METHODS AND DEVICES FOR HYBRID INFLUENCING FOR BEAM MANAGEMENT IN ARTIFICIAL INTELLIGENCE / MACHINE LEARNING SYSTEMS

Abstract

WTRU is configured with input and output beam patterns and trained weighted AI / ML models. Each of the many input beam patterns includes beam indices for the input beam set, and each of the many output beam patterns includes beam indices for the output beam set. Each AI / ML model corresponds to an output beam pattern. WTRU measures the signal quality of the input beam subset of each of the many input beam patterns to determine the best input beam and report that beam to the base station. WTRU receives from the base station an indicator of one of the input beam patterns and one of the output beam patterns to predict the best output beam based on the report. WTRU predicts the best output beam using the AI / ML model corresponding to the indicated output beam pattern and the trained weights, and then reports the predicted best beam to the base station.

Description

METHOD AND APPARATUS FOR HYBRID INFERENCE FOR BEAM MANAGEMENT IN AN ARTIFICIAL INTELLIGENCE / MACHINE LEARNING SYSTEMCROSS REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 531 ,481 filed August 8, 2023, U.S. Provisional Application Serial No. 63 / 531 ,485 filed August 8, 2023, U.S. Provisional Application Serial No. 63 / 531 , 487 filed August 8, 2023, and U.S. Provisional Application Serial No. 63 / 531,492 filed August 8, 2023, the contents of which are hereby incorporated by reference herein.BACKGROUND

[0002] A 3GPP radio access network (RAN) study item on Artificial Intelligence (AI)ZMachine Learning (ML) for the 5G NR air interface was agreed. As one of the target use cases for AI / ML for air interface, beam management was selected. This technology could be a great foundation in improving performance and complexity in conventional beam management aspects, including beam prediction in the time and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement, and so forth.SUMMARY

[0003] A WTRU is configured with input and output beam patterns and AI / ML models with trained weights. Each input beam pattern includes beam indexes for a set of input beams, and each output beam pattern includes beam indexes for a set of output beams. Each AI / ML model corresponds to one output beam pattern. The WTRU measures signal quality of a subset of the set of input beams of each input beam pattern to identify a best input beam and reports that beam to a base station. The WTRU receives, from the base station, an indication of one of the input beam patterns and one of the output beam patterns for predicting a best output beam based on the report. The WTRU predicts the best output beam using the AI / ML model corresponding to the indicated output beam pattern and the trained weights. The WTRU reports the predicted best beam to the base station.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, wherein like reference numerals in the figures indicate like elements, and wherein:

[0005] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented;

[0006] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0007] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0008] FIG. 1 D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0009] FIG. 2 is a diagram showing examples of input beam pattern types (BPTs);

[0010] FIG. 3 is a diagram showing examples of output BPTs;

[0011] FIG. 4 is a flow diagram of an example method of beam prediction;

[0012] FIG. 5A is a system diagram of an example wireless network configured to perform hybrid inference for beam management;

[0013] FIG. 5B is a diagram of example beam patterns at the base station of FIG. 5A;

[0014] FIG. 6 is a diagram of an example AI / ML model at the base station side for hybrid inference;

[0015] FIG. 7 is a diagram of example AI / ML models at the WTRU side for the first WTRU and the secondWTRU of FIG. 5A for hybrid inference;

[0016] FIG. 8A is a diagram of an example of an indication of beam indexes based on generic default numbering; and

[0017] FIG. 8B is a diagram of another example of an indication of beam indexes based on generic default numbering.DETAILED DESCRIPTION

[0018] FIG. 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), singlecarrier FDMA (SC-FDMA), zero-tail unique-word discrete Fourier transform Spread OFDM (ZT-UW-DFT-S- OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0019] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104, a core network (CN) 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or networkelements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a station (STA), may be configured to transmit and / or receive wireless signals and may include a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0020] The com munications systems 100 may also incl ude a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106, the Internet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a NodeB, an eNode B (eNB), a Home Node B, a Home eNode B, a next generation NodeB, such as a gNode B (gNB), a new radio (NR) NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0021] The base station 114a may be part of the RAN 104, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, and the like. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0022] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0023] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink (DL) Packet Access (HSDPA) and / or High-Speed Uplink (UL) Packet Access (HSUPA).

[0024] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0025] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access , which may establish the air interface 116 using NR.

[0026] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0027] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0028] The base station 114b in FIG. 1A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106.

[0029] The RAN 104 may be in communication with the CN 106, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 and / or the CN 106 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 or a different RAT. For example, in addition to being connected to the RAN 104, which may be utilizing a NR radio technology, the CN 106 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0030] The CN 106 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or the other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 or a different RAT.

[0031] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellularbased radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0032] FIG. 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0033] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), any other type of integrated circuit (IC), a statemachine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0034] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0035] Although the transmit / receive element 122 is depicted in FIG. 1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0036] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11 , for example.

[0037] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0038] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may beany suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li- ion), etc.), solar cells, fuel cells, and the like.

[0039] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0040] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and / or Augmented Reality (VR / AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors. The sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, a humidity sensor and the like.

[0041] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the UL (e.g., for transmission) and DL (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e.g., for transmission) or the DL (e.g., for reception)).

[0042] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0043] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b,102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a.

[0044] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, and the like. As shown in FIG. 1 C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0045] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0046] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0047] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0048] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0049] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0050] Although the WTRU is described in FIGS. 1A-1 D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0051] In representative embodiments, the other network 112 may be a WLAN.

[0052] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic in to and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to- peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an “ad-hoc” mode of communication.

[0053] When using the 802.11ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0054] High Throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0055] Very High Throughput (VHT) STAs may support 20MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two noncontiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above described operation for the80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0056] Sub 1 GHz modes of operation are supported by 802.11 af and 802.11ah. The channel operating bandwidths, and carriers, are reduced in 802.11af and 802.11ah relative to those used in 802.11n, and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support Meter Type Control / Machine- Type Communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0057] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11 n, 802.11ac, 802.11af, and 802.11ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all ST As in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode) transmitting to the AP, all available frequency bands may be considered busy even though a majority of the available frequency bands remains idle.

[0058] In the United States, the available frequency bands, which may be used by 802.11 ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11 ah is 6 MHz to 26 MHz depending on the country code.

[0059] FIG. 1D is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0060] The RAN 104 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 104 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / orreceive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0061] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing a varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0062] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non- standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0063] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, DC, interworking between NR and E-UTRA, routing of user plane data towards User Plane Function (UPF) 184a, 184b, routing of control plane information towards Access and Mobility Management Function (AMF) 182a, 182b and the like. As shown in FIG. 1 D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0064] The CN 106 shown in FIG. 1D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0065] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of non-access stratum (NAS) signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b in order to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and the like. The AMF 182a, 182b may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0066] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 106 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 106 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing DL data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0067] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering DL packets, providing mobility anchoring, and the like.

[0068] The CN 106 may facilitate communications with other networks. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local DN 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0069] In view of FIGs. 1A-1 D, and the corresponding description of FIGs. 1A-1 D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station 114a-b, eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other device(s) described herein, may be performed by one or more emulation devices (not shown).The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0070] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or performing testing using over-the-air wireless communications.

[0071] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0072] Artificial intelligence may be broadly defined as the behavior exhibited by machines. Such behavior may, for example, mimic cognitive functions to sense, reason, adapt and act. Machine learning may refer to a type of algorithm that solves a problem based on learning through experience without explicitly being programmed. Machine learning can be considered as a subset of Al. Different machine learning paradigms may be envisioned based on the nature of data or feedback available to the learning algorithm. For example, a supervised learning approach may involve learning a function that maps input to an output based on a labeled training example, wherein each training example may be a pair consisting of an input and the corresponding output. For example, an unsupervised learning approach may involve detecting patterns in the data with no pre-existing labels. For example, a reinforcement learning approach may involve performing a sequence of actions in an environment to maximize the cumulative reward. It may be possible to apply machine learning algorithms using a combination or interpolation of the above-mentioned approaches. For example, a semisupervised learning approach may use a combination of a small amount of labeled data with a large amount of unlabeled data during training. In this regard, semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data).

[0073] Deep learning refers to a class of machine learning algorithms that employ artificial neural networks, which may be referred to as deep neural networks (DNNs). DNNs are a special class of machine learning models inspired by the human brain where the input is linearly transformed and passed through a non-linearactivation function multiple times. DNNs may include multiple layers where each layer includes linear transformation and given non-linear activation functions. The DNNs can be trained using the training data via a back-propagation algorithm. Recently, DNNs have shown state-of-the-art performance in a variety of domains, such as speech, vision, and natural language, and for various machine learning settings, such as supervised, un-supervised, and semi-supervised learning settings.

[0074] AI / ML based methods / processing may enable realization of behaviors and / or conformance with requirements by learning based on data, without an explicit configuration or sequence of steps or actions. Such methods may enable a machine to learn complex behaviors, which may be difficult to specify and / or implement when using legacy methods. An AI / ML model may be referred to herein as an implementation of an AI / ML based method, which may be made up of model parameters and the model structure. For example, a DNN- based A / IML model may include the model parameters, such as weights and biases, and the model structure, such as the types and sizes of each layer of the deep neural network, such as dense layers and convolutional layers.

[0075] A WTRU may transmit or receive a physical channel or reference signal according to at least one spatial domain filter. A beam, as used herein, may be used to refer to such a spatial domain filter. The WTRU may transmit a physical channel or signal using the same spatial domain filter used for receiving a reference signal (RS), such as a channel state information RS (CSI-RS) or a synchronization signal (SS) block. The WTRU transmission may be referred to as a target, and the received RS or SS block may be referred to as a reference or source. In such case, the WTRU may be said to transmit the target physical channel or signal according to a spatial relation with a reference to such RS or SS block.

[0076] The WTRU may transmit a first physical channel or signal according to the same spatial domain filter as the spatial domain filter used for transmitting a second physical channel or signal. The first and second transmissions may be referred to as a target and reference (or source), respectively. In such case, the WTRU may be said to transmit the first target physical channel or signal according to a spatial relation with a reference to the second reference physical channel or signal.

[0077] A spatial relation may be implicit, configured by RRC or signaled by MAC control element (CE) or downlink control information (DCI). For example, a WTRU may implicitly transmit a physical uplink shared channel (PUSCH) and a demodulation reference signal (DM-RS) of a PUSCH according to the same spatial domain filter as a sounding reference signal (SRS) indicated by a scheduling request indicator (SRI) indicated in DCI or configured by radio resource control (RRC). In another example, a spatial relation may be configured by RRC for an SRS resource indicator (SRI) or signaled by MAC CE for a physical uplink control channel (PUCCH). Such spatial relation may also be referred to as a beam indication.

[0078] The WTRU may receive a first target downlink channel or signal according to the same spatial domain filter or spatial reception parameter as a second reference downlink channel or signal. For example, such association may exist between a physical channel, such as a physical downlink control channel (PDCCH)or a physical downlink shared channel (PDSCH) and its respective DM-RS. At least when the first and second signals are reference signals, such association may exist when the WTRU is configured with a quasi-colocation (QCL) assumption type D between corresponding antenna ports. Such association may be configured as a transmission configuration indicator (TCI) state. An association between a CSI-RS or SS block and a DM-RS may be indicated to a WTRU by an index to a set of TCI states configured by RRC and / or signaled by MAC CE. Such indication may also be referred to as a beam indication.

[0079] A WTRU may be configured with one or more sets of RS resources and / or beams (or beam-pairs). Each RS resource or beam or beam-pair may be associated with a transmission from a beam having specific beam parameters (e.g., beam direction and beamwidth). The WTRU may be configured with the associated beams and / or RS resources and the beam parameters.

[0080] In an example, a WTRU may be configured with a first set of RS resources or beams or beam-pairs that may cover the entire RS resource-space or beam-space or beam-pair-space. The WTRU may determine or select a set A and a set B such that the union of set A and set B covers the entire RS-resource-space or beam-space or beam-pair-space. In an example, set A and set B may be mutually exclusive. In an example, a set B includes RS resources on which the WTRU may perform measurements to obtain direct measurement values for a first set of beams or beam-pairs (e.g., one-to-one mapping between an RS resource and a beam or beam-pair) and estimated measurement values for a second set of beams or beam-pairs (e.g., many-to-one mapping between RS resources and a beam or beam-pair). The estimated measurement values may be determined using an AI / ML estimation model, for example.

[0081] A WTRU may be configured with one or more sets of RS resources associated with each beam. For example, a WTRU may be configured with a first beam associated with two sets of RSs: a first set including a single RS resource and a second set including multiple RS resources. A WTRU may determine measurements associated with the beam via direct measurements of the RS resources in the first set or via estimation obtained from measurements of the RS resources in the second set.

[0082] A WTRU may determine a measurement set of RS resources (e.g., a set B) such that for every beam for which it must obtain measurements (either directly or via estimation), the set B contains at least one of the two sets of RS resources associated to the beam. Hereafter, a Set B may be interchangeably used with a set of RS resource sets, beams, beam-pairs, beam RS resources, RS resources and beam pattern. Hereafter, a Set A may be interchangeably used with a set of RS resource sets, beams, beam-pairs, beam RS resources, RS resources, and beam pattern.

[0083] To implement AI / ML for beam management, one option is to have the AI / ML model training and inference performed mostly only at the WTRU side or only at the base station side. There are advantages and disadvantages to each. For AI / ML model training and inference at the WTRU side, the WTRU that performs inference may have access to real-time and accurate channel coefficients. However, each WTRU may have a siloed view of the transmit beams from the network (NW) at least because CSI-RS is conventionallyconfigured in a WTRU-specific way such that data collection will take a prolonged amount of time. For AI / ML model training and inference at the base station side, the NW may have access to computational and storage resources such that training at the base station side can be more generalized and comprehensive, and the NW can, therefore, perform complex computations for the inference. However, the NW that performs inference may not have access to real-time and accurate channel coefficients.

[0084] Another possibility is that the AI / ML model could be trained at the base station and then transferred to the WTRU to perform the inference. However, in 3GPP RAN it was agreed that assistance information from the NW may not be available due to security issues, making cell-specific or site-specific models logistically difficult. Also, in case a WTRU makes inquiry to the NW to establish the validity of the AI / ML model’s use in the current cell, any response from the NW can be used to deduce the network’s beam shape information.

[0085] Embodiments described herein provide for WTRUs, base stations and corresponding methods that may efficiently perform inference and / or training of an AI / ML model at the base station (e.g., gNB) using one or more WTRUs for optimal beam prediction.

[0086] In one or more embodiment, a WTRU may receive or be configured or pre-configured with one or more generalized input and / or output beam pattern types (BPTs) that may be used to indicate beam-groups (e.g., subsets of all beams) and beam-group-based AI / ML models (e.g., via radio resource control (RRC) signaling). The WTRU may also receive or be configured or pre-configured with weights and / or coefficients corresponding to the received BPTs.

[0087] In at least some embodiments, the WTRU may receive a first set of BPTs (e.g., input BPTs) and a second set of BPTs (e.g., output BPTs). For example, the WTRU may receive or be configured or preconfigured with one or more BPTs that may be used to indicate one or more subsets and beam-group-based AI / ML models. The WTRU may receive the cell-common BPTs and corresponding trained weights, coefficients, beam indexes, and so forth via a system information block (SIB), broadcast message, multicast message toward a group of WTRUs, RRC signaling, MAC-CE, and / or DCI. Alternatively, the WTRU may receive WTRU- specific BPTs and corresponding trained weights, coefficients, beam indexes, and so forth via RRC, MAC-CE, and / or DCI.

[0088] FIG. 2 is a diagram 200 showing examples of input BPTs. An input BPT may be an index to a pool of input beam patterns that the WTRU may use as the input, for example to an AI / ML system. In the example illustrated in FIG. 2, a first input BPT 202 includes the beams to be measured (e.g., subset of Set-B beams) for a pattern of four beams 1a, 6a, 11a and 16a in a 4 x 4 beam pattern including 16 potential beams 1a, 2a, 3a, 4a, 5a, 6a, 7a, 8a, 9a, 10a, 11a, 12a, 13a, 14a, 15a and 16a. A second input BPT 204 includes the beams to be measured (e.g., subset of Set-B beams) for a pattern of three beams 1b, 5b and 9b in a 3 x 3 beam pattern including 9 potential beams 1b, 2b, 3b, 4b, 5b, 6b, 7b, 8b and 9b. A third input BPT 206 includes the beams to be measured (e.g., subset of Set-B beams) for a pattern of four beams 3c, 9c, 11c and 15c in a 3 x 5 beam pattern including 15 potential beams 1c, 2c, 3c, 4c, 5c, 6c, 7c, 8c, 9c, 10c, 11c, 12c, 13c, 14c and 15c. A fourthinput BPT 208 includes the beams to be measured (e.g., subset of Set-B beams) for a pattern of four beams 4d, 6d, 10d and 12d in a 3 x 5 beam pattern including 15 potential beams 1 d, 2d, 3d, 4d, 5d, 6d, 7d, 8d, 9d, 10d, 11d, 12d, 13d, 14d and 15d.

[0089] In FIG. 2, some examples of input beam patterns are provided that are identified by the corresponding input BPTs. For example, in input BPT 202, the first set of beam resources is indicated as a grid-based 4 x 4 square of beam resources 1a, 2a, 3a, 4a, 5a, 6a, 7a, 8a, 9a, 10a, 11a, 12a, 13a, 14a, 15a and 16a and the second set of the beam resources is shown as a subset 1a, 6a, 11a and 16a of the first set of beam resources. In another example, in input BPT 204, the first set of beam resources is shown as a gridbased 3 x 3 square of beam resourceslb, 2b, 3b, 4b, 5b, 6b, 7b, 8b and 9b , and the second set of the beam resources is shown as a subset 1b, 5b and 9b of the first set of beam resources. In another example, in input BPT 206, the first set of beam resources is indicated as a grid-based 3 x 5 rectangle of beam resources 1c, 2c, 3c, 4c, 5c, 6c, 7c, 8c, 9c, 10c, 11c, 12c, 13c, 14c and 15c, where the second set of the beam resources is shown as a subset 3c, 9c, 11c and 15c of the first beam resources. In another example, in input BPT 208, the first set of beam resources is indicated as a grid-based 3 x b rectangle of beam resources 1d, 2d, 3d, 4d, 5d, 6d, 7d, 8d, 9d, 10d, 11d, 12d, 13d, 14d and 15d, where the second set of the beam resources is shown as a subset 4d, 6d, 10d and 12d of the first set of beam resources.

[0090] For example, a WTRU may be configured with an input BPT, and the configured input BPT may indicate a corresponding beam pattern that may include a first and a second set of beam resources. The first set of beam resources may cover the entire beam-space or a subset of the beam-space. The second set of beam resources may be a subset of the first beam resources. The second set of beam resources may be used by the WTRU to perform measurements. The second set of beam resources may be a subset of one or more configured or pre-configured Set-B beam resources. That is, the WTRU may receive configuration information of one or more of the beam resources included in the second set of beam resources to receive and measure one or more parameters (e.g., RSRP, channel quality index (CQI), signal to interference noise ratio (SINR), physical downlink control channel (PDCCH) hypothetical block error rate (BLER), etc.).

[0091] FIG. 3 is a diagram 300 showing examples of output BPTs. The output BPT may be an index to a pool of models (e.g., AI / ML models). In the example illustrated in FIG. 3, a first output BPT 302 includes the AI / ML model coefficients for a pattern of four beams 2e, 3e, 6e and 7e in a 4 x 2 beam pattern of beams 1 e, 2e, 3e, 4e, 5ed, 6e, 7e and 8e. A second output BPT 304 includes the AI / ML model coefficients for a pattern of four beams 1 f, 4f, 5f, and 8f in a 4 x 2 beam pattern of beams 1 f, 2f, 3f, 4f, 5f, 6f, 7f and 8f. A third output BPT 306 includes the AI / ML model coefficients for a pattern of four beams 1g, 2g, 3g and 4g in a 2 x 2 beam pattern of beams 1 g, 2g, 3g and 4g. A fourth output BPT 308 includes the AI / ML model coefficients for a pattern of two beams 2h and 3h in a 2 x 2 beam pattern of beams 1 h, 2h, 3h and 4h.

[0092] In FIG. 3, some examples of output beam patterns are provided that are identified by the corresponding output BPTs. For example, in output BPT 302, the first set of beam resources is indicated as agrid-based 4 x 2 rectangle of beam resources 1 e, 2e, 3e, 4e, 5e, 6e, 7e and 8e, where the second set of the beam resources is shown as a subset 2e, 3e, 6e and 7e of the first set of beam resources. In another example, in output BPT 304, the first set of beam resources is indicated as a grid-based 4 x2 rectangle of beam resources 1f, 2f, 3f, 4f, 5f, 6f, 7f and 8f, where the second set of the beam resources is shown as a subset 1f, 4f, 5f, and 8f of the first set of beam resources. In another example, in output BPT 306, the first set of beam resources is indicated as a grid-based 2 x 2 square of beam resources 1g, 2g, 3g and 4g, where the second set of the beam resources is shown as a subset 1g, 2g, 3g and 4g of the first set of beam resources. In another example, in output BPT 308, the first set of beam resources is indicated as a grid-based 2 x 2 square of beam resources 1 h, 2h, 3h and 4h, where the second set of the beam resources is shown as a subset 2h and 3h of the first set of beam resources.

[0093] For example, the WTRU may be configured with an output BPT, where the configured output BPT may indicate a corresponding beam pattern that may include a first set and a second set of beam resources. The first set of beam resources may cover the entire beam-space or a subset of the beam-space. The second set of beam resources may be a subset of the first beam resources.

[0094] For another example, the WTRU may use a configured BPT as an indicator to select from one or more of the configured or pre-configured AI / ML models and corresponding trained weights and / or coefficients to be used for inference based on one or more input beam resources and / or input BPTs. As such, the WTRU may use the configured or pre-configured AI / ML model that corresponds to the configured output BPT to perform inference and beam predictions. The WTRU may determine that, by using the AI / ML model that corresponds to the configured output BPT, the output of the inference may be one of the beam resources from the second set of beam resources.

[0095] A WTRU may use, receive, and / or be configured with one or more AI / ML models (e.g., for beam prediction), where each AI / ML model may be associated with a pair of input and output BPTs. The AI / ML models may be generalized models that can be used for inference at different WTRUs with different scenarios, different input beam indexes, different output beam indexes, and so forth.

[0096] The WTRU may store the received and / or configured AI / ML models. For example, the WTRU may maintain a lookup table of AI / ML models in its memory based on the pair of input and output BPTs containing the most recently used AI / ML models (AI / ML model cache). As new AI / ML models are received, they may be added to this lookup table. The oldest AI / ML models can be removed to free memory when more memory is needed at the WTRU. As such, when a new pair of input and output BPTs is received from the base station, the WTRU may first try to look up the associated AI / ML model from the cache. If it is available, the WTRU may move it to the top of most recently used AI / ML models. If it is not available, the WTRU may send a request to the base station to receive the AI / ML model.

[0097] The WTRU may determine and / or select a first configured or pre-configured AI / ML model for inference based on association of the first AI / ML model with a first indicated output BPT. The WTRU maydetermine and / or select a second configured or pre-configured AI / ML model for inference based on association of the second AI / ML model with a second indicated output BPT.

[0098] The WTRU may receive or be configured or pre-configured with the trained weights and / or coefficients for each AI / ML model. The WTRU may receive or be configured or pre-configured with different types of generalized input and output BPTs and the corresponding association with the AI / ML models. For example, a WTRU may receive the configurations on AI / ML models, input BPTs, and / or output BPTs during initial access to a cell and / or after connecting to a cell and in CONNECTED mode. The WTRU may receive the configurations via cell-specific and / or WTRU-specific signaling.

[0099] The WTRU may receive an indication (e.g., via RRC, MAC-CE, DCI from a base station) to use a configured or pre-configured AI / ML model (e.g., for beam prediction), where the indication may include one or more information on the BPTs and the corresponding beam indexes (e.g., beam locations with regards to the beam grids). The indication may include one or more of an input BPT, an output BPT, input BPT beam indexes and / or output BPT beam indexes. For example, the WTRU may receive an indication of an input BPT (e.g., input BPT 1 , input BPT 2). The WTRU may use the indicated input BPT to determine the subset for Set-B that needs to be used for beam measurements. For another example, the WTRU may receive an indication of an output BPT (e.g., output BPT 1 , output BPT 2). The WTRU may use the indicated output BPT to determine the AI / ML model to be used for inference (e.g., for beam prediction). For another example, the WTRU may receive the index numbers corresponding to the beam resources that the WTRU may use as the input to be used in the AIML model and for inference. For another example, the WTRU may receive the beam indexes corresponding to the beam resources that the WTRU may use along with the indicated output BPT. For example, the WTRU may determine one or more of the indicated output BPT beam indexes as the output of the AI / ML model and as the result of the inference based on the associated AI / ML model.

[0100] A base station, such as a gNB, may perform inference based on the information received from the base station or otherwise configured in the WTRU and the gNB-side trained model. Such a method may be referred to herein as a hybrid inference methodology.

[0101] FIG. 4 is a flow diagram 400 of an example method of beam prediction. The method may be implemented in a WTRU, which may be configured, as described above, with input beam patterns, output beam patterns, artificial intelligence / machine learning (AI / ML) models, and trained weights for each of the AI / ML models. Each of the input beam patterns may include beam indexes corresponding to a set of input beams. Each of the output beam patterns may include beam indexes corresponding to a set of output beams. Each of the AI / ML models may correspond to a respective one of the output beams. Additionally, in at least some embodiments, the WTRU may also be configured with a configuration for receiving, measuring, and reporting one or more beams (e.g., from a first Set B beams (e.g., CSI-RS resources)) based on a configured Set A beams. The WTRU may measure and report up to N beams from the received beams (e.g., highest measured reference signal received power (RSRP)).

[0102] In the example illustrated in FIG. 4, a WTRU may measure a signal quality of a subset of beams of each input beam pattern to identify at least one best input beam having the highest signal quality (402). The WTRU may report the at least one best input beam to a base station (404). The WTRU may receive, from the base station, an indication of one of the input beam patterns and an indication of one of the output beam patterns to use to predict a best output beam based on the report (406). The WTRU may predict the best output beam (408). The WTRU may predict the best output beam using the AI / ML model corresponding to the indicated one of the output beam patterns and the trained weights corresponding to the AI / ML model. The WTRU may report the predicted best beam to the base station (410).

[0103] When the WTRU performs inference in the manner described above (e.g., with respect to FIG. 4), it may be referred to as hybrid inference because some inference steps take place at the base station and some inference steps take place at the WTRU. For example, the WTRU may perform hybrid inference based on AI / ML systems and for beam prediction, as described above. For example, a first step of inference may be performed at the base station based on the received measurements from the WTRU on a first set of Set B beams. The base station may send the output results form the first step of inference to the WTRU, including one or more input BPTs, output BPTs, beam indexes, and so forth. The WTRU may use the received input BPTs to determine a second set of Set B beams. The WTRU may use the received output BPTs to determine an AI / ML model. The WTRU may perform a second step of inference based on the determined AI / ML model and the second set of Set B beams and predict the best beam accordingly.

[0104] In embodiments of hybrid inference, the base station may perform inference based on the information it receives from the WTRU and a base station side trained model. For example, the base station may predict the output best beam, determine the output beam pattern type (BPT), and determine the corresponding beam indexes. The predicted best beam lies in the determined output BPT. For another example, the base station may predict and / or determine the best input BPT that is associated with the predicted best beam and the determined output beam pattern. The base station may determine the output BPT and corresponding information for a given set of scenarios (e.g., characterized by the assistance information received from the WTRU). As such, the WTRU may use the determined input and output BPTs and corresponding beam indexes to perform inference and predict the best beam based on WTRU-side channel state information (CSI) measurements).

[0105] FIG. 5A is a system diagram of an example wireless network 500 configured to perform hybrid inference for beam management. In the example illustrated in FIG. 5A, the wireless network includes a first WTRU 514 and a second WTRU 516, both of which are in communication with a base station 518. In some embodiments, the base station may be a gNB. More specifically, the first WTRU 514 and the second WTRU 516 are configured to communicate with a radio access network (RAN) via the base station 518. In the example illustrated in FIG. 5A, the first WTRU 514 and the second WTRU 516 exchange messages 502, 504, 506 and 508, 510, 512, respectively, as described in more detail below with reference to an example hybrid inference procedure.

[0106] FIG. 5B is a diagram of example beam patterns 550 at the base station 518 of FIG. 5A. In the example illustrated in FIG. 5B, 64 beams are available at the base station 550 and are arranged into input beam patterns and output beam patterns. For example, input beam patterns 554 and 556 are shown in FIG. 5B. Input beam pattern 554 includes beams 1, 2, 3, 4, 17, 18, 19, 20, 33, 34, 35, 36, 49, 50, 51 and 52, and input beam pattern 556 includes beams 26, 27, 28, 42, 43, 44, 58, 59, and 60. For another example, output beam patterns 552 and 558 are shown in FIG. 5B. Output beam pattern 552 includes beams 2, 3, 18, 19, 34, 35, 50 and 51 , and output beam pattern 558 includes beams 43, 44, 59 and 60. Each of the beams has a corresponding unique beam index (not shown).

[0107] As explained above, each of the WTRUs 514 and 516 is configured with multiple input beam patterns and multiple output beam patterns and measures a subset of the beams in each of the input beam patterns to identify the best beam (although only two input beam patterns and two output beam patterns are illustrated in FIG. 5B). In the example illustrated in FIG. 5B, the measured subset of beams (or set B beams) includes beams 1 , 5, 9, 13, 18, 22, 26, 30, 35, 39, 43, 47, 52, 56, 60 and 64.

[0108] Referring back to FIG. 5A, the first WTRU 514 may measure the set B beams and send a report 502 to the base station 518 indicating the best measured beam. In the example illustrated in FIGs. 5A and 5B, the WTRU 514 measures the set B beams, identifies beam 18 as the best beam, and sends a report 502 to the base station 518 indicating that beam 18 is the best measured beam. Similarly, the second WTRU 516 may measure the set B beams and send a report 508 to the base station 518 indicating the best measured beam. Both WTRUs may also report one or more side / assistance information (e.g., WTRU location, WTRU direction, WTRU orientation, etc.).

[0109] The first WTRU 514 may receive a message 504 from the base station 518. The message 504 may include an indication to use output beam pattern 552 and beam indexes (2, 19, 34 and 51) for inference as well as an indication to use input beam pattern 554 with beam indexes (1 , 18, 35, 52) to use for inference. Similarly, the second WTRU 516 may receive a message 510 from the base station 518. The message 510 may include an indication to use output beam pattern 558 and beam indexes (44, 59) for inference as well as an indication to use input beam pattern 556 with beam indexes (26, 43, 60) for inference. The first and second WTRUs 514 and 516 may also receive one or more configurations in messages 504 and 510, as described in more detail above. This scheme may be advantageous over conventional methods in that there may no need for transmission of a beam shape model or detailed information, which may help the base station to determine the optimal model.

[0110] The first and second WTRUs 514 and 516 may perform the inference based on the received input and output BPTs, the configured or pre-configured trained weights and / or coefficients for the corresponding input and / or output BPTs, and measured parameters from the beams in the second set of Set B beams and predict the best beam based thereon. The first WTRU 514 may send a message 506 to the base station 518, which may include an indication of the first WTRU’s predicted best beam. Similarly, the WTRU 516 may senda message 512 to the base station 518, which may include an indication of the second WTRU’s predicted best beam. In the example illustrated in FIGs. 5A and 5B, the first WTRU 514 predicts beam 19 as the predicted best beam and indicates this to the base station 514 in the message 506. The second WTRU 516 predicts beam 44 as the predicted best beam and indicates this to the base station 514 in the message 512. In some embodiments, the base station 518 may determine that, based on the inference performed at the base station 518, the beam that was measured and reported as the best beam by the WTRU is actually the best beam for the WTRU. In such a case, the WTRU may receive an indication that no inference at the WTRU side is required (e.g., BPT 0) and that the measured beam is the best beam. The WTRU may receive DL signalling, or transmit UL signalling, using the reported best beam.

[0111] In some embodiments, a WTRU may receive one or more configurations for hybrid inference. The configurations may be used for receiving, measuring, and reporting one or more beams and may include, for example, AI / ML model related information, Set A beams (e.g., for base station and / or WTRU beam prediction), Set B beams, and reporting configuration.

[0112] AI / ML model related information may be or include at least one of a number of beams (e.g., for Set A and / or Set B), a number of beam patterns, beam pattern types (e.g., input and / or output), AI / ML models, type of AI / ML models, sizes of AI / ML model / weights, and / or trained AI / ML model / weights. The WTRU may receive one or more trained AI / ML model / weights, as mentioned above, or may determine trained AI / ML model / weights for beam prediction (e.g., based on base station configuration and / or indication).

[0113] Set B beams may be for WTRU measurement and, in some embodiments, may be accompanied by one or more CSI-RS resources and one or more parameters. Such parameters may include, for example, CSI- RS / SSB ID, CSI-RS / SSB periodicity and slot offset (e.g., for periodic and semi-persistent CSI-RS resources), CSI-RS / SSB resource mapping to define the number of CSI-RS ports, density, CDM-type, OFDM symbol, subcarrier occupancy, the bandwidth part to which the configured CSI-RS / SSB is allocated, reference to the TCI-State including the QCL source RS or RSs and the corresponding QCL type or types, CSI-RS / SSB transmission periodicity for periodic and semi-persistent CSI reports, CSI-RS / SSB transmission slot offset for periodic, semi-persistent and aperiodic CSI reports, CSI-RS / SSB transmission slot offset list for semi-persistent and aperiodic CSI reports, and / or time restrictions for channel and interference measurements.

[0114] The reporting configuration or configurations may be or include one or more of mode of operation, CSI reporting periodicity for periodic and semi-persistent CSI reports, CSI reporting slot offset for periodic, semi-persistent and aperiodic CSI reports, CSI reporting slot offset list for semi-persistent and aperiodic CSI reports, report frequency band configuration (wideband / sub-band CQI, PMI, and so forth), thresholds and modes of calculations for the reporting quantities (CRI, CQI, RSRP, SINR, LI, Rl, etc.), codebook configuration, group based beam reporting, CQI table, sub-band size, and / or non-PMI port indication. In some embodiments, the WTRU may receive a configuration of the mode of operation for hybrid inference and, in someembodiments, the mode of operation for hybrid inference may be used when CRI is configured as one of the reporting quantities.

[0115] In some embodiments, the WTRU may measure and report beam related information to a base station. The measurement may be based on the configured set B beams (e.g., by measuring the SSB / CSI-RS resources configured for set B beams). Based on the measurement, the WTRU may indicate up to N beams (e.g., via CRIs) from the measured beams (e.g., beams with highest measured RSRPs). In some embodiments, the WTRU may report one or more assistance information, which may be or include, for example, one or more of WTRU location, WTRU direction, or WTRU orientation.

[0116] In some embodiments, the base station may perform a first beam prediction based on the received information and a base station side trained model. For example, the base station may predict one or more best beams and / or best beam patterns for WTRU operation. The base station may determine one or more beam pattern types and / or best beam indexes based on the predicted one or more best beams and / or the predicted best beam patterns. For example, the base station may determine a best beam pattern and / or a best beam pattern type if the predicted best beam is included in a beam pattern type and / or a beam pattern. For example, the gNB may determine a best input and a best output BPT.

[0117] In some embodiments, the base station may determine one or more beam pattern types and / or corresponding information for a given set of scenarios. For example, the base station may determine one or more beam pattern types (e.g., input and output BPTs), beam patterns, and corresponding information for each assistance information received from the WTRU. Based on the determination, the WTRU may receive an indication of the one or more of determined beam pattern types (e.g., input and output BPTs), beam patterns and corresponding information. The indication may be per assistance information and / or a range of a set of assistance information.

[0118] For example, the base station may determine that the WTRU is in a first range if the WTRU’s location is between a first and a second location threshold (e.g., X11 < WTRU location <X12), if the WTRU’s direction is between a first and a second direction threshold (e.g., Y11 < WTRU direction < Y12), if the WTRU’s orientation is between a first and a second orientation threshold (Z11 <WTRU orientation <Z12), and so forth. Alternatively, the base station may determine that the WTRU is in a second range if the WTRU’s location is between a third and a fourth location threshold (e.g., X21 < WTRU location < X22), if the WTRU’s direction is between a third and a fourth direction threshold (e.g., Y21 < WTRU direction < Y22), if the WTRU’s orientation is between a third and a fourth orientation threshold (e.g., Z21 < WTRU orientation < Z22), and so forth. The WTRU may receive configuration information on one or more ranges and the threshold values for the WTRU’s location, direction, orientation, etc. from the base station via one or more of RRC, MAC CE and / or DCI.

[0119] FIG. 6 is a diagram of an example AI / ML model 602a, 602b at the base station side for hybrid inference. The example AI / ML model 602a, 602b, as illustrated in FIG. 6, may be used by the base station 518 (see FIG. 5A) to predict input and output BPTs, as described above with respect to FIGs. 5A and 5B.

[0120] In the example illustrated in FIG. 6, the AI / ML model 602a receives input 604a, and the AI / ML model 602b receives input 604b. The inputs 604a and 604b may be the best beam that was reported to the base station based on WTRU measurement. Referring back to the example illustrated in FIG. 5A, the input 604a is the best beam 18 reported to the base station 518 in the report 502 from the first WTRU 514, and the input 604b is the best beam 60 reported to the base station 518 in the report 508 from the second WTRU 516. While the first WTRU 514 only reported one beam, beam 18, as the best beam, and the second WTRU 516 only reported one beam, beam 60, as the best beam, in some embodiments, a WTRU may report the best one or more beams (e.g., with the highest RSRP) and the corresponding measured RSRP. In some embodiments, the input 604a, 604b may also include side information that the base station may have received from the first WTRU 514 and / or the second WTRU 516.

[0121] The base station may perform inference by using the best reported measured beam or beams as inputs 604a, 604b to the AI / ML model 604a, 604b. The outputs 606a and 608a from the AI / ML model 602a, and the outputs 604b and 608b from the AI / ML model 602b, may be or include the best predicted output BPT forthe corresponding WTRU and corresponding beam indexes as well as the best predicted input BPT and the corresponding beam indexes, which can all be used for inference at the WTRU. For example, referring back to FIG. 5A, the AI / ML model 602a provides as a first output 606a the input beam pattern 610 and beam indexes (1 , 18, 35, 52) and as a second output 608a the output beam pattern 612 and beam indexes (2, 19, 34, 51). The AI / ML model 602b provides as a first output 606b the output beam pattern 614 and beam indexes (26, 43, 60) and as a second output 608b the output beam pattern 616 and beam indexes (44, 59). The AI / ML models 602a and 602b can be different AI / ML models or the same AI / ML model, implemented in the base station 518.

[0122] FIG. 7 is a diagram of example AI / ML models 702a and 702b at the WTRU side for the first WTRU 514 and the second WTRU 516 of FIG. 5A for hybrid inference. The example AI / ML model 702a, 702b, as illustrated in FIG. 7, may be used by the first WTRU 514 and the second WTRU 516 (see FIG. 5A), respectively, to predict the overall best beam, as described above with respect to FIGs. 5A and 5B.

[0123] In the example illustrated in FIG. 7, the first WTRU 514 and the second WTRU 516 (see FIG. 5A) use the beam indexes the base station 518 indicated in messages 504 and 510, respectively, as inputs to the AI / ML models 702a and 702b, respectively. Recall that the base station 518 was able to determine those beam indexes using the AI / ML model 602a, 602b illustrated in FIG. 6. The first and second WTRUs 514 and 516 may select the AI / ML model to use for prediction from a larger group of AI / ML models configured in each of the WTRUs, respectively. The WTRUs may use the output beam pattern information received in the messages 504 and 506 from the base station 518 to select the AI / ML model to use for prediction. In some embodiments, each of the AI / ML models configured in the WTRU corresponds to one of the output beam patterns configured in the WTRU or a pair of one of the output beam patterns configured in the WTRU and one of the input beam patterns configured in the WTRU. The WTRU may select the configured AI / ML that corresponds to the received output beam pattern information or a pair of the received output beam pattern information and input beam pattern information. In the example illustrated in FIG. 7, the AI / ML model 702a corresponds to the pair of theinput BPT 710 and the output BPT 712 (which may correspond to input BPT 610 and output BPT 612 in FIG. 6). The AI / ML model 702b corresponds to the pair of the input BPT 716 and the output BPT 718 (which may correspond to input BPT 614 and output BPT 616 in FIG. 6).

[0124] In the example illustrated in FIG. 7, the AI / ML model 702a receives inputs 700a, 700b, 700c and 700d, and the AI / ML model 702b receives inputs 701a, 701b, and 701c. The inputs 700a, 700b, 700c and 700d to the AI / ML model 702a at the first WTRU 514 may be the beam indexes (1, 18, 35, 52), respectively, of the input beam pattern 710 indicated to the first WTRU 514 in the message 504. The inputs 701a, 701 b, and 701c to the AI / ML model 702b at the second WTRU 516 may be the beam indexes (26, 43, 60), respectively, of the input beam pattern 716 indicated to the first WTRU 514 in the message 510.

[0125] The first WTRU 514 may perform inference by using the beam indexes of the input beam pattern indicated by the base station as inputs 700a, 700b, and 700c, and 700d to the AI / ML model 702a. The second WTRU 516 may similarly perform inference using the beam indexes of the input beam pattern indicated by the base station as inputs 701a, 701b, and 701c to the AI / ML model 702b. The output 704 from the AI / ML model 702a, and the output 708 from the AI / ML model 702b, may be or include the beam index of the best overall beam for the particular WTRU to use, based on measurement at the WTRU, initial prediction at the base station, and second prediction at the WTRU. For example, referring back to FIG. 5A, the AI / ML model 702a at the first WTRU 514 provides beam index 19 as output 704, and the AI / ML model 702b at the second WTRU 516 provides beam index 44 as output 708. Each WTRU may then use the output beam index for transmission or reception, for example as described elsewhere herein.

[0126] In some embodiments, the WTRU may determine which AI / ML model to use and / or weights for the WTRU-side beam prediction. For example, the determination may be based on one or more of the received model ID, associated information, beam pattern type and / or beam pattern. The WTRU may use an AI / ML model and / or weights associated with the received model ID (e.g., indicated via one or more of RRC, MAC CE or DCI). The WTRU may use an AI / ML model and / or weights associated with the current WTRU location, the WTRU speed, the WTRU direction, the WTRU orientation, etc. (e.g., based on an indicated range). The WTRU may use an AI / ML model and / or weights associated with the received, configured and / or indicated input and output beam pattern type and / or beam pattern /

[0127] The WTRU may perform the WTRU-side second prediction based on one or more of measurement of the second set of Set B beams (e.g., measured qualities (e.g., RSRPs) of the second set), determined, configured, and / or indicated input and / or output beam pattern type, determined, configured, and / or indicated beam indexes, determined, configured, and / or indicated associated information, and / or determined, configured, and / or indicated AI / ML model and / or weights. For example, in the example illustrated in FIG. 7, as mentioned above, the first WTRU 514 predicts beam 19 as the best beam, and the second WTRU 516 predicts beam 44. The WTRU may report the predicted one or more best beams (e.g., via CRIs).

[0128] In some embodiments, the WTRU may receive an indication that the second inference and / or corresponding reporting is not needed. For example, if the WTRU’s reported best beam based on measuring the first of Set-B beam beams is the actual best beam (e.g., based on base station-side first inference), the WTRU may receive the indication. Based on the indication, the WTRU may deactivate one or more of determining / measuring the second of Set B beams, predicting / inferring one or more best beams from the second set, and / or indicating one or more best beams from the second set.

[0129] For example, the indication may be an explicit indication. For example, the WTRU may receive an indication with a first value (e.g., value zero) indicating that the second beam prediction is not required. In another example, the WTRU may receive an indication with a second value (e.g., value one) indicating that the second beam prediction is required. For another example, the WTRU may receive an indication of a first value (e.g., value zero and / or NACK) on the WTRU’s reported beam and an indication of a second value (e.g., value one or ACK) on the WTRU’s reported beam.

[0130] For another example, the indication may be an implicit indication. For example, the WTRU may receive the indication via beam pattern type and / or beam pattern. For example, input BPT 0 or output BPT 0 may indicate ACK on the WTRU’s reported beam and / or no support of the WTRU-side second beam prediction.

[0131] The WTRU may receive one or more DL channels / signals and / or transmit one or more UL channels / signals based on the reported one or more best beams.

[0132] Additionally or alternatively, after the WTRU performs the WTRU-side second inference and reports the predicted best beam, the WTRU may perform accuracy measurement. If the WTRU performs accuracy measurement based on the first predicted best beam, the WTRU may measure one or more accuracy parameters on one or more received channels / signals from the base station. The one or more accuracy parameters may be or include, for example, RSRP and / or hypothetical BLER. The WTRU may determine that the measured accuracy parameters are not within the acceptable range for the first predicted best beam, for example due to misdetection during inference and beam prediction, changes in the environment, or WTRU mobility. The WTRU may send an indication that the WTRU needs more information on the AI / ML model and request more information. The WTRU may indicate the invalid accuracy to the base station (e.g., flag indication) along with one or more measured parameters for the first predicted beam as assistance information. A WTRU may similarly perform accuracy measurement for the measured best beam during hybrid inference. If, for example, the WTRU performs accuracy measurement for the periodic Set B measurement, the WTRU may receive configurations (e.g., time period) to measure all beams in the Set B (e.g., long time period). The WTRU may measure and report up to N beams from the received beams (e.g., highest measured RSRP). The WTRU may receive an indication from the base station (e.g., based on inference at the base station) to schedule to receive further information.

[0133] The WTRU may receive information from the base station (e.g., in response to the WTRU’s request for additional information). In an example of a single beam transfer, the WTRU may receive an AI / ML modeltransfer for a single beam (e.g., transfer trained weight coefficients for beam #3 for the first WTRU). In an example of an updated model transfer, the WTRU may receive indications on receiving an updated AI / ML model for the indicated first BPT and the corresponding group-beam-based model (e.g., updated trained weight coefficients for BPT 2 for the first WTRU). In an example of a second BPT indication, the WTRU may receive indications to use a second BPT and corresponding configurations (e.g., the second BPT for the first WTRU may be BPT 3 for beam indexes (2, 3, 18, 19).

[0134] The WTRU may predict a second best predicted beam (e.g., beam 3) based on the received information and report the second best predicted beam to the base station. If the measured accuracy parameters are within the acceptable range, the WTRU may indicate that the WTRU has selected the predicted beam as the best beam. The WTRU may use the predicted best beam for DL reception (e.g., PDCCH, PDSCH, CSI-RS, etc.) and / or UL transmission (e.g., PRACH, PUCCH, SRS, etc.).

[0135] A WTRU may be be configured with and / or otherwise receive one or more first AI / ML models (e.g., input and / or output BPTs) and corresponding configurations (e.g., from a base station). The WTRU may predict a first beam resource (e.g., as the best beam) based on the first A / IML models and may report the predicted first beam resource (e.g., to a base station).

[0136] In some embodiments, the WTRU may measure one or more parameters on the received signals and / or channels based on the first beam resource. The WTRU may be configured with one or more UL transmission and DL reception based on the first beam resource. Also, the WTRU may be configured with one or more resource signals (RSs) based on the first beam resource. For example, the WTRU may measure RSRP, SINR, RSRQ, CQI, PDCCH hypothetical BLER, and so forth.

[0137] If the WTRU determines that one or more of the measured parameters are not within the acceptable range, the WTRU may send an indication that the WTRU needs more information on the AI / ML model and may request more information. For example, if one or more of the measured RSRP, SINR, RSRQ, CQI, etc. are lower than a corresponding threshold, the WTRU may determine that the measured parameters are not within the acceptable range. For another example, in case the measured hypothetical BLER is higher than a corresponding threshold, the WTRU may determine that the measured parameters are not within the acceptable range. The WTRU may report one or more of the measured parameters for the first beam as assistance information.

[0138] In some embodiments, a WTRU may be configured to measure one or more parameters based on a first set of Set-B beams, where the WTRU may determine if the measured parameters are within the acceptable range. For example, the WTRU may be configured to measure the first set of Set-B beams with a time period (e.g., a long time period). For example, the WTRU may measure the first set of Set-B beams and report up to N beam resources (e.g., with highest measured RSRP). The WTRU may receive an indication from the base station to schedule to receive further information.

[0139] In some embodiments, the WTRU may receive further information with regard to the AI / ML model. In an example of single beam transfer, the WTRU may receive indications and / or scheduling information to receive the AI / ML model transfer for a single beam resource and / or beam pattern. In an example of updated model transfer, for example, the WTRU may receive indications and / or scheduling information for receiving an updated AI / ML model for the indicated AI / ML model (e.g., updated trained weight coefficients). In an example of second BPT indication, for example, the WTRU may receive indications to use a second AI / ML model. The indications may include corresponding configurations.

[0140] The WTRU may predict a second best predicted beam based on the received information and the updated AI / ML model. The WTRU may report the second predicted beam to the base station. The WTRU may further measure one or more parameters based on the second beam resource. In case the measured accuracy parameters are within the acceptable range, the WTRU may indicate that the WTRU has selected the predicted beam as the best beam. The WTRU may use the predicted best beam for DL reception (e.g., PDCCH, PDSCH, CSI-RS, etc.) and / or UL transmission (e.g., PRACH, PUCCH, SRS, etc.).

[0141] In some embodiments, a WTRU receives configuration information indicating one or more BPTs to be used for inference at the WTRU side. The WTRU may receive the configuration information on one or more subsets of Set B beams to measure per each BPT. Additionally or alternatively, the WTRU may receive an indication or configuration to perform inference and report the predicted beam per each configured BPT, where the WTRU receives an indication that the purpose of the configured inference and beam reporting is for base station training. Alternatively or additionally, the WTRU may perform inference based on the configured subsets of measured Set B beams per each configured BPT. Additionally or alternatively, the WTRU my report the predicted beams per each configured BPT per each configured subset of Set B beams, in addition to one or more assistance information (UE orientation, location, etc.). The WTRU may determine that the priority for the transmission of the report for the purpose of base station training is a low priority UL compared to other configured and / or scheduled UL or DL occasions. The priority may be a function of the number of BPTs or the categories of BPTs.

[0142] A base station may require training to enable hybrid inference. For example, the base station may require training to enable the base station to predict, select, and / or indicate the best A / IML model and corresponding configurations for a given set of scenarios based on the reported information from the WTRU. This may be part of a wider data collection process by the network where different base stations / TRPs may collect data from one or more WTRUs for one or more scenarios to build a database to allow accurate prediction of BPT to the WTRU for hybrid inference.

[0143] A WTRU may be configured with, or otherwise receive, configurations as part of the training process. The configurations may be used for receiving, measuring, predicting, and reporting one or more beam resources. For example, one or more of the following configurations may be used: BPTs, best serving beam or beams (e.g., beam index), RSRP / RSRQ of best beam or beams, RSRP / RSRQ differential of best beam orbeams, AoA / AoD of best beam or beams, beams with RSRP / RSRQ above a threshold, worst beam or beams (which may correspond to a blockage), RSRP / RSRQ of the worst beam or beams, RSRP / RSRQ differential of worst beam or beams, beams with RSRP / RSRQ below a threshold, blockage detected by the WTRU (e.g., via sudden drop in L1-RSRP, path loss measurements, computed CSI parameters (e.g., low CQI) etc.), information on the blockage to assist the NW in building the database (e.g., blockage duration, location, impacted set of beams, etc.), CSI parameters (e.g., CQI, PMI, Rl) and / or any change thereof, WTRU location / position / coordi nates, WTRU relative position, mobility status, LOS / NLOS / pathloss conditions, and / or time stamps. Any of the aforementioned best or worst beam may refer to any of a transmit beam or receive beam.

[0144] The WTRU may be, for example, configured with one or more input and / or output BPTs. The WTRU may perform inference based on the measured beams from the subset of Set-B beams that the WTRU may determine based on each of the configured input BPTs. The WTRU may select the AI / ML model to be used for inference based on the configured output BPTs. In other words, the WTRU may use the configured input BPTs one by one along with the configured output BPTs to perform inference and predict the best beam. As such, the WTRU may determine one or more pairs of the input and output BPTs that result in predicting the best beam, and the WTRU may report the pairs to the base station.

[0145] The WTRU may, for example, report to the base station the best beam and the BPT that the WTRU used for predicting the best beam. Such information may assist the base station in configuring the constituent beams that form part of each BPT. The WTRU may, for example, report to the base station the RSRP and / or RSRQ of the best predicted beam or beams for each configured input and / or output BPT.

[0146] The WTRU may report, for example, the differential RSRP and / or RSRQ for one or more predicted beams with reference to the best predicted beams, for each configured input and / or output BPT. The WTRU may report the beam indexes for the reported beams. In another example, the WTRU may report the changes in the measured RSRP and / or RSRQ for the best beam based on different scenarios of the WTRU’s location, orientation, etc. In another example, the WTRU may report the changes in the measured RSRP and / or RSRQ for the best beam based on inference based on different input and / or output BPTs.

[0147] The WTRU may, for example, report the AOA and / or AOD of the best predicted beams for each configured input and / or output BPT, for example based on different scenarios of WTRU’s location, orientation, etc. The WTRU may, for example, report one or more beam resources for which the predicted RSRP and / or RSRQ are above a threshold for each configured input and / or output BPT, for example based on different scenarios of the WTRU’s location, orientation, etc. The WTRU may, for example, report the worst predicted serving beam for each configured input and / or output BPT. Reporting such information may assist the base station in configuring the constituent beams that form part of each BPT, for example, by excluding the worst serving beams.

[0148] The WTRU may, for example, report the RSRP and / or RSRQ of the worst predicted beams for each configured input and / or output BPT. The WTRU may, for example, report the differential RSRP and / or RSRQ of the worst predicted beams for each configured input and / or output BPT. In an example, the WTRU may report the differential RSRP and / or RSRQ of the worst predicted beams for each configured input and / or output BPT based on the drop in RSRP.

[0149] The WTRU may, for example, report the predicted beams with the measured RSRP and / or RSRQ below a threshold for each configured input and / or output BPT. The WTRU may, for example, report a detected blockage or predicted blockage for each configured input and / or output BPT.

[0150] A WTRU reporting of the best input and / or output BPTs and the WTRU location may, for example, assist the NW in configuring a fingerprint of the best BPT per location. For example, the WTRU may report its location, orientation, mobility status, etc. Such information, along with the reported best beam, RSRP, RSRQ, and / or the best input and output BPTs, may allow the NW to build a fingerprinting map of signal strength in different locations and configure the BPTs accordingly (e.g., number of beams in each output BPT, number of Set-B beams in each input BPT, etc.).

[0151] A WTRU relative position may indicate, for example, the WTRU relative position with respect to a particular TRP and / or base station. The WTRU may send an SRS to the TRP and / or base station, which may evaluate parameters such as propagation delay, path loss, signal strength etc. to gauge the relative location and / or radio conditions of the WTRU (e.g., WTRU relative position to another WTRU). Mobility status may refer to WTRU speed and WTRU direction of motion.

[0152] The WTRU may be configured to report time stamps corresponding to measurements for any of the aforementioned parameters. In some cases, the WTRU may be configured to report the data as soon as the measurement is performed. In other cases, since this data is for the purpose of base station training, the WTRU may be configured to collect the data over time and report the data at once (e.g., via a data collection framework like the Minimum Drive Test (MDT)), in which case, the timestamps may assist the NW in building an accurate fingerprint of the best BPT per location.

[0153] A WTRU may receive configuration information indicating one or more input and / or output BPTs to be used for inference at the WTRU side. In some embodiments, the WTRU may receive (e.g., from the network) an indication or configuration to perform inference and report the predicted beam per each configured input and / output BPT. The WTRU may receive (e.g., from the NW) a list of configured input and / output BPTs and report to the network one or more of the predicted best beams and the one or more associated input and / output BPTs that were used to predict the best beam.

[0154] For example, the WTRU may perform inference based on the configured subsets of measured Set B beams per each configured input BPT. The WTRU may report the predicted beams per each configured output BPT per each configured subset of Set B beams, in addition to one or more assistance information (WTRU orientation, location, etc. as listed above).

[0155] For another example, the WTRU may report any one or more of the above data and / or assistance information via any one or more of the following frameworks: logged MDT, immediate MDT, RRC (e.g., RRC measurement reports, UE assistance information), early idle and / or inactive measurement reports, beam reporting framework, CSI reporting framework, LPP (LTE Positioning Protocol) for location / positioning information, etc.

[0156] For another example, the WTRU may receive an indication that the purpose of the measurement and reporting is for model training at the network. For example, the WTRU may receive that indication following reception of a list of configured BPTs from the NW. For example, the WTRU may receive that indication following reception of resources to perform measurements (e.g., CSI-RS resources).

[0157] With the knowledge that a measurement may be for base station training, a WTRU may determine that the priority for the transmission of the report for the purpose of base station training is a low priority UL occasion compared to other configured and / or scheduled UL or DL occasions. In one example, the priority may be a function of the number of BPTs or the categories of BPTs.

[0158] For example, the WTRU may be configured with periodicities for when to make measurements. In another example, it may be event-triggered. For example, reception of a configuration of CSI-RS resources and / or resource sets and CSI reporting for training AI / ML model at base station may trigger the WTRU to perform measurements.

[0159] For another example, the WTRU may only perform measurements of the aforementioned parameters in a connected state and report them back to the network (e.g., via immediate MDT, CSI reporting framework, beam reporting framework, etc.). In another example, the WTRU may perform measurements in an idle and / or inactive state and use a different framework for reporting a bulk of data at once (e.g., via logged MDT framework).

[0160] In one example, the WTRU may assist the base station training via traditional methods of measuring the best beam (e.g., beam with highest RSRP) and reporting it to the NW, possibly with other information (e.g., WTRU location). For example, the WTRU may receive a configuration of CSI-RS resources and / or resource sets and CSI reporting fortraining AI / ML model for hybrid inference at the base station. The WTRU may perform periodic measurements to identify the best serving beam (e.g., beam with highest RSRP) and report (e.g., up to four) best beams to the base station. The WTRU may also send to the network its location with every report of the best beam(s) to allow the network to build its database of candidate BPTs per each location and their constituent beams.

[0161] In another example, the WTRU may assist the base station training via AI / ML model at the WTRU. For example, the AI / ML model at the WTRU may output the best BPT out of the preconfigured set of BPTs from the NW in different scenarios (e.g., different WTRU location, speed, LOS / NLOS conditions), which the WTRU may report to the NW to assist in NW training.

[0162] Any of the examples described above, such a data collection process to assist model training at the network, may take place before the corresponding model is deployed for inference. Some fine-tuning and / or retraining may also be performed periodically based on addition of new scenarios and / or update of existing scenarios.

[0163] To maintain the accuracy of AI / ML-based beam predictions, it may be important to monitor the accuracy of beam predictions on a regular basis and to improve the prediction accuracy or take alternative measures when required. One factor that can contribute to the loss of beam prediction accuracy is using an outdated AI / ML model and / or set of inputs (e.g., the AI / ML model and selected input fails to capture / reflect the current behavior of the beams). An AI / ML model can be outdated due to many factors including changes in the environment (e.g., movement of large objects in the environment or a WTRU previously was outdoors that moved indoors), WTRU movement (e.g., changes in the speed and direction of movement), WTRU rotation, and so forth.

[0164] For example, consider a situation where an AI / ML model and set of input for the model (e.g., set of beams) was selected when the WTRU was located indoors. However, over time the WTRU has moved and currently is located in an outdoor environment. In such a situation, the use of the same AI / ML model and set of inputs to the model, which was selected assuming the indoor propagation environment, may fail to provide accurate beam predictions as the environment has changed. To compensate or manage such loss of beam prediction accuracy, appropriate steps may need to be taken (e.g., selecting an alternative AI / ML model, selecting an alternative set of input beams, and so forth).

[0165] Accordingly, in embodiments described herein, after the WTRU performs inference and predicts and reports a predicted best beam to the base station, using a hybrid inference method as described, for example, above, the WTRU may receive configuration information on one or more second candidate BPTs. For example, with reference to FIGs. 5A and 5B, the first WTRU 514 may receive an indication to use a third BPT (not labeled in FIG. 5B) for beam indexes (3, 4, 19, and 20), and / or to use a fourth BPT for beam indexes (3 and 18), as the candidate BPTs. The WTRU may perform inference and predict one or more second beam based on the received candidate second BPT or BPTs.

[0166] The WTRU may compare one or more measured and / or predicted accuracy parameters (e.g., RSRP, hypothetical BLER, etc.) of the first beam with the predicted accuracy parameters of the second predicted beam or beams. The WTRU may receive channels / signals from the base station based on the first (e.g., active) beam (e.g., Beam 19), where the WTRU measures one or more accuracy parameters. Alternatively or additionally, the WTRU may predict one or more accuracy parameters for the first beam.

[0167] The WTRU may determine that one or more of the predicted accuracy parameters corresponding to at least one of the second predicted beams is better than the measured or predicted accuracy parameters of the first beam (e.g., Beam 3). For example, the WTRU may determine that the difference between the predicted RSRP of the second beam compared with the measured / predicted RSRP of the first beam is higher than anRSRP threshold. For another example, the WTRU may determine that the difference between the predicted hypothetical BLER of the second beam compared with the measured / predicted hypothetical BLER of the first beam is higher than a BLER threshold. The WTRU may send a request to the base station to switch to the second BPT for the further inference and predictions. The WTRU may send a request to the base station to switch to the second predicted beam. The WTRU may use the second predicted beam for DL reception (e.g., PDCCH, PDSCH, CSI-RS, etc.) and / or UL transmission (e.g., PRACH, PUCCH, SRS, etc.).

[0168] A WTRU may predict and report one or more first beams (e.g., the beam with the highest predicted RSRP) based on a hybrid inference method as described above, for example. In an example configuration, the WTRU may receive a first input and a first output BPT and the corresponding configuration (e.g., beam indexes) for beam prediction. The WTRU may perform beam inference and predict the first one or more beams (e.g., the beam with the highest predicted RSRP), based on a received first input BPT and a received first output BPT and corresponding configuration. The WTRU may report the predicted first beam to the base station (e.g., via UCI, MAC-CE, and / or RRC indications).

[0169] Referring again to FIGs. 5A and 5B, the first WTRU 514 may receive an indication to use output beam pattern 552 with beam indices (2, 19, 34, and 51) and input beam pattern 554 with beam indexes (1 , 18, 35, and 52). As such, the WTRU may predict and report beam 19 as the first predicted beam (e.g., beam with the highest predicted RSRP).

[0170] The WTRU may receive configuration information for one or more second candidate input BPT and one or more second output BPT that are different from the first configured input and output BPTs. For example, in the example configuration depicted in FIG. 5B, the first WTRU 514A may receive an indication to use output BPT3 (not labeled in FIG. 5B) for beam indices (3, 4,19, and 20) as the second candidate output BPT and input BPT4 (not labeled in FIG. 5B) for beam indexes (5, 22, 18, and 35) as the second candidate input BPT. In another example, the first WTRU 514 may receive indications to use the output BPT4 (not labeled in FIG. 5B) for beam indexes (3 and 18) as the second candidate output BPT and input BPT2 (not labeled in FIG. 5B) for beam indexes (1,18,35) as the second candidate input BPT.

[0171] The WTRU may use one or more of the configured second candidate input and / or output BPTs to perform beam inference and predict one or more second beams. For example, the first WTRU 5A may predict Beam 3 as the best beam based on the configured second candidate input and / or output BPTs. The first WTRU 514 may compare one or more measured and / or predicted beam quality parameters (e.g., RSRP, hypothetical BLER, RSRQ, SINR) of the first or active beam with the predicted beam quality parameters of the one or more second beams predicted using one or more second candidate BPTs.

[0172] The WTRU may use one or more received channels (e.g., PDCCH) or signals (e.g., CSI-RS) via the first beam to measure, determine or estimate one or more channel / signal quality parameters associated with the first beam. For example, the first WTRU 514 that has selected and / or predicted beam 19 as the first and / or active beam may receive one or more channels and / or signals from the base station using beam 19. The firstWTRU 514 may use the received channels and / or signals received via beam 19 to determine channel / signal quality parameters. The first WTRU 514 may predict one or more channel quality parameters for the first or active beam.

[0173] The WTRU may determine that one or more of the measured and / or predicted beam quality parameters associated with at least one of the second predicted beams is better than the measured or predicted beam quality parameters of the first or active beam. For example, the WTRU may determine that the difference between the predicted RSRP of one of the second beams and the measured or predicted RSRP of the first beam is higher than a configured and / or pre-configured RSRP threshold. For example, the WTRU may receive or be configured and / or pre-configured with the corresponding threshold from a base station, for example via RRC signaling, MAC-CE, and / or DCI indication. For another example, the WTRU may determine that the difference between the predicted hypothetical BLER of a channel (e.g., PDCCH) associated with one of the second beams compared with the measured or predicted hypothetical BLER of the first beam is higher than a configured or pre-configured BLER threshold.

[0174] The WTRU may send a report to the base station indicating the predicted second beam and the predicted one or more beam quality parameters. The WTRU may send the report and / or the indication via UCI, MAC-CE, and / or RRC signaling. For example, the report that the WTRU may send may include a request to switch to the second input and / or output BPT for the further inference and predictions.

[0175] The WTRU may monitor and receive confirmation from the base station (e.g., via a DCI, MAC-CE indication, RRC signaling) granting the permission to switch to the second input and / or output BPT for the further inference and predictions. The WTRU may start using the second input and / or output BPT for the further inference and predictions after a configured and / or pre-configured BPT switching time (e.g., configured and / or pre-configured via RRC signaling, MAC-CE indication or DCI indication).

[0176] The report and / or indication that the WTRU may send may include a request to switch to the second predicted beam. The WTRU may send a request to the base station to switch to or grant permission to switch to the second predicted beam for DL reception (e.g., PDCCH, PDSCH, CSI-RS, etc.) and / or UL transmission (e.g., PRACH, PUCCH, SRS, etc.). The WTRU may monitor and receive a confirmation indication to use the second beam (e.g., from the gNB, e.g., in a configured and / or pre-configured monitoring window). For example, the WTRU may monitor for a confirmation indication on a PDCCH (e.g., a PDCCH received via a configured or pre-configured search space / CORESET) or MAC-CE indication or RRC signaling.

[0177] The WTRU may start using the predicted second beam for DL reception (e.g., PDCCH, PDSCH, CSI-RS, etc.) and / or UL transmission (e.g., PRACH, PUCCH, SRS, etc.) after a configured and / or preconfigured beam application time.

[0178] As mentioned above, the WTRU (e.g., the first WTRU 514 or the second WTRU 516 illustrated in FIG. 5A) may be configured with the information regarding AI / ML models and related information in any of a number of different ways. In a specific example, the WTRU may be configured for and / or capable of hybrid-inference for beam management in AI / ML systems. The WTRU may receive configuration information on one or more group radio network temporary identifiers (G-RNTIs) to monitor and receive DCIs scheduling the group- common transfer of the beam-group-based trained weights and / or coefficients corresponding to one or more BPTs. For example, the WTRU may have connected to the cell and may need to receive all the models that are used in the cell. The base station may change the models every other hour (due to security issues) and indicate the new models and / or BPTs to the WTRUs.

[0179] The WTRU may monitor to detect DCI with CRC scrambled using a G-RNTI based on one or more of: the WTRU receiving a configuration (e.g., for hybrid inference) that requires the trained weights and / or coefficients of a first BPT where the WTRU determines that the WTRU does not have corresponding trained weights and / or coefficients; the WTRU receiving an indication (e.g., paging, group-common DCI, etc.) that the trained weights and / or coefficients corresponding to the first BPT are updated at the base station and that the WTRU needs to receive the group-common transfer of the coefficients; the WTRU determining that the accuracy parameters of the beam prediction based on the configured first BPT is not valid and / or acceptable and / or the configured BPT has expired; and / or the WTRU determining that the accuracy parameters of the beam prediction based on the configured first BPT is not valid and / or acceptable.

[0180] When the WTRU receives a configuration for hybrid inference that requires the trained weights and / or coefficients of a first BPT, and where the WTRU determines that the WTRU does not have corresponding trained weights and / or coefficients, the WTRU may select the first G-RNTI that is associated with the first BPT. The WTRU may monitor to detect the DCI with CRC scrambled by the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first BPT.

[0181] When the WTRU receives an indication (e.g., paging, group-common DCI, etc.) that the trained weights and / or coefficients corresponding to the first BPT are updated at the gNB and that the WTR needs to receive the group-common transfer of the coefficients, the WTRU may select the first G-RNTI that is associated with the first BPT. The WTRU may monitor to detect the DCI with CRC scrambled by the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first BPT.

[0182] When the WTRU determines that the accuracy parameters of the beam prediction based on the configured first BPT are not valid and / or acceptable and / or the configured BPT has expired, the WTRU may monitor to detect the DCI with CRC scrambled using the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first BPT. When the WTRU determines that the accuracy parameters of the beam prediction based on the configured first BPT is not valid and / or acceptable, the WTRU may determine, request, or recommend switching to a second BPT. The WTRU may select the second G-RNTI that is associated with the second BPT. The WTRU may monitor to detect the DCI with CRC scrambled using the second G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the second BPT.

[0183] The WTRU may use the received trained weights and / or coefficients corresponding to the configured BPT to perform inference and predict the best beam. The WTRU may report the predicted best beam and receive and / or transmit DL and / or UL according to the predicted best beam.

[0184] A WTRU may receive configuration information on one or more group indications and / or identifiers to monitor and / or receive DCIs scheduling one or more group-common transfer of the beam-group-based trained weights and / or coefficients corresponding to one or more AI / ML system models. For example, the WTRU may receive one or more group G-RNTI to receive group-common DCI signaling. The WTRU may be configured with a first G-RNTI that is associated with a first AI / ML system model, a second G-RNTI that is associated with a second AI / ML system model, and so forth. For example, the WTRU may be configured with separate and different G-RNTIs for different AI / ML system models. For example, the WTRU may receive the configuration on the G-RNTIs via SIB, RRC, MAC-CE, or DCI during initial access to a cell and / or after connecting to a cell and in CONNECTED mode.

[0185] Upon reception of a DCI for which the CRC is scrambled using a first G-RNTI, the WTRU may receive a configured and / or dynamic grant via the DCI indicating the time and / or frequency resources for a DL grant. The WTRU may use the configured time and frequency resources to receive, transfer, and / or download (e.g., from a gNB) the information including trained weights and / or coefficients corresponding to a first AI / ML system model that is associated with the indicated first G-RNTI. The WTRU may determine to receive, download, and / or transfer the information if, for example, the WTRU has recently connected to the cell and needs to receive all the AI / ML models that are used in this cell. Alternatively, the WTRU may receive an indication (e.g., from the base station) that the AI / ML models are updated (e.g., due to the base station updating the models based on a recent re-training, or due to base station changing the models every other hour, for example due to security issues). As such, the WTRU may determine to receive, download, and / or transfer the information.

[0186] In some embodiments, the WTRU may receive one or more configuration information, for an operation (e.g., for hybrid inference) based on one or more AI / ML models. For example, the WTRU may receive configurations to perform inference based on a first AI / ML model. The WTRU may determine that it does not have corresponding trained weights, coefficients, and / or AI / ML models (e.g., in WTRU’s memory or storage). As such, the WTRU may select the first G-RNTI that is associated with the first AI / ML model. The WTRU may monitor to detect the DCI with CRC scrambled using the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first AI / ML model.

[0187] In some embodiments, the WTRU may receive one or more indications where the WTRU may determine that a first AI / ML model is updated. For example, the WTRU may receive one or more indications via DCI, MAC-CE, and / or RRC from a base station indicating that a first system model is updated at the base station side, for example due to trainings at the base station. As such, the WTRU may select the first G-RNTI that is associated with the first AI / ML model. The WTRU may monitor to detect the DCI with CRC scrambledusing the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first AI / ML model.

[0188] In some embodiments, a WTRU may determine that one or more of the configured input and / or output BPT has expired. For example, the WTRU may determine that a corresponding timer or counter has expired. For another example, the WTRU may determine the expiry of the BPTs based on one or more events, such as beam failure detection, or multiple consecutive retransmission requests from the base station, or multiple consecutive NACKs, and so forth. As such, the WTRU may monitor to detect the DCI with CRC scrambled using the first G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the first BPT.

[0189] In some embodiments, a WTRU may determine that the accuracy parameters for the inference based on a first AI / ML model are not in the acceptable range. For example, the WTRU may determine that one or more measured and / or predicted parameters based on received signals and / or channels based on a predicted first beam are not in acceptable range. For example, the WTRU may determine that the measured RSRP, RSRQ, SINR, and so forth, that are measured based on an RS according to the predicted first beam are lower than a corresponding configured threshold, where the threshold may be configured via RRC, MAC- CE, and / or DCI. For another example, the WTRU may determine that the measured hypothetical BLER based on a PDCCH received based on the predicted first beam is higher than a corresponding configured threshold, where the threshold may be configured via RRC, MAC-CE, and / or DCI.

[0190] The WTRU may determine and send a request to the base station to use a second AI / ML model for inference (e.g., as described above). Upon receiving the confirmation from the base station to use the second AI / ML model, the WTRU may select the second G-RNTI that is associated with the second AI / ML model. The WTRU may monitor to detect the DCI with CRC scrambled using the second G-RNTI to receive the scheduled resources to receive the trained weights and / or coefficients corresponding to the second AI / ML model. For example, the WTRU may use the received, transferred, and / or downloaded AI / ML model to perform inference and predict a best beam. The WTRU may report the predicted best beam and receive DL signaling and / or transmit UL signaling according to the predicted best beam.

[0191] In some embodiments, a WTRU may receive configurations on one or more generalized input and / or output BPTs (e.g., via RRC), which may be used to indicate small and beam-group-based AI / ML models. The configurations may include one or more of BPT configurations and / or BPT indications. A WTRU may receive one or more configuration information regarding one or more input and / or output BPTs, including, for example, one or more of BPT category, BPT ID, number of beams in the BPT, BPT grid structure, focus beams in the BPT grid, beam indexes in the BPT, trained weights and / or coefficients for output BPTs, and so forth. A WTRU may receive one or more indication to use one or more input and / or output BPTs (e.g., for hybrid inference at the WTRU), including the BPT ID and the corresponding beam indexes. The WTRU may determine one or more of an input BPT ID and / or an output BPT ID based on one or more of a received input BPT ID, a receivedoutput BPD ID, an offset value, a TCI state, an absolute value, and / or generic default numbering. The WTRU may perform, determine and / or report beam measurements and / or beam IDs based on the determined input BPT and output BPT.

[0192] In some embodiments, a WTRU may be configured with and / or receive a configuration and / or indication (e.g., via RRC, MAC-CE, and / or DCI) on one or more input and / or output BPT. For example, the WTRU may receive the configurations on AI / ML models, input BPTs, and / or output BPTs during initial access to a cell and / or after connecting to a cell and in CONNECTED mode. The WTRU may receive the configurations via cell-specific and / or WTRU-specific signaling. The configuration on the input and / or output BPTs may include one or more of BPT category, BPT ID, number of beams in the BPT, BPT grid structure, focus beams in the BPT grid, and / or beam indexed in the BPT.

[0193] A WTRU may receive indications on whether a configured BPT is an input BPT or output BPT. A WTRU may receive an index or an identification that each BPT is associated with. A WTRU may receive input BPT 1 , BPT 2, and so forth, and / or output BPT1 , BPT2, and so forth. The WTRU may receive configurations or be configured with the number of beams that are considered in each input and / or output BPT. For example, the number of the beams may be 16, 9, 15, and 15 for input BPT 202, input BPT 204, input BPT 206, and input BPT 208, respectively, in the example illustrated in FIG. 2. For another example, the number of beams may be 8, 8, 4, and 4 for output BPT 302, output BPT 304, output BPT 306, and output BPT 308, respectively, in the example illustrated in FIG. 3.

[0194] The WTRU may be configured with the structure and the dimension of the grid that is used for each input and / or output BPT. For example, the BPT may be based on a square grid, a rectangular grid, a circular grid, a hexagonal grid, and so forth. For example, the input BPT 202 in FIG. 2 has a square grid structure with 4x4 dimensions. For another example, the output BPT 304 in FIG. 3 has a rectangular grid structure with 4x2 dimensions.

[0195] The WTRU may receive configurations or otherwise be configured with focus beams in for each configured input and / or output BPT. For example, the focus beams in an input BPT may be associated with a subset of Set-B beams that are included in the corresponding input BPT. For example, the green beams in input BPT 206 in FIG. 2 may be the focus beams. For another example, the focus beams in an output BPT may be associated with the beams for which the trained weights and / or coefficients are provided as part of the BPT definition. For example, beams 1 f, 4f, 5f and 8f in output BPT 304 in FIG. 3 may be the focus beams.

[0196] The WTRU may determine and / or be configured with numbering for the beam indexes based on a numbering procedure, which may be a default numbering procedure. For example, the WTRU may consider numbering the beams within the configured BPT grid structure, starting from an initial value (e.g., zero) up to the total number of the beams in the BPT. The indication of focus beams, for example, may therefore be based on the numbering procedure. For example, the input BPT 204 in FIG. 2 may have 9 beams that are located in a square grid structure with 3x3 dimensions. As such, the WTRU may determine or be configured with beamnumbering, such as {0, 1 , 2, 8}. Therefore, the WTRU may determine or be configured such that, for inputBPT 204, the focus beams are beams {0, 4, 8}.

[0197] The WTRU may receive and / or otherwise be configured with trained weights and / or coefficients for the focus beams in each output BPT. For example, the WTRU may use the configured trained weights and / or coefficients as the model for inference at the WTRU side.

[0198] A WTRU may receive indication information to use one or more input and / or output BPTs and / or BPT pairs for inference. For example, the BPT pairs may be an indication to a pairing of an input and an output BPT, where the WTRU may determine the indicated input and output BPTs by receiving the BPT pair indication. For another example, the WTRU may receive the indication information from a base station via DCI, MAC-CE, and / or RRC. The indication information may include an indication of the BPT IDs to be used. The indication information may also include the beam indexes to be considered for the input and output BPTs for the purpose of inference. The WTRU may receive the indication of the beam indexes to be used along with one or more input and / or output BPTs based on one or more of absolute values, offset values, generic default numbering, and / or TCI states.

[0199] A WTRU may receive an indication of absolute beam IDs for one or more BPTs. For example, the WTRU may receive an indication of absolute Beam IDs to be used along with an indicated input and output BPT. Referring back to FIG. 7, for example, a first WTRU (e.g., first WTRU 514 in FIG. 5A) may be configured with input BPT 202, where the beam indexes to be used along with the configured BPT 202 may be indicated based on absolute beam indexes that are considered within the network (e.g., beam indexes {1 , 18, 35, and 52}). For another example, the first WTRU (e.g., the WTRU 514 in FIG. 5A) may be configured with output BPT 304, where the beam indexes to be used along with the configured BPT 304 may be indicated based on absolute beam indexes that are considered within the network (e.g., beam indexes {2, 19, 34, and 51}).

[0200] A WTRU may receive an indication of a first and / or anchor absolute beam ID and one or more offsets to the first beam ID to determine other Beam IDs to be used along with an indicated input and / or output BPT. For example, a first WTRU (e.g., the first WTRU 514 in FIG. 5A) may be configured with input BPT 202, where the beam indexes to be used along with the configured BPT 202 may be indicated based on an absolute beam index for the first and / or anchor beam (e.g., Beam 1a) and one or more offset values where the offset values are each indicated based on the previous beam index (e.g., offset values {17, 17, 17}). As such, the WTRU may use the absolute beam index for the first and / or anchor beam and determine the beam index for the other beam indexes accordingly (e.g., Beam indexes {1 , 18, 35, and 52}).

[0201] A WTRU may receive and / or otherwise be configured with one or more configurations to use for determining the indicated input and output BPT beam indexes based on generic and / or default numbering of the beam indexes in the BPT. Referring back to FIGs. 2 and 3, for example, the WTRU may receive and / or be configured with an indication to use input BPT 202 of FIG. 2 along with output BPT 304 of FIG. 3. The WTRU may use default or configured and / or pre-configured beam indexes {0, 1 , 2, ..., 15} for the beam indexes inthe input BPT 202. As such, the WTRU may use beam indexes { 0, 5, 10, 15} for focus beam indexes in the input BPT 202.

[0202] FIG. 8A is a diagram of an example of an indication of beam indexes based on generic default numbering. FIG. 8B is a diagram of another example of an indication of beam indexes based on generic default numbering.

[0203] A WTRU may be configured or determine the beam indexes and the focus beam indexes corresponding to the configured and / or indicated output BPT based on the indicated beam indexes for the input BPT. The WTRU may determine, be configured with, or receive, an indication that the first and / or anchor focus beam for the output BPT is based on the indicated beam indexes for the input BPT. That is, for example, the WTRU may receive indications that the first and / or anchor focus beam for the indicated output BPT 2 is Beam # 1 based on the indicated beam indexes for the input BPT. As such, the WTRU may determine the other beam indexes for the output BPT 2 to be, for example, beam indexes {1, 2, 5, 6, 9, 10, 13, 14}. This may be seen in FIG. 8A, for example, where the beams 0, 5, 10 and 15 are the beam indexes corresponding to the input BPT and the beams 1 , 6, 9 and 14 are the beam indexes corresponding to the output BPT.

[0204] If the WTRU has not received an indication of the first and / or anchor focus beam index for the configured output BPT, the WTRU may determine that the first and / or anchor focus beam index for the configured output BPT is the same as the first beam index in the configured input BPT. That is, for example, the WTRU that is configured with input BPT 1 and output BPT 2 and not configured with the first and / or anchor focus beam for the output BPT, may determine that the first focus beam for the indicated output BPT 2 is the same as the first beam index for the input BPT (e.g., Beam #0). As such, the WTRU may determine the other beam indexes for the output BPT 2 to be for example beam indexes {0, 1 , 4, 5, 8, 9, 12, 13}. This may be seen in FIG. 8B, for example, where beams 0, 5, 10 and 15 are the beam indexes corresponding to the input BPT and beams 0, 5, 8 and 13 are the beam indexes corresponding to the output BPT.

[0205] The WTRU may determine beams belonging to a BPT (e.g., input-BPT) based on the BPT information (e.g., BPT-ID and / or number of beams in the BPT) and the active TCI-state set. For example, the WTRU may be configured to select beams associated to TCI-state# 1, 2, 3 of an active TCI-state set as beams belonging to a first input-BPT consisting of 3 beams. For example, the WTRU may be configured to select beams associated with TCI-state# 3, 4 of active TCI-state set as beams belonging to a second input-BPT consisting of 2 beams. In addition, the WTRU may be configured to assign BPT-specific beam IDs to the beams of a BPT. For example, the WTRU may assign Beam IDs in descending order of determined L1-RSRPs of RSs associated with beams belonging to a BPT. Additionally or alternatively, the WTRU may receive a configuration of a mapping between an indicated TCI-state and a configured BPT (e.g., output BPT).

[0206] Although features and elements are described above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. In addition, the methods described herein may be implemented in a computer program,software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magnetooptical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

CLAIMSWhat is Claimed:

1. A wireless transmit / receive unit (WTRU), configured with a plurality of input beam patterns, a plurality of output beam patterns, a plurality of artificial intelligence / machine learning (AI / ML) models, and trained weights for each of the plurality of AI / ML models, wherein each of the plurality of input beam patterns comprises a plurality of beam indexes corresponding to a set of input beams, wherein each of the plurality of output beam patterns comprises a plurality of beam indexes corresponding to a set of output beams, and wherein each of the plurality of AI / ML models corresponds to a respective one of the plurality of output beam patterns, the WTRU comprising: a transceiver; and a processor, wherein the transceiver and the processor are configured to measure a signal quality of a subset of the set of input beams of each of the plurality of input beam patterns to identify at least one input beam having the highest signal quality, wherein the transceiver and the processor are further configured to report the at least one input beam to a base station, wherein the transceiver and the processor are further configured to receive, from the base station, an indication of one of the plurality of input beam patterns and an indication of one of the plurality of output beam patterns to use to predict an output beam based on the report, wherein the transceiver and the processor are further configured to predict an output beam using the AI / ML model corresponding to the indicated one of the plurality of output beam patterns and the trained weights corresponding to the AI / ML model, and wherein the transceiver and the processor are further configured to report the predicted output beam to the base station.

2. The WTRU of claim 1 , wherein: the transceiver and the processor are further configured to receive an other configuration for at least one other input beam pattern comprising a plurality of beam indexes corresponding to an other set of input beams and at least one other output beam pattern comprising a plurality of beam indexes corresponding to an other set of output beams, and the transceiver and the processor are further configured to predict an other output beam using the other configuration.

3. The WTRU of claim 2, wherein: the transceiver and the processor are further configured to compare at least one accuracy parameter of the predicted output beam and the predicted other output beam,the transceiver and the processor are further configured to determine that the at least one accuracy parameter of the predicted other output beam is better than the at least one accuracy parameter of the predicted output beam, and the transceiver and the processor are further configured to send a message to the base station, wherein the message comprises a request to switch from the predicted output beam to the predicted other output beam.

4. The WTRU of claim 2 or 3, wherein the transceiver and the processor are further configured to send a message to the base station, wherein the message comprises a request to switch to using the at least one other input beam pattern and the at least one other output beam pattern for further prediction.

5. The WTRU of any of claims 1-4, wherein the transceiver and the processor are further configured to receive a configuration, for at least one of the plurality of input beam patterns, the plurality of output beam patterns, the plurality of AI / ML models, or the trained weights for each of the plurality of AI / ML models, via radio resource control (RRC) signaling.

6. The WTRU of any of claims 1-5, wherein: the transceiver and the processor are further configured to monitor a physical downlink control channel (PDCCH) to detect a downlink control information (DCI) with cyclic redundancy check (CRC) scrambled using a group radio temporary identifier (G-RNTI) to retrieve trained weights for an AI / ML model based on one or more of: the WTRU receives an indication to use a particular input beam pattern or a particular output beam pattern and the WTRU does not have corresponding trained weights, the WTRU receives an indication that the trained weights are updated at the base station, or the WTRU determines the accuracy parameters for the predicted output beam do not meet defined criteria.

7. A method, implemented in a wireless transmit / receive unit (WTRU), configured with a plurality of input beam patterns, a plurality of output beam patterns, a plurality of artificial intel I igence / machine learning (AI / ML) models, and trained weights for each of the plurality of AI / ML models, wherein each of the plurality of input beam patterns comprises a plurality of beam indexes corresponding to a set of input beams, wherein each of the plurality of output beam patterns comprises a plurality of beam indexes corresponding to a set of output beams, and wherein each of the plurality of AI / ML models corresponds to a respective one of the plurality of output beam patterns, the method comprising: measuring a signal quality of a subset of the set of input beams of each of the plurality of input beam patterns to identify at least one input beam having the highest signal quality; reporting the at least one input beam to a base station;receiving, from the base station, an indication of one of the plurality of input beam patterns and an indication of one of the plurality of output beam patterns to use to predict an output beam based on the report; predicting an output beam using the AI / ML model corresponding to the indicated one of the plurality of output beam patterns and the trained weights corresponding to the AI / ML model; and reporting the predicted output beam to the base station.

8. The method of claim 7, further comprising: receiving an other configuration for at least one other input beam pattern comprising a plurality of beam indexes corresponding to an other set of input beams and at least one other output beam pattern comprising a plurality of beam indexes corresponding to an other set of output beams; and predicting an other output beam using the other configuration.

9. The method of claim 8, further comprising: comparing at least one accuracy parameter of the predicted output beam and the predicted other output beam; determining that the at least one accuracy parameter of the predicted other output beam is better than the at least one accuracy parameter of the predicted output beam; and sending a message to the base station, wherein the message comprises a request to switch from the predicted output beam to the predicted other output beam.

10. The method of claim 7 or 8, further comprising sending a message to the base station, wherein the message comprises a request to switch to using the at least one other input beam pattern and the at least one other output beam pattern for further prediction.

11. The method of any of claims 6-10, further comprising receiving a configuration, for at least one of the plurality of input beam patterns, the plurality of output beam patterns, the plurality of AI / ML models, or the trained weights for each of the plurality of AI / ML models, via radio resource control (RRC) signaling.

12. The method of any of claims 6-11 , further comprising: monitoring a physical downlink control channel (PDCCH) to detect a downlink control information (DCI) with cyclic redundancy check (CRC) scrambled using a group radio temporary identifier (G-RNTI) to retrieve trained weights for an AI / ML model based on one or more of: the WTRU receives an indication to use a particular input beam pattern or a particular output beam pattern and the WTRU does not have corresponding trained weights, the WTRU receives an indication that the trained weights are updated at the base station, or the WTRU determines the accuracy parameters for the predicted output beam do not meet defined criteria.

13. A base station comprising: a transceiver; and a processor, wherein the transceiver and the processor are configured to send at least one configuration message to the base station, wherein the at least one configuration message comprises configuration information for a plurality of input beam patterns, a plurality of output beam patterns, a plurality of artificial intelligence / machi ne learning (AI / ML) models, and trained weights for each of the plurality of AI / ML models, wherein each of the plurality of input beam patterns comprises a plurality of beam indexes corresponding to a set of input beams, wherein each of the plurality of output beam patterns comprises a plurality of beam indexes corresponding to a set of output beams, and wherein each of the plurality of AI / ML models corresponds to a respective one of the plurality of output beam patterns, wherein the transceiver and the processor are further configured to receive, from the WTRU, a report of a measured beam at the WTRU among a subset of the set of input beams of each of the plurality of input beam patterns, wherein the transceiver and the processor are further configured to send, to the WTRU, an indication of one of the plurality of input beam patterns and an indication of one of the plurality of output beam patterns to use to predict an output beam based on the report, and wherein the transceiver and the processor are further configured to receive, from the WTRU, a report of a predicted beam predicted using the AI / ML model corresponding to the indicated one of the plurality of output beam patterns and the trained weights corresponding to the AI / ML model, and wherein the transceiver and the processor are further configured to send a downlink transmission to the WTRU using the predicted beam.

14. The base station of claim 13, wherein: the transceiver and the processor are further configured to send an other configuration for at least one other input beam pattern comprising a plurality of beam indexes corresponding to an other set of input beams and at least one other output beam pattern comprising a plurality of beam indexes corresponding to an other set of output beams, and the transceiver and the processor are further configured to receive, from the WTRU, a report of a predicted other output beam predicted using the other configuration.

15. The base station of claim 13 or 14, wherein: the transceiver and the processor are further configured to send downlink control information (DCI), on a physical downlink control channel (PDCCH), with cyclic redundancy check (CRC) scrambled using a group radio temporary identifier (G-RNTI), wherein the DCI comprises scheduling information for the WTRU to retrieve trained weights for an AI / ML model.

Images