on the at least one measurement report, each of the plurality of beam switching instances being associated with at least one corresponding beam of the plurality of beams and a corresponding time window; and switching, based on the indication, to at least one corresponding beam during the corresponding time window.

Example D2. The method of Example DI, wherein the plurality of beam switching instances is determined based at least on: generating a prediction model based on the at least one measurement report; determining, using the prediction model, a plurality of beam quality predictions and corresponding time values; and determining, for each of the plurality of beam switching instances, the at least one corresponding beam to switch to and the corresponding time window based on the plurality of beam quality predictions and corresponding time values.

Example D3. The method of any one of Examples DI and/or D2, wherein the plurality of beam switching instances are associated with a trajectory of the wireless device 22.

As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and/or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and/or functionality described herein may be performed by, and/or associated to, a corresponding module, which may be implemented in software and/or firmware and/or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

Some embodiments are described herein with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

It is to be understood that the functions/acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows. Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined in any way and/or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

Abbreviations that may be used in the preceding description include:

3GPP 3rd Generation Partnership Project

5G Fifth Generation

ACK Acknowledgement

Al Artificial Intelligence

Ao A Angle of Arrival

CORESET Control Resource Set

CSI Channel State Information

CSLRS CSI Reference Signal

CQI Channel Quality Indicator

DCI Downlink Control Information

DoA Direction of Arrival DL Downlink

DMRS Downlink Demodulation Reference Signals

FDD Frequency-Division Duplex

FR2 Frequency Range 2

HARQ Hybrid Automatic Repeat Request

ID identity gNB gNodeB

MAC Medium Access Control

MAC-CE MAC Control Element

ML Machine Learning

NR New Radio

NW Network

OFDM Orthogonal Frequency Division Multiplexing

PBCH Physical Broadcast Channel

PCI Physical Cell Identity

PDCCH Physical Downlink Control Channel

PDSCH Physical Downlink Shared Channel

PRB Physical Resource Block

QCL Quasi co-located

RB Resource Block

RRC Radio Resource Control

RSRP Reference Signal Strength Indicator/Reference Signal Receive Power

RSRQ Reference Signal Received Quality

RS SI Received Signal Strength Indicator

SCS Subcarrier Spacing

SINR Signal to Interference plus Noise Ratio

SSB Synchronization Signal Block

RL Reinforcement Learning

RS Reference Signal

Rx Receiver

TB Transport Block TDD Time-Division Duplex

TCI Transmission configuration indication

TRP Transmission/Reception Point

Tx Transmitter UE User Equipment

UL Uplink

It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings without departing from the scope of the following claims.