Methods of life cycle management for artificial intelligence (AI)-based channel state information (CSI) prediction

Abstract

The present application relates to an improved method of operating a user equipment (UE), comprising: transmitting a first capability indication to a base station, wherein the first capability indication relates to capabilities of one or more artificial intelligence (AI) or machine learning (ML)-based models for performing one or more Channel State Information (CSI)-related tasks; receiving a first network configuration (e.g., a model ID) to activate a use of at least one of the one or more models; selecting a first model of the one or more models to use to perform a CSI-related task; transmitting at least one CSI report determined based on an output of the first model; and then monitoring, over time, at least one performance metric for the first model. The UE may further transmit to the base station a request to activate or deactivate the use of at least one of the one or more models.

Description

TITLE: METHODS OF LIFE CYCLE MANAGEMENT FOR ARTIFICIALINTELLIGENCE (AI)-BASED CHANNEL STATE INFORMATION (CSI)PREDICTIONTECHNICAL FIELD

[0001] The present application relates to wireless devices and wireless networks, including user devices, terminals, circuits, computer-readable media, and methods for performing life cycle management (LCM) for Artificial Intelligence (Al) and / or Machine Learning (ML)- based Channel State Information (CSI) prediction models.BACKGROUND

[0002] Wireless communication systems are rapidly growing in usage. In recent years, wireless devices such as smart phones and tablet computers have become increasingly sophisticated. In addition to supporting telephone calls, many mobile devices now provide access to the Internet, email, text messaging, and navigation using the global positioning system (GPS) and are capable of operating sophisticated applications that utilize these functionalities. Additionally, there exist numerous different wireless communication technologies and standards. Some examples of wireless communication standards include GSM, UMTS (associated with, for example, WCDMA or TD-SCDMA air interfaces), Long- Term Evolution (LTE), LTE Advanced (LTE-A), HSPA, 3GPP2 CDMA2000 (e.g., IxRTT, IxEV-DO, HRPD, eHRPD), IEEE 802.11 (WLAN or Wi-Fi), and BLUETOOTH™, among others.

[0003] The ever-increasing number of features and functionality introduced in wireless communication devices also creates a continuous need for improvement in both wireless communications and in wireless communication devices. To increase coverage and betterserve the increasing demand and range of envisioned uses of wireless communication, in addition to the communication standards mentioned above, there are further wireless communication technologies under development, including the fifth generation (5G) standard and New Radio (NR) communication technologies and beyond. Accordingly, improvements in the field in support of such development and design are desired.

[0004] In Third Generation Partnership Project (3 GPP) standards development, channel state information (CSI) feedback has been an essential topic in almost every 3 GPP standards release. Further, nearly all CSI codebook design has been focused on feedback based on a current CSI reference signal (CSI-RS) measurement, e.g., as illustrated in Figure 5 by diagram 530. In the case of such traditional CSI feedback (e.g., through 3GPP Release 17), a base station (e.g., also referred to herein as a “gNB” or “gNodeB”) periodically transmits a CSI-RS to a UE, and the UE periodically provides CSI feedback (CSI-FB). The base station then applies the CSI feedback to generate precoding matrix index (PMI) until a next CSI feedback is available.

[0005] Further, the base station may use an older CSI feedback function that assumes that a channel’s strength does not change substantially over time (e.g., over the span of a few milliseconds). Such a scheme often works well for low UE mobility cases. However, one possible 3GPP Release 18 enhancement is illustrated in Figure 5 by diagram 550. In such cases, the base station may transmit a cluster for CSI-RSs, and the UE may transmit CSI feedback to the base station based on at least one CSI-RS of the cluster of CSI-RSs. The base station then applies the CSI feedback to generate PMI for a duration of time, e.g., until a next CSI feedback measurement is available. In both instances, however, frequent CSI feedback is required form the UE, and both schemes 530 and 550 are still best suited for low mobility UEs.

[0006] Thus, improvements have been proposed to provide techniques for Al-based (and / or Machine Learning (ML)-based) CSI feedback with CSI prediction, including mechanisms for a UE to indicate a predicted CSI report, network configuration of CSI feedback, UE PMI report format, and / or perform rudimentary Al-based model life cycle management (LCM). For example, by leveraging an Al-based CSI feedback model, a UE may predict a channel at one or more times in the future. The valid time frame (e.g., a duration of time and / or predicted time) for the CSI prediction may be determined by the UE and / or configured by a network (e.g., a base station). However, there are opportunities for the LCM of Al-based CSI prediction models to be improved, such as by providing UEs with the ability to transmit more rich UE capability reports to the base station, as well as the ability to autonomously (and / or automatically): select, monitor the performance of, and / or switch between Al-based CSI prediction models while the UE is in operation (e.g., in some cases, the model selection, monitoring, and / or switching may also be based on one or more network configurations). Thus, improvements are desired.SUMMARY

[0007] In accordance with one or more embodiments, a method of operating a user equipment (UE) is disclosed herein, the method comprising: transmitting, from the UE, a first capability indication to a base station, wherein the first capability indication relates to capabilities of one or more models for performing at least one Channel State Information (CSI)- related task based on artificial intelligence (Al) or machine learning (ML); receiving, at the UE, a first network configuration to activate a use of at least one of the one or more models; selecting, at the UE and based, at least in part, on the first network configuration, a first model of the one or more models to use to perform a CSLrelated task; transmitting, from the UE tothe base station, at least one CSI report determined based, at least in part, on an output of the first model; and monitoring, by the UE, at least one performance metric for the first model. According to some aspects, the method may further comprise: transmitting, by the UE to the base station, a request to activate or deactivate use of at least one of the one or more models.

[0008] According to other aspects, the first capability indication may comprise at least one of: an indication that the UE supports channel -based CSI prediction; an indication that the UE supports precoding matrix indicator (PMI)-based CSI prediction; an indication that the UE supports a maximum CSI prediction time window; an indication of a CSI prediction granularity level; or an indication of a CSI measurement window.

[0009] According to still other aspects, the act of monitoring, by the UE, the at least one performance metric for the first model may further comprise: comparing, by the UE, a first predicted CSI measurement determined based, at least in part, on an output of the first model against a second CSI measurement made subsequently to the first predicted CSI measurement. According to still other aspects, the act of monitoring, by the UE, the at least one performance metric for the first model may further comprise: comparing, by the UE, the at least one performance metric for the first model against a threshold value configured by the base station.

[0010] According to still other aspects, the method may further comprise: determining, by the UE and based, at least in part, on the act of comparing, that a performance metric for the first model has degraded below a threshold value. According to still other aspects, the method may further comprise determining, by the UE and based, at least in part, on the act of comparing, a CSI prediction metric; and then transmitting the determined CSI prediction metric by the UE to the base station.

[0011] According to still other aspects, the method may further comprise: selecting, at theUE and based on the monitoring, a second model of the one or more models to perform the CSI-related task; and then transmitting, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the second model. According to some aspects, the UE may also transmit to the base station an indication that the second model was the model that was used to produce the at least one CSI report.

[0012] According to still other aspects, the method may further comprise: selecting, at the UE, the first model is based, at least in part on one or more of: a position of the UE, a speed of the UE, or a training condition associated with the first model.

[0013] According to still other aspects, the method may further comprise: transmitting, from the UE to the base station, an ACK / NACK indication in response to a downlink (DL) transmission, wherein the ACK / NACK indication is indicative, at least in part, of a performance metric for the first model (e.g., the more NACKs that are received by the base station over a particular time window, the higher the likelihood is that a model has failed; although, of course, there could also be other causes for the high proportion of NACKs being received).

[0014] According to some aspects, the first network configuration may specify one or more of the following: a time offset value for predicted CSI measurements; a position value for predicted CSI measurements; an indication that the UE shall perform channel-based CSI prediction; an indication that the UE shall perform PMI-based CSI prediction; an indication of a periodic CSI reference signal (p-CSI-RS) configuration; an indication of a semi-persistent CSI reference signal (sp-CSI-RS) configuration; or an indication of an aperiodic CSI reference signal (ap-CSI-RS) configuration.

[0015] According to still other aspects, the method may further comprise, in response todetermining, by the UE, that a performance metric for each of the one or more models has degraded below a threshold value: transmitting, by the UE to the base station, a request to deactivate use of each of the one or more models.

[0016] According to one or more further embodiments, another method of operating a UE is disclosed herein, the method comprising: transmitting, from the UE, a first capability indication to a base station, wherein the first capability indication comprises one or more sets of model IDs and the capabilities corresponding to those model IDs, and wherein each model ID relates to a model for performing at least one Channel State Information (CSI)-related task based on artificial intelligence (Al) or machine learning (ML); receiving, at the UE, a first network configuration comprising at least one model ID; selecting, at the UE and based, at least in part, on the first network configuration, a first model corresponding to a first model ID of the at least one model ID to use to perform a CSLrelated task; transmitting, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the first model; and monitoring, by the UE, at least one performance metric for the first model. According to some aspects, the method may further comprise: transmitting the first model ID that is associated with the first model to the base station along with the at least one CSI report

[0017] According to some aspects, the first network configuration comprising at least one of the one or more model IDs is received via one of: Radio Resource Control (RRC) signaling; or Medium Access Control (MAC) Control Element (CE) signaling. According to other aspects, selecting the first model corresponding to the first model ID further comprises: receiving, at the UE from the base station, an activation command indicating the first model ID via one of: RRC signaling or MAC CE signaling.

[0018] According to still other aspects, monitoring, by the UE, at least one performancemetric for the first model further comprises: periodically transmitting, from the UE to the base station, the first model ID and one or more additional CSI reports determined based, at least in part, on outputs of the first model. According to other such aspects, the UE may also transmit to the base station, in response to determining that a performance metric for the first model has degraded below a threshold value, the first model ID and an additional CSI report determined based, at least in part, on an output of the first model.

[0019] The various methods and techniques summarized in this section may likewise be performed by a UE device comprising: a receiver; a transmitter; and a processor configured to perform any of the various methods and techniques summarized herein. The various methods and techniques summarized in this section may likewise be stored as instructions in a nonvolatile computer-readable medium, wherein the instructions, when executed, cause the performance of the various methods and techniques summarized herein.

[0020] This Summary is intended to provide a brief overview of some of the subject matter described in this document. Accordingly, it will be appreciated that the above-described features are merely examples and should not be construed to narrow the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become apparent from the following Detailed Description, Figures, and Claims.BRIEF DESCRIPTION OF DRAWINGS

[0021] A better understanding of the present subject matter may be obtained when the following detailed description of various aspects is considered in conjunction with the following drawings:

[0022] Figure 1 illustrates an example wireless communication system, according to someaspects.

[0023] Figure 2 illustrates another example of a wireless communication system, according to some aspects.

[0024] Figure 3 illustrates an example block diagram of a UE, according to some aspects.

[0025] Figure 4 illustrates an example block diagram of a Base Station (BS), according to some aspects.

[0026] Figure 5 illustrates various diagrams detailing methods of performing Channel State Information (CSI) feedback, according to some aspects.

[0027] Figure 6 illustrates a flow diagram detailing a method of performing improved life cycle management (LCM) for Al-based CSI prediction models, according to some aspects.

[0028] Figure 7 illustrates a flow diagram detailing another method of performing improved life cycle management (LCM) for Al-based CSI prediction models, according to some aspects.

[0029] Figure 8 is a flowchart detailing a method of performing function-based LCM for Al-based CSI prediction models, according to some aspects.

[0030] Figure 9 is a flowchart detailing a method of performing model identifier (ID)-based LCM for Al-based CSI prediction models, according to some aspects.

[0031] While the features described herein may be susceptible to various modifications and alternative forms, specific aspects thereof are shown by way of example in the drawings and are herein described in detail. It should be understood, however, that the drawings and detailed description thereto are not intended to be limiting to the particular form disclosed, but on the contrary, the intention is to cover all modifications, equivalents and alternatives falling withinthe spirit and scope of the subject matter as defined by the appended claims.DETAILED DESCRIPTION

[0032] The present application relates to improved methods for performing Life Cycle Management (LCM) for Artificial Intelligence (Al) and / or Machine Learning (ML)-based Channel State Information (CSI) prediction models running on User Equipment (UEs). In particular, disclosed herein are methods for function-based model life cycle management (e.g., by enhancing traditional methods of signaling based on particular functions performed by the models), as well as methods for model ID-based signaling for life cycle management (e.g., including the development of a unified Al-specific signaling framework).

[0033] So-called function-based embodiments disclosed herein may provide for: (1) additional UE capabilities related to model functionality (e.g., support of channel-based and / or pre-coding matrix indicator (PMI)-based CSI prediction, increased max prediction windows, and improved prediction granularity); (2) the activation and deactivation of the CSI prediction function by the network (e.g., with the UE autonomously switching between multiple CSI prediction models and / or the UE sending requests to the network for activation / deactivation of models); and (3) improved model performance monitoring (e.g., autonomous UE model performance monitoring and / or UE model monitoring according to network-configured performance metrics and thresholds).

[0034] So-called model ID-based embodiments disclosed herein may provide for: (1) the UE reporting back Al-based model IDs and / or model descriptions that have been used for CSI prediction to the network; (2) the network activation of Al-based models at the UE through the base station signaling particular model ID(s) to the UE; and (3) the UE performing inference time predictions using the specified Al-based model ID and reporting its feedback to thenetwork.

[0035] The following is a glossary of additional terms that may be used in this disclosure:

[0036] Memory Medium - Any of various types of non-transitory memory devices or storage devices. The term “memory medium” is intended to include an installation medium, (e.g., a CD-ROM, floppy disks, or tape device; a computer system memory or random-access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM), a non-volatile memory such as a Flash, magnetic media (e.g., a hard drive, or optical storage; registers, or other similar types of memory elements). The memory medium may include other types of non-transitory memory as well or combinations thereof. In addition, the memory medium may be located in a first computer system in which the programs are executed or may be located in a second different computer system which connects to the first computer system over a network, such as the Internet. In the latter instance, the second computer system may provide program instructions to the first computer for execution. The term “memory medium” may include two or more memory mediums which may reside in different locations (e.g. , in different computer systems that are connected over a network). The memory medium may store program instructions (e.g., embodied as computer programs) that may be executed by one or more processors.

[0037] Carrier Medium - a memory medium as described above, as well as a physical transmission medium, such as a bus, network, and / or other physical transmission medium that conveys signals such as electrical, electromagnetic, or digital signals.

[0038] Programmable Hardware Element - includes various hardware devices comprising multiple programmable function blocks connected via a programmable interconnect. Examples include FPGAs (Field Programmable Gate Arrays), PLDs(Programmable Logic Devices), FPOAs (Field Programmable Object Arrays), and CPLDs (Complex PLDs). The programmable function blocks may range from fine grained (combinatorial logic or look up tables) to coarse grained (arithmetic logic units or processor cores). A programmable hardware element may also be referred to as “reconfigurable logic.”

[0039] User Equipment (UE) (also “User Device,” “UE Device,” or “Terminal”) - any of various types of computer systems or devices that are mobile or portable and that perform wireless communications. Examples of UE devices include mobile telephones or smart phones (e.g., iPhone™, Android™-based phones), portable gaming devices (e.g., Nintendo Switch™, Nintendo DS™, PlayStation Vita™, PlayStation Portable™, Gameboy Advance™, iPhone™), laptops, wearable devices (e.g., smart watch, smart glasses), PDAs, portable Internet devices, music players, data storage devices, other handheld devices, in-vehicle infotainment (IVI), in- car entertainment (ICE) devices, an instrument cluster, head-up display (HUD) devices, onboard diagnostic (OBD) devices, dashtop mobile equipment (DME), mobile data terminals (MDTs), Electronic Engine Management System (EEMS), electronic / engine control units (ECUs), electronic / engine control modules (ECMs), embedded systems, microcontrollers, control modules, engine management systems (EMS), networked or “smart” appliances, machine type communications (MTC) devices, machine-to-machine (M2M), internet of things (loT) devices, and the like. In general, the terms “UE” or “UE device” or “terminal” or “user device” may be broadly defined to encompass any electronic, computing, and / or telecommunications device (or combination of devices) that is easily transported by a user (or vehicle) and capable of wireless communication.

[0040] Wireless Device - any of various types of computer systems or devices that perform wireless communications. A wireless device may be portable (or mobile) or may be stationaryor fixed at a certain location. A UE is an example of a wireless device.

[0041] Communication Device - any of various types of computer systems or devices that perform communications, where the communications may be wired or wireless. A communication device may be portable (or mobile) or may be stationary or fixed at a certain location. A wireless device is an example of a communication device. A UE is another example of a communication device.

[0042] Base Station - The terms “base station,” “wireless base station,” or “wireless station” have the full breadth of their ordinary meaning, and at least includes a wireless communication station installed at a fixed location and used to communicate as part of a wireless telephone system or radio system. For example, if the base station is implemented in the context of LTE, it may alternately be referred to as an ‘eNodeB’ or ‘eNB’. If the base station is implemented in the context of 5GNR, it may alternately be referred to as a ‘gNodeB’ or ‘gNB’. Although certain aspects are described in the context of LTE or 5G NR, references to “eNB,” “gNB,” “nodeB,” “base station,” “NB,” and the like, may refer to one or more wireless nodes that service a cell to provide a wireless connection between user devices and a wider network generally and that the concepts discussed are not limited to any particular wireless technology. Although certain aspects are described in the context of LTE or 5G NR, references to “eNB,” “gNB,” “nodeB,” “base station,” “NB,” and the like, are not intended to limit the concepts discussed herein to any particular wireless technology and the concepts discussed may be applied in any wireless system.

[0043] Node - The term “node,” or “wireless node” as used herein, may refer to one more apparatus associated with a cell that provide a wireless connection between user devices and a wired network generally.

[0044] Processing Element (or Processor) - refers to various elements or combinations of elements that are capable of performing a function in a device, such as a user equipment or a cellular network device. Processing elements may include, for example: processors and associated memory, portions or circuits of individual processor cores, entire processor cores, individual processors, processor arrays, circuits such as an Application Specific Integrated Circuit (ASIC), programmable hardware elements such as a field programmable gate array (FPGA), as well any of various combinations of the above.

[0045] Channel - a medium used to convey information from a sender (transmitter) to a receiver. It should be noted that since characteristics of the term “channel” may differ according to different wireless protocols, the term “channel” as used herein may be considered as being used in a manner that is consistent with the standard of the type of device with reference to which the term is used. In some standards, channel widths may be variable (e.g., depending on device capability, band conditions, and the like). For example, LTE may support scalable channel bandwidths from 1.4 MHz to 20MHz. WLAN channels may be 22MHz wide while Bluetooth channels may be IMhz wide. Other protocols and standards may include different definitions of channels. Furthermore, some standards may define and use multiple types of channels (e.g., different channels for uplink or downlink and / or different channels for different uses such as data, control information, and the like).

[0046] Band - The term “band” has the full breadth of its ordinary meaning, and at least includes a section of spectrum (e.g., radio frequency spectrum) in which channels are used or set aside for the same purpose.

[0047] Configured to - Various components may be described as “configured to” perform a task or tasks. In such contexts, “configured to” is a broad recitation generally meaning“having structure that” performs the task or tasks during operation. As such, the component may be configured to perform the task even when the component is not currently performing that task (e.g., a set of electrical conductors may be configured to electrically connect a module to another module, even when the two modules are not connected). In some contexts, “configured to” may be a broad recitation of structure generally meaning “having circuitry that” performs the task or tasks during operation. As such, the component may be configured to perform the task even when the component is not currently on. In general, the circuitry that forms the structure corresponding to “configured to” may include hardware circuits.

[0048] Various components may be described as performing a task or tasks, for convenience in the description. Such descriptions should be interpreted as including the phrase “configured to.” Reciting a component that is configured to perform one or more tasks is expressly intended not to invoke 35 U.S.C. § 112(f) interpretation for that component.

[0049] Example Wireless Communication System

[0050] Turning now to Figure 1, a simplified example of a wireless communication system is illustrated, according to some aspects. It is noted that the system of Figure l is a non-limiting example of a possible system, and that features of this disclosure may be implemented in any of various systems, as desired.

[0051] As shown, the example wireless communication system includes a base station 102A, which communicates over a transmission medium with one or more user devices 106A and 106B, through 106N. Each of the user devices may be referred to herein as a “user equipment” (UE). Thus, the user devices 106 are referred to as UEs or UE devices.

[0052] The base station (BS) 102A may be a base transceiver station (BTS) or cell site(e.g., a “cellular base station”) and may include hardware that enables wireless communicationwith the UEs 106 A through 106N.

[0053] The communication area (or coverage area) of the base station may be referred to as a “cell.” The base station 102A and the UEs 106 may be configured to communicate over the transmission medium using any of various radio access technologies (RATs), also referred to as wireless communication technologies, or telecommunication standards, such as GSM, UMTS (associated with, for example, WCDMA or TD-SCDMA air interfaces), LTE, LTE-A, 5G NR, HSPA, 3GPP2 CDMA2000. Note that if the base station 102A is implemented in the context of LTE, it may alternately be referred to as an ‘eNodeB’ or ‘eNB’. Note that if the base station 102A is implemented in the context of 5G NR, it may alternately be referred to as a ‘gNodeB’ or ‘gNB’.

[0054] In some aspects, the UEs 106 may be loT UEs, which may comprise a network access layer designed for low-power loT applications utilizing short-lived UE connections. An loT UE may utilize technologies such as M2M or MTC for exchanging data with an MTC server or device via a public land mobile network (PLMN), proximity service (ProSe) or device-to-device (D2D) communication, sensor networks, or loT networks. The M2M or MTC exchange of data may be a machine-initiated exchange of data. An loT network describes interconnecting loT UEs, which may include uniquely identifiable embedded computing devices (within the Internet infrastructure), with short-lived connections. As an example, vehicles to everything (V2X) may utilize ProSe features using an SL interface for direct communications between devices. The loT UEs may also execute background applications (e.g., keep-alive messages, status updates, and the like) to facilitate the connections of the loT network.

[0055] As shown, the UEs 106, such as UE 106A and UE 106B, may directly exchangecommunication data via an SL interface 108. The SL interface 108 may be a PC5 interface comprising one or more physical channels, including but not limited to a Physical Sidelink Shared Channel (PSSCH), a Physical Sidelink Control Channel (PSCCH), a Physical Sidelink Broadcast Channel (PSBCH), and a Physical Sidelink Feedback Channel (PSFCH).

[0056] In V2X scenarios, one or more of the base stations 102 may be or act as Road Side Units (RSUs). The term RSU may refer to any transportation infrastructure entity used for V2X communications. An RSU may be implemented in or by a suitable wireless node or a stationary (or relatively stationary) UE, where an RSU implemented in or by a UE may be referred to as a “UE-type RSU,” an RSU implemented in or by an eNB may be referred to as an “eNB-type RSU,” an RSU implemented in or by a gNB may be referred to as a “gNB-type RSU,” and the like. In one example, an RSU is a computing device coupled with radio frequency circuitry located on a roadside that provides connectivity support to passing vehicle UEs (vUEs). The RSU may also include internal data storage circuitry to store intersection map geometry, traffic statistics, media, as well as applications / software to sense and control ongoing vehicular and pedestrian traffic. The RSU may operate on the 5.9 GHz Intelligent Transport Systems (ITS) band to provide very low latency communications required for high speed events, such as crash avoidance, traffic warnings, and the like. Additionally, or alternatively, the RSU may operate on the cellular V2X band to provide the aforementioned low latency communications, as well as other cellular communications services. Additionally, or alternatively, the RSU may operate as a Wi-Fi hotspot (2.4 GHz band) and / or provide connectivity to one or more cellular networks to provide uplink and downlink communications. The computing device(s) and some or all of the radio frequency circuitry of the RSU may be packaged in a weather enclosure suitable for outdoor installation, and it may include a network interface controller to provide a wired connection (e.g., Ethernet) to a traffic signal controllerand / or a backhaul network.

[0057] As shown, the base station 102A may also be equipped to communicate with a network 100 (e.g., a core network of a cellular service provider, a telecommunication network such as a public switched telephone network (PSTN), and / or the Internet, among various possibilities). Thus, the base station 102A may facilitate communication between the user devices and / or between the user devices and the network 100. In particular, the cellular base station 102 A may provide UEs 106 with various telecommunication capabilities, such as voice, SMS and / or data services.

[0058] Base station 102 A and other similar base stations (such as base stations 102B through 102N) operating according to the same or a different cellular communication standard may thus be provided as a network of cells, which may provide continuous or nearly continuous overlapping service to UEs 106A-106N and similar devices over a geographic area via one or more cellular communication standards.

[0059] Thus, while base station 102A may act as a “serving cell” for UEs 106A-106N as illustrated in Figure 1, each UE 106 may also be capable of receiving signals from (and possibly within communication range of) one or more other cells (which may be provided by base stations 102B-102N and / or any other base stations), which may be referred to as “neighboring cells.” Such cells may also be capable of facilitating communication between user devices and / or between user devices and the network 100. Such cells may include “macro” cells, “micro” cells, “pico” cells, and / or cells which provide any of various other granularities of service area size. For example, base stations 102A and 102B illustrated in Figure 1 may be macro cells, while base station 102N may be a micro cell. Other configurations are also possible.

[0060] In some aspects, base station 102 A may be a next generation base station, (e.g., a 5G New Radio (5G NR) base station, or “gNB”). In some aspects, a gNB may be connected to a legacy evolved packet core (EPC) network and / or to a NR core (NRC) / 5G core (5GC) network. In addition, a gNB cell may include one or more transition and reception points (TRPs). In addition, a UE capable of operating according to 5G NR may be connected to one or more TRPs within one or more gNBs. For example, it may be possible that that the base station 102A and one or more other base stations 102 support joint transmission, such that UE 106 may be able to receive transmissions from multiple base stations (and / or multiple TRPs provided by the same base station). For example, as illustrated in Figure 1, both base station 102 A and base station 102C are shown as serving UE 106 A.

[0061] Note that a UE 106 may be capable of communicating using multiple wireless communication standards. For example, the UE 106 may be configured to communicate using a wireless networking (e.g., Wi-Fi) and / or peer-to-peer wireless communication protocol (e.g., Bluetooth, Wi-Fi peer-to-peer, and the like) in addition to at least one of the cellular communication protocol discussed in the definitions above. The UE 106 may also or alternatively be configured to communicate using one or more global navigational satellite systems (GNSS) (e.g., GPS or GLONASS), one or more mobile television broadcasting standards (e.g., ATSC-M / H), and / or any other wireless communication protocol, if desired. Other combinations of wireless communication standards (including more than two wireless communication standards) are also possible.

[0062] As illustrated in Figure 2, in one or more embodiments, the UE 106 may be a device with cellular communication capability such as a mobile phone, a hand-held device, a computer, a laptop, a tablet, a smart watch, or other wearable device, or virtually any type ofwireless device.

[0063] The UE 106 may include a processor (processing element) that is configured to execute program instructions stored in memory. The UE 106 may perform any of the method aspects described herein by executing such stored instructions. Alternatively, or in addition, the UE 106 may include a programmable hardware element such as an FPGA (field- programmable gate array), an integrated circuit, and / or any of various other possible hardware components that are configured to perform (e.g., individually or in combination) any of the method aspects described herein, or any portion of any of the method aspects described herein.

[0064] The UE 106 may include one or more antennas for communicating using one or more wireless communication protocols or technologies. In some aspects, the UE 106 may be configured to communicate using, for example, NR or LTE using at least some shared radio components. As additional possibilities, the UE 106 could be configured to communicate using CDMA2000 (IxRTT / IxEV-DO / HRPD / eHRPD) or LTE using a single shared radio and / or GSM or LTE using the single shared radio. The shared radio may couple to a single antenna, or may couple to multiple antennas (e.g., for a multiple-input multiple output (MIMO) configuration) for performing wireless communications. In general, a radio may include any combination of a baseband processor, analog RF signal processing circuitry (e.g., including filters, mixers, oscillators, amplifiers, and the like), or digital processing circuitry (e.g., for digital modulation as well as other digital processing). Similarly, the radio may implement one or more receive and transmit chains using the aforementioned hardware. For example, the UE 106 may share one or more parts of a receive and / or transmit chain between multiple wireless communication technologies, such as those discussed above.

[0065] In some aspects, the UE 106 may include separate transmit and / or receive chains(e.g., including separate antennas and other radio components) for each wireless communication protocol with which it is configured to communicate. As a further possibility, the UE 106 may include one or more radios which are shared between multiple wireless communication protocols, and one or more radios which are used exclusively by a single wireless communication protocol. For example, the UE 106 might include a shared radio for communicating using either of LTE or 5GNR (or either of LTE or IxRTT, or either of LTE or GSM, among various possibilities), and separate radios for communicating using each of WiFi and Bluetooth. Other configurations are also possible.

[0066] In some aspects, a downlink resource grid may be used for downlink transmissions from any of the base stations 102 to the UEs 106, while uplink transmissions may utilize similar techniques. The grid may be a time-frequency grid, called a resource grid or time-frequency resource grid, which is the physical resource in the downlink in each slot. Such a timefrequency plane representation is a common practice for Orthogonal Frequency Division Multiplexing (OFDM) systems, which makes it intuitive for radio resource selection. Each column and each row of the resource grid corresponds to one OFDM symbol and one OFDM subcarrier, respectively. The duration of the resource grid in the time domain corresponds to one slot in a radio frame. The smallest time-frequency unit in a resource grid is denoted as a resource element. Each resource grid may comprise a number of resource blocks, which describe the mapping of certain physical channels to resource elements. Each resource block comprises a collection of resource elements. There are several different physical downlink channels that are conveyed using such resource blocks.

[0067] The physical downlink shared channel (PDSCH) may carry user data and higher layer signaling to the UEs 106. The physical downlink control channel (PDCCH) may carryinformation about the transport format and resource allocations related to the PDSCH channel, among other things. It may also inform the UEs 106 about the transport format, resource allocation, and HARQ (Hybrid Automatic Repeat Request) information related to the uplink shared channel. Typically, downlink scheduling (assigning control and shared channel resource blocks to the UE 102 within a cell) may be performed at any of the base stations 102 based on channel quality information fed back from any of the UEs 106. The downlink resource assignment information may be sent on the PDCCH used for (e.g., assigned to) each of the UEs.

[0068] The PDCCH may use control channel elements (CCEs) to convey the control information. Before being mapped to resource elements, the PDCCH complex- valued symbols may first be organized into quadruplets, which may then be permuted using a sub-block interleaver for rate matching. Each PDCCH may be transmitted using one or more of these CCEs, where each CCE may correspond to nine sets of four physical resource elements known as resource element groups (REGs). Four Quadrature Phase Shift Keying (QPSK) symbols may be mapped to each REG. The PDCCH may be transmitted using one or more CCEs, depending on the size of the Downlink Control Information (DCI) and the channel condition. There may be four or more different PDCCH formats defined in LTE with different numbers of CCEs (e.g., aggregation level, L=l, 2, 4, or 8).

[0069] Example Communication Device

[0070] Figure 3 illustrates an example simplified block diagram of a communication device106, according to some aspects. It is noted that the block diagram of the communication device of Figure 3 is only one example of a possible communication device. According to aspects, communication device 106 may be a UE device or terminal, a mobile device or mobile station,a wireless device or wireless station, a desktop computer or computing device, a mobile computing device (e.g., a laptop, notebook, or portable computing device), a tablet, and / or a combination of devices, among other devices. As shown, the communication device 106 may include a set of components configured to perform core functions. For example, this set of components may be implemented as a system on chip (SOC), which may include portions for various purposes. Alternatively, this set of components may be implemented as separate components or groups of components for the various purposes. The set of components may be coupled (e.g., communicatively; directly or indirectly) to various other circuits of the communication device 106.

[0071] For example, the communication device 106 may include various types of memory (e.g., including NAND flash 310), an input / output interface such as connector I / F 320 (e.g., for connecting to a computer system; dock; charging station; input devices, such as a microphone, camera, keyboard; output devices, such as speakers; and the like), the display 360, which may be integrated with or external to the communication device 106, and wireless communication circuitry 330 (e.g., for LTE, LTE-A, NR, UMTS, GSM, CDMA2000, Bluetooth, Wi-Fi, NFC, GPS, and the like). In some aspects, communication device 106 may include wired communication circuitry (not shown), such as a network interface card (e.g., for Ethernet connection).

[0072] The wireless communication circuitry 330 may couple (e.g., communicatively; directly or indirectly) to one or more antennas, such as antenna(s) 335 as shown. The wireless communication circuitry 330 may include cellular communication circuitry and / or short to medium range wireless communication circuitry, and may include multiple receive chains and / or multiple transmit chains for receiving and / or transmitting multiple spatial streams, suchas in a MIMO configuration.

[0073] In some aspects, as further described below, cellular communication circuitry 330 may include one or more receive chains (including and / or coupled to (e.g., communicatively; directly or indirectly) dedicated processors and / or radios) for multiple Radio Access Technologies (RATs) (e.g., a first receive chain for LTE and a second receive chain for 5G NR). In addition, in some aspects, cellular communication circuitry 330 may include a single transmit chain that may be switched between radios dedicated to specific RATs. For example, a first radio may be dedicated to a first RAT (e.g., LTE) and may be in communication with a dedicated receive chain and a transmit chain shared with a second radio. The second radio may be dedicated to a second RAT (e.g., 5G NR) and may be in communication with a dedicated receive chain and the shared transmit chain. In some aspects, the second RAT may operate at mmWave frequencies. As mmWave systems operate in higher frequencies than typically found in LTE systems, signals in the mmWave frequency range are heavily attenuated by environmental factors. To help address this attenuating, mmWave systems often utilize beamforming and include more antennas as compared LTE systems. These antennas may be organized into antenna arrays or panels made up of individual antenna elements. These antenna arrays may be coupled to the radio chains.

[0074] The communication device 106 may also include and / or be configured for use with one or more user interface elements.

[0075] The communication device 106 may further include one or more smart cards 345 that include Subscriber Identity Module (SIM) functionality, such as one or more Universal Integrated Circuit Card(s) (UICC(s)) cards 345.

[0076] As shown, the SOC 300 may include processor(s) 302, which may execute programinstructions for the communication device 106 and display circuitry 304, which may perform graphics processing and provide display signals to the display 360. The processor(s) 302 may also be coupled to memory management unit (MMU) 340, which may be configured to receive addresses from the processor(s) 302 and translate those addresses to locations in memory (e.g., memory 306, read only memory (ROM) 350, NAND flash memory 310) and / or to other circuits or devices, such as the display circuitry 304, wireless communication circuitry 330, connector I / F 320, and / or display 360. The MMU 340 may be configured to perform memory protection and page table translation or set up. In some aspects, the MMU 340 may be included as a portion of the processor(s) 302.

[0077] As noted above, the communication device 106 may be configured to communicate using wireless and / or wired communication circuitry. As described herein, the communication device 106 may include hardware and software components for implementing any of the various features and techniques described herein. The processor 302 of the communication device 106 may be configured to implement part or all of the features described herein (e.g., by executing program instructions stored on a memory medium). Alternatively (or in addition), processor 302 may be configured as a programmable hardware element, such as a Field Programmable Gate Array (FPGA), or as an Application Specific Integrated Circuit (ASIC). Alternatively (or in addition) the processor 302 of the communication device 106, in conjunction with one or more of the other components 300, 304, 306, 310, 320, 330, 340, 345, 350, 360 may be configured to implement part or all of the features described herein.

[0078] In addition, as described herein, processor 302 may include one or more processing elements. Thus, processor 302 may include one or more integrated circuits (ICs) that are configured to perform the functions of processor 302. In addition, each integrated circuit mayinclude circuitry (e.g., first circuitry, second circuitry, and the like) configured to perform the functions of processor(s) 302.

[0079] Further, as described herein, wireless communication circuitry 330 may include one or more processing elements. In other words, one or more processing elements may be included in wireless communication circuitry 330. Thus, wireless communication circuitry 330 may include one or more integrated circuits (ICs) that are configured to perform the functions of wireless communication circuitry 330. In addition, each integrated circuit may include circuitry (e.g., first circuitry, second circuitry, and the like) configured to perform the functions of wireless communication circuitry 330.

[0080] Example Base Station

[0081] Figure 4 illustrates an example block diagram of a base station 102, according to some aspects. It is noted that the base station of Figure 4 is a non-limiting example of a possible base station. As shown, the base station 102 may include processor(s) 404 which may execute program instructions for the base station 102. The processor(s) 404 may also be coupled to memory management unit (MMU) 440, which may be configured to receive addresses from the processor(s) 404 and translate those addresses to locations in memory (e.g., memory 460 and read only memory (ROM) 450) or to other circuits or devices.

[0082] The base station 102 may include at least one network port 470. The network port 470 may be configured to couple to a telephone network and provide a plurality of devices, such as UE devices 106, access to the telephone network as described above in Figure 1.

[0083] The network port 470 (or an additional network port) may also or alternatively be configured to couple to a cellular network, e.g., a core network of a cellular service provider. The core network may provide mobility related services and / or other services to a plurality ofdevices, such as UE devices 106. In some cases, the network port 470 may couple to a telephone network via the core network, and / or the core network may provide a telephone network (e.g., among other UE devices serviced by the cellular service provider).

[0084] In some aspects, base station 102 may be a next generation base station, (e.g., a 5G New Radio (5G NR) base station, or “gNB”). In such aspects, base station 102 may be connected to a legacy evolved packet core (EPC) network and / or to a NR core (NRC) / 5G core (5GC) network. In addition, base station 102 may be considered a 5G NR cell and may include one or more transition and reception points (TRPs). In addition, a UE capable of operating according to 5G NR may be connected to one or more TRPs within one or more gNBs.

[0085] The base station 102 may include at least one antenna 434, and possibly multiple antennas. The at least one antenna 434 may be configured to operate as a wireless transceiver and may be further configured to communicate with UE devices 106 via radio 430. The antenna 434 communicates with the radio 430 via communication chain 432. Communication chain 432 may be a receive chain, a transmit chain or both. The radio 430 may be configured to communicate via various wireless communication standards, including 5G NR, LTE, LTE- A, GSM, UMTS, CDMA2000, Wi-Fi, and the like.

[0086] The base station 102 may be configured to communicate wirelessly using multiple wireless communication standards. In some instances, the base station 102 may include multiple radios, which may enable the base station 102 to communicate according to multiple wireless communication technologies. For example, as one possibility, the base station 102 may include an LTE radio for performing communication according to LTE as well as a 5G NR radio for performing communication according to 5G NR. In such a case, the base station 102 may be capable of operating as both an LTE base station and a 5G NR base station. Whenthe base station 102 supports mmWave, the 5G NR radio may be coupled to one or more mmWave antenna arrays or panels. As another possibility, the base station 102 may include a multi-mode radio, which is capable of performing communications according to any of multiple wireless communication technologies (e.g., 5GNR and LTE, 5GNR and Wi-Fi, LTE and Wi-Fi, LTE and UMTS, LTE and CDMA2000, UMTS and GSM, and the like).

[0087] Further, the BS 102 may include hardware and software components for implementing or supporting implementation of features described herein. The processor 404 of the base station 102 may be configured to implement or support implementation of part or all of the methods described herein (e.g. , by executing program instructions stored on a memory medium). Alternatively, the processor 404 may be configured as a programmable hardware element, such as a Field Programmable Gate Array (FPGA), or as an Application Specific Integrated Circuit (ASIC), or a combination thereof. Alternatively (or in addition) the processor 404 of the BS 102, in conjunction with one or more of the other components 430, 432, 434, 440, 450, 460, 470 may be configured to implement or support implementation of part or all of the features described herein.

[0088] In addition, as described herein, processor(s) 404 may include one or more processing elements. Thus, processor(s) 404 may include one or more integrated circuits (ICs) that are configured to perform the functions of processor(s) 404. In addition, each integrated circuit may include circuitry (e.g. , first circuitry, second circuitry, and the like) configured to perform the functions of processor(s) 404.

[0089] Further, as described herein, radio 430 may include one or more processing elements. Thus, radio 430 may include one or more integrated circuits (ICs) that are configured to perform the functions of radio 430. In addition, each integrated circuit may include circuitry(e.g., first circuitry, second circuitry, and the like) configured to perform the functions of radio430.

[0090] Channel State Information (CSI) Prediction and Artificial Intelligence (AI)- based and / or Machine Learning (ML)-based Models

[0091] As used herein, Artificial intelligence (Al) refers to the simulation of human intelligence processes by machines, usually computer systems, and Machine learning (ML) refers to a subset of Al that creates algorithms and statistical models to perform a specific task without using explicit instructions, relying instead on patterns and inference. ML algorithms may build mathematical models based on sample data, called training data, to make predictions or decisions without being programmed specifically for that task. Learned signal processing algorithms are expected to empower the next generation of wireless systems with significant reductions in power consumption and improvements in density, throughput, and accuracy when compared to the brittle and manually-designed systems of today.

[0092] Turning now to Figure 5, various diagrams 500 / 530 / 550 detailing methods of performing Channel State Information (CSI) feedback are illustrated, according to some aspects. Referring first to diagram 500, a base station 505 (e.g., also referred to herein as a “gNB” or “gNodeB”) may configure a periodic CSI-RS pattern (e.g., 506i, 5062, 5063, 5064. . .). Then, a UE 510 may calculate a CSI feedback (CSI-FB) measurement (e.g., CSI-FB 51 li) based on one or more previous CSI-RS measurements (e.g., 506i, 5062, and 506s). In some cases, the UE 510 may also be able to make one or more predictions of future CSI measurements 515. For example, the UE 510 may predict the channel measurement 5203-1 (as well as one or more subsequent channel measurements, e.g., 5203-2, though ideally all prior to the transmission of 5064) based on the measurements 506i, 5062, and 5063 and the use of oneor more Al-based prediction models. The UE 510 may calculate the CSI feedback jointly or separately for each of occasions 51 li, 5203-1, and 5203-2, as shown in diagram 500. The UE 510 may feedback the codebook at some configured time that is at least a predicted processing time delay amount after the time of measurement 5063. In other alternatives, the predicted processing time delay amount can be longer than the current number of symbols, so as to accommodate the model requiring additional time to make the prediction of one or more future CSI feedback measurements.

[0093] Turning now to diagram 530, as mentioned above, in the case of traditional CSI feedback (e.g., through 3GPP Release 17), a base station 535 (e.g., also referred to herein as a “gNB” or “gNodeB”) may periodically transmit a CSI-RS pattern (e.g., 536i, 5362, 5363, 5064. . .) to a UE 540, and the UE 540 periodically provides CSI feedback (e.g., CSI-FB 5411, 54U, 5413, 5414, etc.). The base station 535 may then apply the CSI feedback to generate percoding matrix index (PMI) for a duration of time (e.g., 545 I, 5452, 5453, 5454, etc.) until a next CSI feedback 54 lnis available from UE 540.

[0094] As also mentioned above, some base stations may use an older CSI feedback function that assumes that a channel’s strength does not change substantially over time (e.g., over the span of a few milliseconds). One possible 3GPP Release 18 enhancement is illustrated in diagram 550. As shown in diagram 550, the base station 555 may transmit a cluster for CSI- RSs (e.g., 556i, 5562, 5563, 5564, etc.), and the UE 560 may transmit CSI feedback (e.g., CSI- FB 561i, 56h, 56b, 5614, etc.) to the base station 555 based on at least one CSI-RS of the cluster of CSI-RSs 556n. The base station then applies the CSI feedback to generate PMI for a duration of time (e.g., 565i, 5652, 5653, 5654, etc.) until a next CSI feedback 56 lnis available from UE 560. In both instances of diagrams 530 and 550, however, frequent CSI feedbackfrom the UE is required, and both schemes are only best suited for low mobility UE scenarios.

[0095] Performing Life Cycle Management (LCM) for Artificial Intelligence (AI)- based Channel State Information (CSI) Prediction Models

[0096] Turning now to Figure 6, a flow diagram detailing a method 600 of performing improved life cycle management (LCM) for Al-based CSI prediction models is illustrated, according to some aspects. Method 600 may begin by a UE 605 transmitting one or more UE capabilities (615) to a network base station, e.g., gNodeB 610. According to some embodiments, the one or more UE capabilities 615 may comprise one or more of: (1) ability to support of Al-based CSI prediction; (2) a maximum prediction window (i.e., how far into to the “future” the UE is able to predict CSI measurements); (3) a prediction granularity level; and / or (4) a measurement window.

[0097] Regarding capability (1) above, a UE may, e.g., report a “channel -based” prediction capability or a “PMI-based” prediction capability to the base station. Regarding the channelbased prediction capability, the CSI feedback is generally separately configured by the network, wherein the CSI feedback scheme can be any type CSI feedback (e.g., type I, type II, e-type II, or R-18 codebook enhancement). Regarding the PMI-based prediction capability, the UE may predict the PMI from previously-calculated PMI directly.

[0098] Regarding capability (2) above, a UE’s maximum prediction window may be calculated from a CSI-RS reference resource (e.g., n-nCdi_ref), or the max prediction window can be calculated from the CSI report slot. It is noted that Al-based CSI prediction can typically predict out for longer windows than traditional “signaling processing-based” approaches (e.g., 5ms, 10ms, 15ms, 20ms, etc.).

[0099] Regarding capability (3) above, a UE’s prediction granularity level may compriseone slot or multiple slots, or it may be the same as the CSI-RS periodicity (e.g., when p-CSI- RS or sp-CSI-RS are used).

[0100] Regarding capability (4), in the case of p-CSI-RS or sp-CSI-RS configuration, the measurement window may be left up to a UE’s implementation; whereas, in the case of ap- CSI-RS configuration, the measurement window may simply be the length of bursty CSI-RS occasion in the ap-CSI-RS configuration.

[0101] Returning to method 600, at step 620, the gNodeB 610 may transmit a network configuration to the UE 605. The network configuration 620 may be used to activate and / or deactivate the UE’s CSI prediction function. Activation through a CSI report configuration may be made with one or multiple predicted time offsets. For example, an offset value may be counted from a legacy CSI-RS reference resource n-nCdi_ref, or it may be counted from a CSI report occasion. In some embodiments, the selected CSI prediction position then needs to be one that is supported by the UE’s capability report. If the UE supports R-18 CSI codebook or Al-based CSI compression using time / frequency / spatial domain, then multiple predicted time offsets may be configured. However, if the UE only supports the pre-R-18 codebook, only one predicted position can be configured per CSI report (or, if multiple predicted positions are desired, it may be achieved with multiple PMI and can be configured in one aggregated CSI report).

[0102] In cases where channel-based prediction is activated, the UE may predict a channel measurement and then calculate PMI using traditional codebook or Al-based feedback. Whereas, in cases where PMI-based prediction is activated, the UE may simply predict the PMI based on a past PMI.

[0103] At step 625, the gNodeB 610 may transmit a CSI-RS transmission to UE 605. Incases where the CSI prediction only applies to p-CSI-RS configuration or sp-CSI-RS configuration, there is no need for the UE to report the measurement window; whereas, if AI- based CSI prediction applies to ap-CSI-RS configuration, then the gNodeB 610 would need to configuration multiple ap-CSI-RS, i.e., according to measurement window report.

[0104] Next, at step 630, the UE may make and report back its first CSI report using a selected Al-based model to the gNodeB 610. As shown at block 635, according to method 600, the UE 605 may actively select, monitor the performance of, and / or switch between models during the life cycle of the models and during the window in which is it making AI- based predictions for its CSI reports. According to some embodiments, model selection is up to the UE, and the UE can select from among one or more pre-trained Al models, e.g., based on a training condition, such as UE current speed, UE current position, etc.

[0105] As mentioned above, according to some embodiments, it may be important that, over time, the UE is able to monitor the performance of the Al-based models. For example, the UE may monitor Al-based model performance by comparing predicted channel measurements to CSI-RS measurement received at a later time. For example, a UE may then be able to autonomously determine whether the Al-based model’s performance has degraded beyond a threshold amount, such that the model should be discarded, switched, and / or updated. Alternately, the network may configure the UE to periodically send CSI prediction metrics (e.g., normalized mean square error (NMSE), cosine similarity, or squared cosine similarity) back to the network. In another alternative, the network itself may configure the Al-based model performance metric that the UE should use (e.g., NMSE for channel-based predictions, and / or cosine similarity for PMI-based predictions), and a UE may then be able to autonomously determine whether the Al-based model’s performance has degraded beyond aconfigured threshold value.

[0106] As also mentioned above, according to some embodiments, the UE may autonomously (and / or automatically) switch which Al-based model it is using and then send subsequent CSI reports to the network, e.g., as shown at step 640. After the model switching, the UE may either let the network know (e.g., by reporting back a model ID of the new model) or not let the network know that the active model has been switched. In the case where all of the models stored at the UE have failed, the UE may send an uplink MAC CE requesting that the network disable all use of Al-based CSI prediction function until further request by the UE to activate it, and the network may respond by sending a deactivation command.

[0107] According to some embodiments, the network may also indirectly monitor the AI- based model performance indirectly via ACK / NACK feedback and downlink (DL) throughput in response to coherent DL transmission (as shown, e.g., at step 645). As described above, the more NACKs that are received by the base station over a particular time window, the higher the likelihood is that a model has failed; although, of course, there could also be other causes for the high proportion of NACKs being received. For another example, the UE can determine that the performance of the Al model has degraded if the Physical Downlink Shared Channel (PDSCH) Block Error Rate (BLER) increases. The particular metrics used for performance monitoring may be configured by the network,

[0108] Figure 7 illustrates a flow diagram detailing another method 700 of performing improved LCM for Al-based CSI prediction models is illustrated, according to some aspects. Similar to method 600, method 700 may begin at step 705 by the UE 605 transmitting one or more UE capabilities (705) to a network base station, e.g., gNodeB 610. According to some embodiments, the one or more UE capabilities 705 may comprise one or more pairs of modelIDs and the capability sets / descriptions that correspond to such model IDs. According to some embodiments, the Al-based models may be trained by a UE offline, and then can be fine-tuned when online. For example, after deployment, a model can be updated similarly to a software upgrade (e.g., a model may be fine-tuned / updated based on new data received from an over- the-top (OTT) server). When multiple models are trained, a UE may report all of its model IDs to the network. The model description may describe the potential usage of each model, e.g., what scenarios the model can be used in, channel statistics, doppler, etc., as well as the expected model performance (e.g., in terms of NMSE, general cosine similarity (GCS), or squared general cosine similarity (SGCS), etc.).

[0109] In some embodiments, e.g., at step 710, the network may configure the Al-model that is to be used by the UE via a transmitted model ID. In some embodiments, the network may configure a single Al model and activate it using one form of signaling (e.g., RRC or MAC CE signaling). In other embodiments, the network may configure the Al-based model ID to be used via RRC, but then activate or deactivate it later via MAC CE signaling. Alternately, the network may configure a list of model IDs via RRC, and then the UE may select one (or more) of the model IDs from the signaled list of model IDs. The remaining CSI report configuration (e.g., in terms of offset, position, codebook to be used, etc.) is similar to that described with regard to step 620 of Figure 6.

[0110] At step 715, the gNodeB 610 may transmit a CSI-RS transmission to UE 605. In cases where the CSI prediction only applies to p-CSI-RS configuration or sp-CSI-RS configuration, there is no need for the UE to report the measurement window; whereas, if AI- based CSI prediction applies to ap-CSI-RS configuration, then the gNodeB 610 would need to configuration multiple ap-CSI-RS, i.e., according to measurement window report.[OHl] Next, at step 720 (and similarly to step 635 described above with reference to Figure 6), the UE 605 may actively select, monitor the performance of, and / or switch between models during the life cycle of the models and during the window in which is it making Al-based predictions for its CSI reports. According to some embodiments, the UE may periodically report a currently active model ID and intermediate key performance indicators (KPI) to the network, wherein the network may be able to configure the report periodicity and / or performance metrics, and the network may be the entity that makes the decision to instruct the UE to switch to a different Al-based CSI prediction model. Alternately, the UE may employ an event-driven reporting scheme, where, e.g., the UE only reports back to the network when a model’s performance metric has degraded below a threshold value (e.g., a network- configurable threshold value). If that level of degradation occurs, the UE may report both the model ID and corresponding performance metric value back to the network.

[0112] As mentioned above with regard to Figure 6, according to some embodiments, the network may also perform indirect model performance monitoring via DL throughput values and / or ACK / NACK feedback monitoring. In some embodiments, the network may be able to activate, deactivate, and / or switch the model that is currently being used by the UE by transmitting the model ID of the model that the network desires the UE to begin using instead.

[0113] At step 725, the UE 605 may send a second CSI report to the gNodeB 610, e.g., a CSI report made by a second (i.e., different) model than the model used to produce the measurements reported in CSI report 715. In some embodiments, the UE may also transmit the corresponding model ID for the second model in its second CSI report 725. Finally, the network may generate coherent DL transmissions (as shown, e.g., at step 730), e.g., in order to perform the aforementioned network performance monitoring via DL throughout and / or theproportion of NACKs in the ACK / NACK feedback received from particular UEs.

[0114] Exemplary Methods

[0115] Turning now to Figure 8, a flowchart 800 detailing a method of performing function-based LCM for Al-based CSI prediction models is illustrated, according to some aspects. First, at block 802, a UE practicing the method of 800 may transmit, from a user equipment (UE), a first capability indication to a base station, wherein the first capability indication relates to capabilities of one or more models for performing at least one Channel State Information (CSI)-related task based on artificial intelligence (Al) or machine learning (ML). Next, at block 804, the method 800 may receive, at the UE, a first network configuration to activate a use of at least one of the one or more models.

[0116] At block 806, the UE may select based, at least in part, on the first network configuration, a first model of the one or more models to use to perform a CSLrelated task. Next, at block 808, the method 800 may transmit, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the first model. Finally, at block 810, the UE may monitor at least one performance metric for the first model over time, e.g., to determine if or when the model’s performance has degraded to a level where the model should be retired, switched, or updated, etc.

[0117] Turning now to Figure 9, a flowchart 900 detailing a method of performing model identifier (ID)-based LCM for Al-based CSI prediction model is illustrated, according to some aspects. First, at block 902, a UE practicing the method of 900 may transmit, from a user equipment (UE), a first capability indication to a base station, transmit, from a user equipment (UE), a first capability indication to a base station, wherein the first capability indication comprises one or more sets of model IDs and corresponding capabilities, and wherein eachmodel ID relates to a model for performing at least one Channel State Information (CSI)-related task based on artificial intelligence (Al) or machine learning (ML). Next, at block 904, the method 900 may receive, at the UE, a first network configuration comprising at least one model ID.

[0118] At block 906, the UE may select based, at least in part, on the first network configuration, a first model corresponding to a first model ID of the at least one model ID to use to perform a CSLrelated task. Next, at block 908, the method 900 may transmit, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the first model. In some implementations, the first model ID may be transmitted along with the at least one CSI report. Finally, at block 910, the UE may monitor at least one performance metric for the first model over time, e.g., to determine if or when the model’s performance has degraded to a level where the model should be retired, switched, or updated, etc.

[0119] Additional Comments

[0120] The use of the connective term “and / or” is meant to represent all possible alternatives of the conjunction “and” and the conjunction “or.” For example, the sentence “configuration of A and / or B” includes the meaning and of sentences “configuration of A and B” and “configuration of A or B.”

[0121] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.

[0122] Aspects of the present disclosure may be realized in any of various forms. For example, some aspects may be realized as a computer-implemented method, a computer- readable memory medium, or a computer system. Other aspects may be realized using one or more custom-designed hardware devices such as ASICs. Still other aspects may be realized using one or more programmable hardware elements such as FPGAs.

[0123] In some aspects, a non-transitory computer-readable memory medium may be configured so that it stores program instructions and / or data, where the program instructions, if executed by a computer system, cause the computer system to perform a method (e.g., any of a method aspects described herein, or, any combination of the method aspects described herein, or any subset of any of the method aspects described herein, or any combination of such subsets).

[0124] In some aspects, a device (e.g., a UE 106, a BS 102) may be configured to include a processor (or a set of processors) and a memory medium, where the memory medium stores program instructions, where the processor is configured to read and execute the program instructions from the memory medium, where the program instructions are executable to implement any of the various method aspects described herein (or, any combination of the method aspects described herein, or, any subset of any of the method aspects described herein, or, any combination of such subsets). The device may be realized in any of various forms.

[0125] Although the aspects above have been described in considerable detail, numerous variations and modifications will become apparent to those skilled in the art once the above disclosure is fully appreciated. It is intended that the following claims be interpreted to embrace all such variations and modifications.

Claims

CLAIMSWhat is claimed is:

1. A method of operating a user equipment (UE), the method comprising: transmitting, from the UE, a first capability indication to a base station, wherein the first capability indication relates to capabilities of one or more models for performing at least one Channel State Information (CSI)-related task based on artificial intelligence (Al) or machine learning (ML); receiving, at the UE, a first network configuration to activate a use of at least one of the one or more models; selecting, at the UE and based, at least in part, on the first network configuration, a first model of the one or more models to use to perform a CSLrelated task; transmitting, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the first model; and monitoring, by the UE, at least one performance metric for the first model.

2. The method of claim 1, wherein the first capability indication comprises at least one of: an indication that the UE supports channel-based CSI prediction; an indication that the UE supports precoding matrix indicator (PMI)-based CSI prediction; an indication that the UE supports a maximum CSI prediction time window; an indication of a CSI prediction granularity level; or an indication of a CSI measurement window.

3. The method of claim 1, further comprising: transmitting, by the UE to the base station, a request to activate or deactivate use of at least one of the one or more models.

4. The method of claim 1, wherein the act of monitoring, by the UE, the at least one performance metric for the first model further comprises: comparing, by the UE, a first predicted CSI measurement determined based, at least in part, on an output of the first model against a second CSI measurement made subsequently to the first predicted CSI measurement.

5. The method of claim 4, further comprising: determining, by the UE and based, at least in part, on the act of comparing, that a performance metric for the first model has degraded below a threshold value.

6. The method of claim 4, further comprising: determining, by the UE and based, at least in part, on the act of comparing, a CSI prediction metric; and transmitting, by the UE to the base station, the determined CSI prediction metric.

7. The method of claim 1, wherein the act of monitoring, by the UE, the at least one performance metric for the first model further comprises: comparing, by the UE, the at least one performance metric for the first model against a threshold value configured by the base station.

8. The method of claim 1, further comprising: selecting, at the UE and based on the monitoring, a second model of the one or more models to perform the CSI-related task; and transmitting, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the second model.

9. The method of claim 8, further comprising: transmitting, from the UE to the base station, an indication that the second model was used to produce the at least one CSI report.

10. The method of claim 1, wherein the selecting, at the UE, of the first model is based, at least in part on one or more of: a position of the UE, a speed of the UE, or a training condition associated with the first model.

11. The method of claim 1, further comprising: transmitting, from the UE to the base station, an ACK / NACK indication in response to a downlink (DL) transmission,wherein the ACK / NACK indication is indicative, at least in part, of a performance metric for the first model.

12. The method of claim 1, wherein the first network configuration specifies one or more of the following: a time offset value for predicted CSI measurements; a position value for predicted CSI measurements; an indication that the UE shall perform channel-based CSI prediction; an indication that the UE shall perform PMI-based CSI prediction; an indication of a periodic CSI reference signal (p-CSI-RS) configuration; an indication of a semi-persistent CSI reference signal (sp-CSI-RS) configuration; or an indication of an aperiodic CSI reference signal (ap-CSI-RS) configuration.

13. The method of claim 1, further comprising: in response to determining, by the UE, that a performance metric for each of the one or more models has degraded below a threshold value: transmitting, by the UE to the base station, a request to deactivate use of each of the one or more models.

14. A method of operating a user equipment (UE), the method comprising: transmitting, from the UE, a first capability indication to a base station, wherein the first capability indication comprises one or more sets of model IDs and corresponding capabilities, and wherein each model ID relates to a model for performing at least one Channel State Information (CSI)-related task based on artificial intelligence (Al) or machine learning (ML); receiving, at the UE, a first network configuration comprising at least one model ID; selecting, at the UE and based, at least in part, on the first network configuration, a first model corresponding to a first model ID of the at least one model ID to use to perform a C Si-related task; transmitting, from the UE to the base station, at least one CSI report determined based, at least in part, on an output of the first model; and monitoring, by the UE, at least one performance metric for the first model.

15. The method of claim 14, wherein the first network configuration comprising at least one of the one or more model IDs is received via one of: Radio Resource Control (RRC) signaling; or Medium Access Control (MAC) Control Element (CE) signaling.

16. The method of claim 15, wherein selecting the first model corresponding to the first model ID further comprises: receiving, at the UE from the base station, an activation command indicating the first model ID via one of: RRC signaling or MAC CE signaling.

17. The method of claim 14, wherein monitoring, by the UE, at least one performance metric for the first model further comprises: periodically transmitting, from the UE to the base station, the first model ID and one or more additional CSI reports determined based, at least in part, on outputs of the first model.

18. The method of claim 14, wherein monitoring, by the UE, at least one performance metric for the first model further comprises:transmitting, from the UE to the base station and in response to determining that a performance metric for the first model has degraded below a threshold value, the first model ID and an additional CSI report determined based, at least in part, on an output of the first model.

19. The method of claim 14, further comprising: transmitting, from the UE to the base station along with the at least one CSI report, the first model ID associated with the first model.

20. A user equipment (UE) device comprising: a receiver; a transmitter; and a processor configured to perform any action or combination of actions described in any of the methods of claims 1-19.

21. A non-volatile computer-readable medium that stores instructions that, when executed, cause the performance of any action or combination of actions described in any of the methods of claims 1-19.

22. A baseband processor configured to cause a user equipment (UE) to perform any action or combination of actions described in any of the methods of claims 1-19.

Images