Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SYSTEM AND METHOD TO VERIFY A RESPONSE SIGNATURE FROM A WIRELESS COMMUNICATION DEVICE
Document Type and Number:
WIPO Patent Application WO/2019/122984
Kind Code:
A1
Abstract:
A system and method to verify a response signature from a wireless communication device (920) in accordance with a statistical model. In one embodiment, the apparatus (930) is configured to ping (1020) the wireless communication device (920) positioned at a location (905) in a physical grid (905), and receive (1030) a ping response from the wireless communication device (920). The apparatus (930) is also configured to compare (1040) a ping response signature to an expected ping response signature for the location (910) to ascertain if the ping response is consistent with the statistical model associated with the expected ping response signature, and report (1070) an error condition if the ping response signature is inconsistent with the expected ping response signature.

Inventors:
VALENTINE ERIC LEE (US)
BEDHU KALYANA CHAKRAVARTHY (IN)
COLLIER GEORGE (US)
SUNDSTEDT BO (US)
Application Number:
IB2017/058323
Publication Date:
June 27, 2019
Filing Date:
December 22, 2017
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ERICSSON TELEFON AB L M (SE)
International Classes:
H04W4/35; G01S5/02; H04W4/029; H04W4/70
Foreign References:
US20090201152A12009-08-13
US20150371139A12015-12-24
Other References:
ALEKSANDAR JOVICIC ET AL: "Mobile device positioning using learning and cooperation", INFORMATION SCIENCES AND SYSTEMS (CISS), 2012 46TH ANNUAL CONFERENCE ON, IEEE, 21 March 2012 (2012-03-21), pages 1 - 6, XP032241508, ISBN: 978-1-4673-3139-5, DOI: 10.1109/CISS.2012.6310930
None
Attorney, Agent or Firm:
BOISBRUN, Glenn W. (PLLC12900 Preston Road, Suite 20, Dallas Texas, US)
Download PDF:
Claims:

WHAT IS CLAIMED IS:

1. An apparatus (930) operable in a communication system (900) including a wireless communication device (920), comprising:

processing circuitry (515), configured to:

ping said wireless communication device (920) positioned at a location

(905) in a physical grid (905);

receive a ping response from said wireless communication device (920); compare a ping response signature to an expected ping response signature for said location (910) to ascertain if said ping response is consistent with a statistical model associated with said expected ping response signature; and

report an error condition if said ping response signature is inconsistent with said expected ping response signature.

2. The apparatus (930) as recited in Claim 1 wherein said location (905) comprises a base, a tier, and a row of an object (910) including said wireless communication device (920).

3. The apparatus (930) as recited in Claim 2 wherein said statistical model is dependent on said base, said tier, and said row of said object (910).

4. The apparatus (930) as recited in Claim 2 wherein said object (910) is a container positioned onboard a vessel (110).

5. The apparatus (930) as recited in Claim 1 wherein said statistical model is employed for a plurality of wireless communication devices (920).

6. The apparatus (930) as recited in Claim 1 wherein said processing circuitry (515) is further configured to associate a timestamp with said location (905) and said ping response signature.

7. The apparatus (930) as recited in Claim 6 wherein said processing circuitry (515) is further configured to store said timestamp, said location (905) and said ping response signature in memory (530, 940).

8. The apparatus (930) as recited in Claim 7 wherein said memory (530, 940) is remotely located from said wireless communication device (920).

9. The apparatus (930) as recited in Claim 1 wherein said processing circuitry (515) is further configured assess a quality of radio coverage of said wireless communication device (920) in accordance with said statistical model.

10. The apparatus (930) as recited in Claim 1 wherein said processing circuitry (515) is further configured to build said statistical model from a plurality of wireless communication devices (920) identifying said location (905) and said expected ping response signature.

11. The apparatus (930) as recited in Claim 1 wherein said processing circuitry (515) is further configured to build said statistical model using machine learning and predictive analytic techniques.

12. The apparatus (930) as recited in Claim 1 wherein said statistical model is configured to predict a failure mode of said wireless communication device (920).

13. The apparatus (930) as recited in Claim 1 wherein said error condition comprises a received signal strength indication of said wireless communication device (920) being beyond a range of values within said statistical model.

14. The apparatus (930) as recited in Claim 1 wherein said statistical model is configured to predict a future value of said ping response signature.

15. The apparatus (930) as recited in Claim 14 wherein said statistical model is configured to prioritize an impact, flag and categorize deviations of a predicted future value into an urgency bin.

16. The apparatus (930) as recited in Claim 1 wherein said statistical model is configured to describe communication characteristics of said wireless communication device (920).

17. The apparatus (930) as recited in Claim 16 wherein said communication characteristics comprise at least one of a bit-error rate, an expected signal amplitude, a data rate and a communication technology.

18. The apparatus (930) as recited in Claim 1 wherein said wireless communication device (920) is an Internet of Things (IoT) device.

19. A method (1000) operable in a communication system (900) including a wireless communication device (920), comprising:

pinging (1020) said wireless communication device (920) positioned at a location (905) in a physical grid (905);

receiving (1030) a ping response from said wireless communication device

(920);

comparing (1040) a ping response signature to an expected ping response signature for said location (910) to ascertain if said ping response is consistent with a statistical model associated with said expected ping response signature; and

reporting (1080) an error condition if said ping response signature is inconsistent with said expected ping response signature.

20. The method (1000) as recited in Claim 19 wherein said location (905) comprises a base, a tier, and a row of an object (910) including said wireless communication device (920).

21. The method (1000) as recited in Claim 20 wherein said statistical model is dependent on said base, said tier, and said row of said object (910).

22. The method (1000) as recited in Claim 21 wherein said object (910) is a container positioned onboard a vessel (110).

23. The method (1000) as recited in Claim 19 wherein said statistical model is employed for a plurality of wireless communication devices (920).

24. The method (1000) as recited in Claim 19 further comprising associating (1050) a timestamp with said location (905) and said ping response signature.

25. The method (1000) as recited in Claim 24 further comprising storing (1060) said timestamp, said location (905) and said ping response signature in memory (530, 940).

26. The method (1000) as recited in Claim 25 wherein said memory (530, 940) is remotely located from said wireless communication device (920).

27. The method (1000) as recited in Claim 19 further comprising assessing (1070) a quality of radio coverage of said wireless communication device (920) in accordance with said statistical model.

28. The method (1000) as recited in Claim 19 further comprising building (1010) said statistical model from a plurality of wireless communication devices (920) including identifying said location (905) and said expected ping response signature.

29. The method (1000) as recited in Claim 19 wherein said building (1010) comprises building said statistical model using machine learning and predictive analytic techniques.

30. The method (1000) as recited in Claim 19 wherein said statistical model is configured to predict a failure mode of said wireless communication device (920).

31. The method (1000) as recited in Claim 19 wherein said error condition comprises a received signal strength indication of said wireless communication device (920) being beyond a range of values within said statistical model.

32. The method (1000) as recited in Claim 19 wherein said statistical model is configured to predict a future value of said ping response signature.

33. The method (1000) as recited in Claim 32 wherein said statistical model is configured to prioritize an impact, flag and categorize deviations of a predicted future value into an urgency bin.

34. The method (1000) as recited in Claim 19 wherein said statistical model is configured to describe communication characteristics of said wireless communication device (920).

35. The method (1000) as recited in Claim 34 wherein said communication characteristics comprise at least one of a bit-error rate, an expected signal amplitude, a data rate and a communication technology.

36. The method (1000) as recited in Claim 19 wherein said wireless communication device (920) is an Internet of Things (IoT) device.

Description:
SYSTEM AND METHOD TO VERIFY A RESPONSE SIGNATURE

FROM A WIRELESS COMMUNICATION DEVICE

TECHNICAL FIELD

The present invention is directed, in general, to communication systems and, more particularly, to a system and method to verify a response signature from a wireless communication device in accordance with a statistical model.

BACKGROUND

increasingly, wireless communication devices are used as part of Internet of Things (“loT”) solutions. For example, logistics are increasingly lo'T enabled and communication dependent. One example of IoT-enabled logistics is related to refrigerated containers. For refrigerated containers, loT devices communicate their status as well as alarms, and facilitate the download of new firmware and software.

This communication enablement provides many benefits including near real-time tracking of container contents and condition. However, this capability requires communication in realtime. If the wireless communication device loses connectivity, then the container and its contents may become impaired.

Accordingly, what is needed in the art is a system and method that can anticipate communication failures, and predict the ability of the wireless communication devices to communicate with a grade of service.

SUMMARY

These and other problems may be generally solved or circumvented, and technical advantages may be generally achieved by advantageous embodiments that, for example, include a system and method to verify a response signature from a wireless

communication device in accordance with a statistical model. In one embodiment, the apparatus is configured to ping the wireless communication device positioned at a location in a physical grid, and receive a ping response from the wireless communication device. The apparatus is also configured to compare a ping response signature to an expected ping response signature for the location to ascertain if the ping response is consistent with the statistical model associated with the expected ping response signature, and report an error condition if the ping response signature is inconsistent with the expected ping response signature. The foregoing has outlined rather broadly the features and technical advantages of the present examples in order that the detailed description that follows may be better understood. Additional features and advantages of various examples will be described hereinafter, which form the subject of the claims of the invention. It should be appreciated by those skilled in the art that the conception and specific embodiments disclosed may be readily utilized as a basis for modifying or designing other structures or processes for carrying out the same purposes of different embodiments. It should also be realized by those skilled in the art that such equivalent constructions do not depart from the spirit and scope of the disclosure as set forth in the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

For a more complete understanding of the present invention, reference is now' made to the following descriptions taken in conjunction with the accompanying drawings, in which:

FIGURE 1 illustrates a view of an embodiment of a maritime vessel having first and second antenna sectors;

FIGURE 2 illustrates a view of an embodiment of a first maritime vessel in communication with a second maritime vessel and in a communication range with an external network;

FIGURE 3 illustrates a view of an embodiment of a first maritime vessel in communication with a second maritime vessel and a first external network;

FIGURE 4 illustrates a block diagram of an embodiment of a communication system onboard a maritime vessel ;

FIGURE 5 illustrates a block diagram of an embodiment of a computer system;

FIGURE 6 illustrates a graphical representation of received signal strengths onboard a maritime vessel;

FIGURE 7 illustrates a block diagram of a collection of objects onboard a maritime vessel stacked in a physical grid including rows, bays and tiers;

FIGURE 8 illustrates a tabular representation of a number of containers in rows, bays and tiers;

FIGURE 9 illustrates a block diagram of an embodiment of a communication system, or portions thereof, employable with a collection of objects onboard a maritime vessel stacked in a physical grid including rows, bays and tiers; and FIGURE 10 illustrates a flow diagram of an embodiment of a method of operating a communication system.

Corresponding numerals and symbols in the different figures generally refer to corresponding parts unless otherwise indicated, and may not be redescribed in the interest of brevity after the first instance. The FIGURES are drawn to illustrate the relevant aspects of exemplary embodiments.

DETAILED DESCRIPTION

The making and using of the present exemplary embodiments are discussed in detail below. It should be appreciated, however, that the embodiments provide many applicable inventive concepts that can be embodied in a wide variety of specific contexts. The specific embodiments discussed are merely illustrative of specific ways to make and use the systems, subsystems, and modules to verify a response signature from a wireless communication device in accordance with a statistical model. While the principles will be described in the environment of a Third Generation Partnership Program (“3GPP”) Long Term Evolution (“LTE”) communication system, any wireless communication environment is well within the broad scope of the present disclosure.

Referring initially to FIGURE 1, illustrated is a view of an embodiment of a maritime vessel (also referred to as a“vessel”) 110 having first and second antenna sectors 120, 130. The maritime vessel 110 is close, but outside of a national legal boundary 140 that accommodates a communication range (genetically designated 150) to at least one of a plurality of external networks {e.g., terrestrial networks) 160, 170 within a shore line 180 of a country or sovereign nation. The first and second antenna sectors 120, 130 are forward-facing toward and rear-facing from, respectively, the plurality of external networks 160, 170. It can be contemplated that at some point transmissions emanating from the first antenna sector 120 will be within the communication range 150 of at least one of the plurality of external networks 160, 170. This may create interference with ones of the plurality of external networks 160, 170. Under such circumstances, it may make sense to disable the first antenna sector 120 directed toward the plurality of external networks 160, 170 as the maritime vessel 110 moves in close proximity to and across the national legal boundary 140.

The national legal boundary 140 is a j urisdictional/national boundary and can be based on sovereignty, licensing, or other laws or regulations including regulations as specified in the United Nations Convention on the Law of the Sea. The second antenna sector 130 facing away from the plurality of external networks 160, 170 may continue to transmit (and potentially at a higher power level) when the first antenna sector 120 is disabled. At some point, however, the second antenna sector 130 may also be disabled based on the location of the maritime vessel 110 to the shore line 180 within the national legal boundary 140. For instance, it may be unlawful to transmit information in some frequency bands within the national legal boundary 140 regardless of the direction of an antenna sector even with respect to the second antenna sector 130 facing away from the plurality of external networks 160, 170.

A proximity of the maritime vessel 110 to the plurality of external networks 160, 170 can be determined by a stored map with the coordinates of the maritime vessel 110 derived from a global positioning system or by other locating means, or by having a radio“sniffer” onboard the maritime vessel 110 that can detect the plurality of external networks 160, 170 including what frequencies and standards are being used and by which operator(s). In the event that the maritime vessel 110 is within the

communication range 150 of the plurality of external networks 160, 170, at least one of the plurality of external networks 160, 170 can be used for communications to and from the maritime vessel 110, provided that suitable roaming agreements are in place. This communication can be done either by simply turning off an access network onboard the maritime vessel 110 and letting wireless com unication devices (also referred to as “communication devices” such as user equipment (“UE”) and Internet of Things (“loT”) devices) onboard the maritime vessel 110 to automatically swatch over to (or communicate directly with) one of the plurality of external networks 160, 170, or by enabling a device (e.g. , an interoperability unit) onboard the maritime vessel 110 to connect to at least one of the plurality of external networks 160, 170.

Turning now' to FIGURE 2, illustrated is a view' of an embodiment of a first maritime vessel 210 in communication with a second maritime vessel 220 and in a communication range 250 with an external network (e.g., a terrestrial network) 260.

The first maritime vessel 210 is within a national legal boundary 240 that

accommodates the communication range 250 to the external network 260 within a shore line 280 of a country or sovereign nation. Assuming that the external network 260 is a cellular network, a first communication path 215 from the first maritime vessel 210 and/or first communication devices thereon to the external network 260 is a cellular communication path governed by business rules such as roaming agreements and the like associated therewith. It should also be understood that the first communication devices may communicate with a first access network onboard the first maritime vessel 210 using a first standard (e.g. , IEEE standard 802.11 for Wi-Fi communications) and co municate over the first communication path 215 using a 3GPP LTE cellular standard.

The first maritime vessel 210 also communicates with the second maritime vessel 220 and/or second communication devices thereon via a second communication path 225 therebetween. The second communication path 225 serves as part of a transport network between first and second access networks onboard the first and second maritime vessels 210, 220, respectively. As illustrated, the second maritime vessel 220 is not within the communication range 250 of the external network 260 and is located outside of the national legal boundary 240. The second communication path 225 is typically unlicensed spectrum such as unlicensed LTE, WiMAX, microwave, etc. bands, which is unaffected by the business rules associated with the external network 260 within the national legal boundary 240. As described herein, the first mariti me vessel 210 may provide access to the external network 260 for the second

communication devices even though the second maritime vessel 220 is outside of the communication range 250 of the external network 260. In effect, the first maritime vessel 210 is serving as a conduit or relay for the second communication devices onboard the second maritime vessel 220.

As described with respect to FIGURE 2, an antenna sector of the first maritime vessel 210 facing away from the external network 260 may be energized (with increased power) to facilitate communication with the second maritime vessel 220 and the second communication devices. Depending on selected communication parameters, the aforementioned communication may be performed without impacting other communications (from other sources) with the external network 260. Thus, the second communication devices may communicate with a first access network and/or interoperability unit on the first maritime vessel 210, which in turn communicates with the external network 260. Turning now to FIGURE 3, illustrated is a view of an embodiment of a first maritime vessel 310 in communication with a second maritime vessel 320 and a first external network (e.g., a satellite network) 330. A first communication path 315 from the first maritime vessel 310 via satellite communication equipment (e.g., a very small aperture terminal and antenna) thereon to the first external network 330 is a satellite co munication path. The first maritime vessel 310 also communicates with the second maritime vessel 320 and/or second communication devices thereon via a second communication path 325 therebetween. The second communication path 325 serves as part of a transport network between first and second access networks onboard the first and second maritime vessels 310, 320, respectively. The second communication path 325 is typically unlicensed spectrum such as unlicensed LTE, WiMAX, microwave, etc. bands. As described herein, the first maritime vessel 310 may provide access to the first external network 330 for the second communication devices even though the second maritime vessel 320 is not communicating with the first external network 330. In effect, the first maritime vessel 310 is serving as a conduit or relay for the second communication devices onboard the second maritime vessel 320. It is possible that the second maritime vessel 320 is not equipped with satellite communication equipment or the satellite communication equipment has been disabled. It is also possible that the second maritime vessel 320 is bandwidth limited and would be better served to allow the second communication devices to communicate with the external network 330 via an alternative. In either case, the first maritime vessel 310 can accommodate communication to the first external network 330 for the second maritime vessel 320.

The first external network 330 communicates with a second external network (e.g., a terrestrial network) 340 via a third communication path 335 therebetween, which is connected to or includes a core network (“CN”) 350. The second external network 340 also is connected to a network operations center (“NOC”) 360. The network operations center 360 is responsible for maintaining communication parameters such as a central repository for the business rules. The network operations center 360 updates a business rules database onboard the first and second maritime vessels 310, 320, and maintains a central map regarding territorial boundaries. The network operations center 360 updates a map database on board the first and second maritime vessels 310,

320 and maintains a central repository with information regarding of external networks available in areas traveled by the first and second maritime vessels 310, 320. The network operations center 360 updates the external network database onboard each of the first and second maritime vessels 310, 320.

The network operations center 360 is responsible for communicating an initial set of rules, boundaries and network communications to the first and second maritime vessels 310, 320. Boundary information is typically relatively static, but business rules can be modified based on, for instance, new or updated roaming agreements or satellite bandwidth pricing agreements. Similarly, while discovery of new' external networks or previous external networks at a particular location may be determined on the vessel level, the central repository of the available external networks should be maintained and communicated to the first and second maritime vessels 310, 320 at a global level, especially as a maritime vessel moves into a new location. Satellite coverages can also change due to circumstances such as new satellites being placed into orbits, coverage from a beam on one satellite being replaced by a beam from another satellite, etc.

Turning now to FIGURE 4, illustrated is a block diagram of an embodiment of a communication system onboard a maritime vessel 400. The communication system includes wireless communication devices (one of which is designated 410 and again also referred to“communication devices”) in communication with access networks including a base station 420 and/or an access point 430 to form a type of local area network(s). A communication manager 440 of the communication system is in communication with the access networks and an interoperability unit 450. A transceiver 460 of the

communication system facilitates communication from and to the maritime vessel 400 with an external network and/or another maritime vessel. Of course, the aforementioned subsystems and modules, or portions thereof, may be combined into an integrated module, and/or include multiple instances thereof. The communication system, therefore, acts a gateway for communications from the communication devices 410 to the external network and/or another maritime vessel.

With respect to the access network(s), there are many advantages to providing a radio communication system onboard the maritime vessel 400. Such a co munication system allows for a vast array of the communication devices 410 to communicate amongst one another and with land-based systems via the external networks in communication with the maritime vessel 400 For example, in the shipping industry it is advantageous to equip containers with the communication devices 410. This allows inventory systems to maintain an accurate inventory of the containers that are onboard the maritime vessel 400 via communication with the communication devices 410 using, for instance, short message system (“SMS”) messages. Furthermore, some containers require climate control to maintain temperature and humidity therein to protect the climate- sensitive contents within the container. A climate control system associated with the container may include a sensor as part of the communication devices 410 to communicate with inventory systems or diagnostic systems to report climate status or to adjust climate settings via radio communication. In another application, the communication devices 410 may act as a sensor (e.g., engine sensor) to measure parameters associated with the maritime vessel 400 and communicate the information to an onboard vessel control system (e.g., a computer system) and/or a remote control center via the access network(s) and the externa) networks. Furthermore, the communication system is able to receive configuration settings and software updates for the subsystems and modules onboard the maritime vessel 400 to maintain efficient communications with the communication devices 410.

The communication manager 440 selects the transport routes or channels via the transceiver 460 to the external networks for data transmission for the communication devices 410. The transceiver 460 may implement a satellite backhaul technology to communicate with a corresponding satellite external network and/or a cellular backhaul technology to communicate with a corresponding cellular external network.

The base station 420 can implement many different communication protocols to create a local area network with the communication devices 410. The communication protocols include, without limitation, a global system for mobile communications (“GSM”) protocol, a code division multiple access 2000 (“CDMA2000”) protocol, a general packet radio service (“GPRS”) protocol, and/or an enhanced data rate for global system (“EDGE”) protocol. The access point 430 can implement many different communication protocols (e.g. , an IEEE 802.11 wireless local area network standard) to create a local area network with the communication devices 410. Of course, other communication protocols and standards such as personal area networks (i.e., IEEE 802.15) and wireless wide area networks (i.e., IEEE 802.16 for WiMAX) may also be employed to advantage. The interoperability unit 450 supports and converts between multiple communication protocols and standards to permit communication for the communication devices 410 to the external networks and/or another maritime vessel.

Turning now to FIGURE 5, illustrated is a block diagram of an embodiment of a computer system 500 operable with the systems, subsystems and modules described herein. For example, the computer system 500, or portions thereof, can be employed with a communication manager, a network operations center, communication devices (e.g., user equipment (‘TIE”) and Internet of Tilings (“IoT”) devices), etc. Those skilled in the art should recognize that the computer system 500 may have more or less components including many instances of the subsystems or modules set forth below.

The computer system 500 includes a bus 540, which is coupled to a processor (or processing circuitry) 515, a power supply 520, memory that can be implemented as volatile memory 525 (e.g., double data rate random access memory (“DDR-RAM”), single data rate (“SDR”) RAM), and nonvolatile memory 530 (e.g., a hard drive, flash memory, or a phase-change memory (“PCM”). The processor 515 may be coupled to a cache 510. The processor 515 may retrieve instruction(s) from the volatile memory 525 and/or the nonvolatile memory 530, and execute the instruction(s) to perform operations described herein. The bus 540 couple the above elements together and further couple a sensor 550, a display controller and display device 555, one or more input/output devices 560 (e.g., a network interface card, a cursor control such as a mouse, trackball, touchscreen, touchpad, and a keyboard), and a wireless transceiver 565 (e.g., Bluetooth, Wi-Fi, infrared, cellular, satellite, etc.).

The techniques shown in the FIGURES illustrated herein can be implemented using code and data stored and executed on one or more electronic devices. Such electronic devices store and commun icate (internally and/or with other electronic devices over a network) code and data using non-transitory tangible machine readable medium (e.g., magnetic disks; optical disks; read only memory; flash memory devices; phase- change memory) and transitory machine-readable communication medium (e.g., electrical, optical, acoustical or other forms of propagated signals such as carrier waves, infrared signals, digital signals, etc.). In addition, such electronic devices typically include a set or one or more processors 515 coupled with one or more other components, such as a storage device (e.g., the nonvolatile memory 530), one or more input/output devices 560, and a network connection. The coupling of the set of processors 515 and other components is typically through one or more busses or bridges (also termed bus controllers) 540. The storage device and signals carrying the network traffic respectively represent one or more non-transitory tangible machine readable medium and transitory machi ne-readable communication medium. Thus, the storage device of a given electronic device typically stores code and/or data for execution on the set of one or more processors 515 of the electronic device. Of course, one or more parts of the systems, subsystems and modules may be implemented using different combination of software, firmware, and/or hardware. For example, the techniques shown in the FIGURES have been described with reference to a specific entity performing the techniques. One of skill in the art would recognize that in other embodiments other or different entities may perform the same techniques. Furthermore, separate entities may be combined as one entity in other embodiments without changing the fundamental teachings of the techniques.

The processors 515, which may be implemented with one or a plurality of processing devices, performs functions associated with its operation including, without limitation, precoding of antenna gain/phase parameters, encoding and decoding of individual bits forming a communication message, formatting of information and overall control of a respective communication device. Exemplary functions related to management of communication resources include, without limitation, hardware installation, traffic management, performance data analysis, configuration management, security, billing and the like. The processors 515 may be of any type suitable to the local application environment, and may include one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (“DSPs”), field- programmable gate arrays (“FPGAs”), application-specific integrated circuits (“ASICs”), and processors based on a multi-core processor architecture, as non-limiting examples.

The memories (e.g., the volatile memory 525 and the nonvolatile memory 530) may be one or more memories and of any type suitable to the local application environment, and may be implemented using any suitable volatile or nonvolatile data storage technology such as a semiconductor-based memory device, a magnetic memory device and system, an optical memory device and system, fixed memory and removable memory. The programs stored in the memories may include program instructions or computer program code that, when executed by an associated processor, enable the respective communication device to perform its intended tasks. Of course, the memories may form a data buffer for data transmitted to and from the same. Exemplary

embodiments of the system, subsystems, and modules as described herein may be implemented, at least in part, by computer software executable by processors, or by- hardware, or by combinations thereof

The transceivers 565 modulate information onto a carrier waveform for transmission by the respective communication device via the respective antenna(s) to another communication device. The respective transceiver 565 demodulates information received via the antenna(s) for further processing by other communication devices. The transceiver 565 is capable of supporting duplex operation for the respective

communication device. The network interface performs similar functions as the transceiver communicating with a core network.

As introduced herein, a connectivity layer for the wireless communication devices such as the loT devices is addressed and machine learning and other analytic techniques are applied to create geospatial“maps” that describe communications capabilities for the loT devices. These maps are used to monitor and predict both the behavior of the loT de vices as well as the heterogeneous networks serving them.

The main techniques to monitor communication health are some form of monitoring or polling. For instance, the communication device can be“pinged” at intervals with its response indicating that the device can still communicate. A more passive approach is to monitor whether a communication is received from a

communication device over a prescribed period of time. A problem with this approach is that it does not anticipate failure modes, but only detects them. Once a failure occurs, it can be very difficult to facilitate repair because the communication device may be hard to find and harder to communicate with.

In general, at the core of the business problem is to automate detection, categorization, and preventive intervention of connectivity anomalies in communication devices, IoT devices or otherwise. Machine learning and statistically driven monitoring and optimization, coupled with reports from a population of the IoT devices, offers solutions that can transform these functions. The solution can be conceived as having two main parts. A first part is the use of a population of loT devices to act as“sniffers,” reporting communications capabilities in a way so they can he correlated with other observations, both temporally and geospatially. Therefore, the ϊoT device can report a location, a timestamp, and some form of connection quality indicator, such as radio signal strength. The IoT device can also report values such as a connection type (e.g. 4G or 5G), a network code, etc. The data can then be used to build a geospatial model that describes connection capabilities.

A second part of the solution is the application of machine learning and predictive analytic techniques to the geospatial model to predict connectivity gaps, changes in connectivity capabilities across time and position, and predict potential failure modes of both devices and network elements. These solutions are generally applicable for general loT communications, although container shipping is used herein as an example.

in its simplest form, based on data reported by IoT devices, a statistical radio

“fingerprint” is created for each known position. Parameters are assigned to each position so that if an IoT device crosses that position and reports radio strength outside of those values, an appropriate action can be taken, such as raising an alarm or marking that the IoT device as needing closer inspection when it is close to an inspection facility.

In the specific case of container shipping, a model for a maritime vessel will be such that the influence of the arrangement of containers is known so that radio coverage can be predicted based on the way the containers are loaded. Besides predicting how the radio coverage across the maritime vessel would change, this modeling allows the shipper to use this model as an input into a loading algorithm to enhance

communications therewith, for instance, a best communication across all containers, or prioritizing communications for certain containers.

The general solution can allow radio failures to be anticipated by incorporating existing logistical concepts, such as loading and unloading docks, into a radio measuring system. Such a system can also be used to monitor the host radio system itself, thereby anticipating potential failures both in the IoT device population as well as in the host system. More generally, the solution will allow the prediction of

communication capabilities anywhere in the anticipated path of an IoT device. This information can be used for such purposes as allowing the IoT application to tailor its workload, allowing business operations to evaluate the cost-effectiveness of

connectivity contracts, or giving end-users insights into when cargo or package information might be unavailable.

The specific solution can allow the use of radio coverage modeling to be integrated into the load-planning parts of the shipping operations systems, thereby enhancing the commercial value of the container monitoring solution. Examples of the solution described herein relate to maritime vessels, although the principle can be applied to any cases where radio-enabled IoT devices regularly pass known positions. For instance, the same principles would apply to delivery trucks delivering monitored goods.

Using a refrigerated container as an example, each container includes a wireless communication device such as an IoT device. The communication device can operate using many different kinds of radio technologies from 3GPP-based technologies (such as wideband code division multiple access (“WCDMA”), LTE) to WiFi to Zigbee, etc. In general, an IoT device includes at least one radio interface and an ability to report location and some aspect of connection quality.

To further exemplify this case, when a container is at sea, its location is determined first by its location on earth (e.g., its latitude and longitude) and then by a combination of the maritime vessel tier, bay and row. The tiers correspond roughly to level and generally start, in the bottom of the hold, with tier 2, and count upwards by 2. The first tier above the deck typically starts with 82 and counts upwards by 2. The bays tire horizontal cross sections and numbered from the front of the ship to the stern of the ship. The numbering scheme takes into account the fact that containers may be twenty or forty feet long. The rows run lengthwise along a ship and are numbered from side to side.

It can therefore be seen that any possible container position on a maritime vessel can be identified by its stowage position. A stowage position of“020882” would mean a stowage position in bay 02, which would typically be at the front of the maritime vessel, in row 8 and in tier 82, which would be the first level of containers above the deck of the vessel. Each maritime vessel has at least a base station and antenna installed. The antenna position may vary across the maritime vessels, but is typically stationary on the vessel. The radiated power of the base station and antenna are also relatively constant when the system is turned on. Each container has a communication device that receives the radio signal. Part of the communication protocol is for the com munication device to report its received signal strength back to the communication system. In GSM systems, this is sometime referred to as a receive signal strength indication (“RSSi”).

Over time, as different containers report RSSI values from these stowage positions, it will be possible to build a statistical model of the radio coverage at that position. For instance, if one container reports an RSSI value more than 10 decibels (“dB”) below the mean, it could indicate a problem with the container. If multiple containers report low RSSI values for the same stowage position, however, then it is possible that the output power of the host communication system is dropping due to antenna misalignment, an obstruction, or other reasons.

It is advantageous to consider in this specific case, which applies to the more general case as well, that radio characteristics at a particular stowage position can be dependent on the broader geospatial context. To put this more concretely, if a maritime vessel is within 12 nautical miles off shore, the on-board communication system will turn off and coverage will be provided by shore-based communication systems. Radio characteristics, particularly below deck, will be very different compared to the case when the on-board communication system is transmitting.

In general, it can be seen that application of machine learning techniques can support a solution that continually refines predictions about the performance of communication systems at specific locations. The prediction can take the for of predicting a continuous performance measure or classifying performance into '‘buckets.” Using standard machine learning techniques, a cross-validated solution would, for instance, train itself on 80 percent (“%”) of the data received and then validate its predictions on the 20% that was not used for training. Statistical techniques used for the machine learning may include any of a large number of techniques used to either classify or predict the value of a dependent measurement. These include regression models, neural networks, deep learning for continuous predictions or upport vector machines, logistic regression for classification. Clustering techniques, such as nearest neighbor or mean shift can be used to group positions according to various performance measures. If the communication system is changed, the system can be designed to relearn the predictions and detectors and thus would be self-adapting.

As can be seen, applications of machine learning and artificial intelligence (“AI”) techniques can create a performance monitoring and management system that can“self-monitor” and adapt to changing conditions. Such self-learning and self- correcting solutions are particularly appealing as the networks of loT devices, particularly networks of mobile IoT devices, scale to very large networks as will inevitably take place.

However, it is not just enough to detect anomalies, as these algorithms keep looking for deviant patterns and, as such, there may be an overload of alarms. Since the resources to tend to such alarms are always scarce, there needs to be a mechanism to prioritize the impact, flag, and categorize items into multiple urgency bins such as red, amber and yellow bins. A statistical monitoring tool that takes a temporal view of detected anomalies at a communication device or cluster level helps track and prioritize actions.

In summary, focusing on the behavior and inter-arrival time messages from a communication device along with temporal characteristics of status and intensity of the connectivity can offer beneficial knowledge and expertise in detecting‘sick ' co munication devices and keeping up the communication system function. This detection should be continuous, probabilistic and pattern oriented. Machine learning techniques are advantageous for such intensive and stochastic business problems.

These techniques can support a solution that offers continually refined predictions about the performance of communication devices at specific locations. The solution can be built by taking advantage of historical multi-source data by combining various data sources like voyages, load lists, signal strength indicators, messaging logs, etc., to identify and detect patterns. The training can be performed on 80% of the data received and then test its predictions on the 20% that was not used for training. This standard machine learning (“ML”) technique ensure that the patterns are“realistic” and will stand the test of deployment. The hypothesis set for the techniques can be wide including regression, classification, anomaly detection, and more. The complex nature of structured and unstructured sources and fuzzy nature of joins in spatial and temporal data are conducive for deep layered pattern detection architectures such as a deep neural nets.

Turning now to FIGURE 6 illustrated is a graphical representation of received signal strengths onboard a maritime vessel. The stowage positions are shown as a three-dimensional grid of tier (e.g., the vertical location on the vessel) with tier 2 being at the bottom of the cargo hold and tier 82 being the first level above the deck. The bay describes a slice across the maritime vessel, numbered from the front of the vessel to the rear of the vessel. The odd numbers represent twenty-foot positions and even numbers represent forty-foot positions. The rows run lengthwise on the maritime vessel with odd numbers on the starboard, or right side of the vessel, and even numbers on the port, or left side of the vessel. The row numbers are actually all positive numbers, the minus signs in the diagra designate the port side of the maritime vessel.

FIGURE 6 show's signal strengths in tiers with“+” symbols representing the lower signal strengths and the circles representing higher signal strengths. The circles show stowage positions with valid measurements, whereas crosses show locations of invalid measurements. From the signal strengths, it can be understood how a set of measurements can be associated with each stowage position including, without limitation, mean value, minimum measure value, maximum value, standard deviation, median, historical trend, etc. Again, while stowage positions on maritime vessels is used as an example, it should be understood that the same principle applies anywhere that communication devices regularly pass a communication system at fairly precisely known points. This could be, for instance, at loading docks, the doors of delivery trucks, etc.

Turning now to FIGURE 7, illustrated is a block diagram of a collection of objects {e.g., containers) onboard a maritime vessel stacked in a physical grid 705 including rows, bays and tiers. Each container, such as container 710 at a location 715 in the physical grid 705, is individually equipped with a wireless communication device (also referred to as a“communication device” such as an ioT device). The heavy line just below the middle tier represents the deck level of the maritime vessel such that everything below the heavy line is below deck and everything above the heavy line is above deck. Generalizing the container layout on the maritime vessel, it can be seen that it can be modeled as a three-dimension object, where the x-axis identifies the bay (also referred to as a“base” ), the y-axis identifies the row and the z-axis identifies the tier. FIGURE 8 illustrates a tabular representation of a number of containers in rows, bays and tiers.

The containers may be stacked in row's from bow to stem, in bays from port side to starboard side, and in tiers from a lower level to a higher level. The arrangement of the containers could affect the propagation of radio waves. A container sitting above other containers could have a good radio signal until new containers are added, at which time it could become blocked. A container that is blocked on its left (e.g., port) side may still have a good communication situation if the maritime vessel is sailing northward to the west of a coastline.

As the containers under discussion have communication devices and regularly report received signal strength, it becomes possible to“learn” per maritime vessel and route combination, what the effects of various load arrangements are. Using this knowledge as one of the inputs into load planning, it becomes possible to augment communication. The radio coverage information from these containers is therefore collected, including a history of received signal strength, stowage position, and route information, and a predictive model of coverage on the maritime vessel can be built under various load arrangements.

Attributes associated with the coordinates of this object are assigned, which may itself be in a broader geospatial context (e.g., within 12 nautical miles, as described previously). Those attributes reflect the radio measurements relevant at those coordinates. The radio attributes include, without limitation, the mean signal strength, the median signal strength, the maximum and minimum signal strengths, and potentially other values such as the number of observations, etc.

Turning now' to FIGURE 9, illustrated is a block diagram of an embodiment of a co munication system 900, or portions thereof, employable with a collection of objects (e.g., containers) onboard a maritime vessel stacked in a physical grid 905 including row's, bays (also referred to as a“base”) and tiers. The containers (one of which is designated 910) at a location 915 in the physical grid 905 are equipped with a communication device (one of which is designated 920, e.g., an IoT device) in communication with a radio device manager (“RDM”) 930, which is in coupled to database (“DB”, a type of memory) 940. Attributes associated with each container include, without limitation, minimum, maximum and median values of RSSIs. These attributes are mapped onto positions and are transmitted wirelessly to and stored in the database 940 via the radio device manager 930. Again, the heavy line just below the middle tier represents the deck level of the maritime vessel.

The radio device manager 930 receives wireless signals from the communication device 920 associated with the container 910, and stores information about the container 910 in a database 940. The information stored in the database 940 is employed to monitor communication performance for the container 910 are stowed in locations onboard the maritime vessel. When the radio device manager 930 receives a signal strength result and stowage position from the communication device 920, it both updates and checks the database 940. In case the received value is outside the predicted range based on the stored values, the radio device manager 930 can raise an alarm, for instance, through a maintenance console (“MC”) 935. Using the same collected data, it becomes possible to build a system such that an analysis of stowage and historical radio coverage information will yield a prediction of radio coverage (not shown). The radio device manager 930 communicates with the maintenance console 935 to provide a user interface that presents operational and communication status to an onboard or remotely located technician.

The radio device manager 930, maintenance console 935 and database 940 may be onboard the maritime vessel (e.g., associated with or part of the communications manager 440 of FIGURE 4). Alternatively, the radio device manager 930, maintenance console 935 and database 940 may be external to the maritime vessel as part of a remote control center and in comm unication with, for instance, communication devices (see, e.g., communication devices 410 of FIGURE 4) via a base station (see, e.g. , the base station 420 of FIGURE 4).

Turning now to FIGURE 10, illustrated is a flow diagram of an embodiment of a method 1000 of operating a communication system. With continuing reference to the preceding FIGURES, the method is operable on an apparatus such as the radio device manager (930) illustrated and described with respect to FIGURE 9. The method 1000 begins at a start step or module 1005. At a step or module 1010, the apparatus builds a statistical model from a plurality of wireless communication devices (920, e.g., loT devices) including identifying a location (905) in a physical grid (905) and an expected ping response signature. The location (905) may include a base, a tier, and a row of an object (such as a container (910) onboard a vessel (110)) including a wireless communication device (920).

The statistical model may be constructed using machine learning and predictive analytic techniques, and may be dependent on the base, the tier, and the row of the object (910). The statistical model can predict a failure mode of a wireless communication device (920). The statistical model can predict a future value of a ping response signature from wireless communication device (920). The statistical model can prioritize an impact, flag and categorize deviations of a predicted future value into an urgency bin. The statistical model can describe communication characteristics of a wireless communication device (920). The communication characteristics include, without limitation, a bit-error rate, an expected signal amplitude, a data rate and a

communication technology.

At a step or module 1020, the apparatus pings a wireless communication device (920) positioned at a location (905) in a physical grid (905), and receives a ping response from the wireless communication device (920) at a step or module 1030. At a step or module 1040, the apparatus compares a ping response signature to an expected ping response signature for the location (910) to ascertain if the ping response is consistent with the statistical model associated with the expected ping response signature. At a step or module 1050, the apparatus associates a timestamp with the location (905) and the ping response signature, and stores the timestamp, the location (905) and the ping response signature in memory (530, 940) at a step or module 1060. The memory'· (530, 940) may be remotely located from the wireless communication device (920).

At a step or module 1070, the apparatus assesses a quality of radio coverage of the wireless communication device (920) in accordance with the statistical model. The apparatus reports an error condition if the ping response signature is inconsistent with the expected ping response signature at a step or module 1080. The error condition may include a received signal strength indication of the wireless communication device (920) being beyond a range of values within the statistical model. Of course, the statistical model may be employed for a plurality of wireless communication devices (920). The method 1000 ends at a step or module 1090.

A population of communication devices (e.g., loT devices) reports

communication capabilities using a coordinate system. One or more geospatialiy- enabled databases maintain sets of communications capabilities along with relevant predictive models and other parameters needed to create new predictions. Known coordinates at various locations are monitored so that these radio quality profiles are created. As the communication devices pass by those coordinates, radio measurements from those communication devices are compared to the profile. By applying predictive analytic techniques, multiple measurements across the points can be used to determine whether the communication devices are starting to perform in a non-compliant way, or whether the radio system at that location is starting to perform in a non-compliant way. Other predictions are also possible, such as whether there will be communication dropouts along the predicted path, changes in characteristics (bandwidth, latency), etc.

Although the embodiments and its advantages have been described in detail, it should be understood that various changes, substitutions, and alterations can be made herein without departing from the spirit and scope thereof as defined by the appended claims. For example, many of the features and functions discussed above can be implemented in software, hardware, or firmware, or a combination thereof. Also, many of the features, functions, and steps of operating the same may be reordered, omitted, added, etc., and still fall within the broad scope of the various embodiments.

Moreover, the scope of the various embodiments is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification. As one of ordinary skill in the art will readily appreciate from the disclosure, processes, machines, manufacture, compositions of matter, means, methods, or steps, presently existing or later to be developed, that perform substantially the same function or achieve substantially the same result as the corresponding embodiments described herein may be utilized as well.

Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or steps.