Methods and apparatus for beam management in a wireless transmit / receive unit using artificial intelligence / machine learning (ai / ml)

Abstract

Procedures, methods, architectures, apparatuses, systems, devices, and computer program products comprising a wireless transmit / receive unit (WTRU) configured for receiving, from a network, at least one measurement configuration for performing measurements of beam parameters; receiving, from the network, configuration information for configuring at least one artificial intelligence / machine learning (AI / ML) model for predicting beam management parameters in the network, the configuration information including at least one trigger condition; determining that the at least one trigger condition has been satisfied, and responsively activating the at least one AI / ML model to at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model; and transmitting, to the network, a report comprising first information relating to at least one of: (1) training of the at least one AI / ML model and (2) predictions generated by the at least one AI / ML model.

Description

METHODS AND APPARATUS FOR BEAM MANAGEMENT IN A WIRELESS TRANSMIT / RECEIVE UNIT USING ARTIFICIAL INTELLIGENCE / MACHINE LEARNING (AI / ML)CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 531,253 filed August 7, 2023, which is incorporated herein by reference in its entirety.FIELD

[0002] This disclosure pertains to procedures, methods, architectures, apparatus, systems, devices, and computer program products for, and / or directed to using AI / ML at a WTRU for beam management in a wireless communication network.BRIEF DESCRIPTION OF THE DRAWINGS

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

[0004] FIG. 1 A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented;

[0005] FIG. IB 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;

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

[0007] FIG. ID 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;

[0008] FIG. 2 is diagram illustrating a beam measurement model according to 3GPP TS 38.300;

[0009] FIG. 3 is a diagram illustrating an AI / ML model for time series prediction of RSRP;

[0010] FIG. 4 is a flowchart illustrating a method of operating an AI / ML model in a WTRU in accordance with embodiments;[OH] FIG. 5 is a flowchart illustrating a method of evaluating the operation of an AI / ML model in a wireless network in accordance with embodiments; and

[0012] FIG. 6 is a flowchart illustrating a method of determining an optimal dataset for training an AI / ML model in accordance with embodiments; and

[0013] FIG. 7 is a flowchart illustrating another method of operating an AI / ML model in a WTRU in accordance with embodiments.DETAILED DESCRIPTION

[0014] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components, and circuits have not been described in detail, so as not to obscure the following description. Further, embodiments and examples not specifically described herein may be practiced in lieu of, or in combination with, the embodiments and other examples described, disclosed, or otherwise provided explicitly, implicitly and / or inherently (collectively "provided") herein.

[0015] FIG. 1 A 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 DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0016] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRU s) 102a, 102b, 102c, 102d, a RAN 104 / 113, a CN 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations,networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and / or a “STA”, may be configured to transmit and / or receive wireless signals and may include 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.

[0017] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106 / 115, 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 Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a 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.

[0018] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in 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.

[0019] 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).

[0020] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and / or High- Speed Uplink Packet Access (HSUPA).

[0021] 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).

[0022] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0023] 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).

[0024] 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 IX, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), InterimStandard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0025] The base station 114b in FIG. 1 A 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. 1 A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0026] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing a NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0027] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or 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), userdatagram 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 / 113 or a different RAT.

[0028] 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. 1 A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0029] FIG. IB is a system diagram illustrating an example WTRU 102. As shown in FIG. IB, 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.

[0030] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. IB 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.

[0031] 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, forexample. 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.

[0032] Although the transmit / receive element 122 is depicted in FIG. IB 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.

[0033] 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.

[0034] 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).

[0035] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel -zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0036] 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 theWTRU 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.

[0037] 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, and / or a humidity sensor.

[0038] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the uplink (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit 139 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 uplink (e.g., for transmission) or the downlink (e.g., for reception)).

[0039] 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.

[0040] 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 anembodiment. 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.

[0041] 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 uplink (UL) and / or downlink (DL), and the like. As shown in FIG. 1C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0042] 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 (or PGW) 166. While each of 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.

[0043] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c in the RAN 104 via an SI interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0044] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S 1 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.

[0045] 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.

[0046] 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 traditionalland-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.

[0047] Although the WTRU is described in FIGS. 1 A-1D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0048] In representative embodiments, the other network 112 may be a WLAN.

[0049] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic 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 802.1 le DLS or an 802. l lz 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.

[0050] When using the 802.1 lac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particularSTA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0051] 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 nonadj acent 20 MHz channel to form a 40 MHz wide channel.

[0052] 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 non-contiguous 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 the 80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0053] Sub 1 GHz modes of operation are supported by 802.1 laf and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.1 laf and 802.1 lah relative to those used in 802.1 In, and 802.1 lac. 802.1 laf supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.1 lah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.1 lah may support Meter Type Control / Machine-Type Communications, 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).

[0054] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.1 In, 802.1 lac, 802.1 laf, and 802.1 lah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.1 lah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode,even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0055] In the United States, the available frequency bands, which may be used by 802.1 lah, 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 802.1 lah is 6 MHz to 26 MHz depending on the country code.

[0056] FIG. ID is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0057] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated MultiPoint (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0058] 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 varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0059] 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.

[0060] 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 uplink (UL) and / or downlink (DL), support of network slicing, dual connectivity, 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. ID, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0061] The CN 115 shown in FIG. ID 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 each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0062] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling,mobility management, and the like. Network slicing may be used by the AMF 182a, 182b 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 machine type communication (MTC) access, and / or the like. The AMF a82a, 182b may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0063] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183 a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP -based, non-IP based, Ethernet-based, and the like.

[0064] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, 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 multihomed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0065] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0066] In view of Figs. 1A-1D, and the corresponding description of Figs. 1A-1D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station114a-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.

[0067] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0068] 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 viaRF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0069] In RRC CONNECTED mode, the WTRU measures multiple beams (at least one) of a cell, and the measurement results (power values) are averaged to derive the cell quality. In doing so, the WTRU is configured to consider a subset of the detected beams. Filtering takes place at two different levels, namely, at the physical layer to derive beam quality and then at the RRC level to derive cell quality from multiple beams. Cell quality from beam measurements is derived in the same way for the serving cell(s) and for the non-serving cell(s). Measurement reports may contain the measurement results of the X best beams if the WTRU is configured to do so by the gNB.

[0070] The corresponding high-level measurement model is described in FIG. 2, which is Figure 9.2.4-1 from 3GPP TS 38.300. More detail of RRC measurements in NR can be found in 3GPP TS 38.300 subclause 9.2.

[0071] Beam filtered measurements can be obtained from either Synchronization Signal Block (SSB) beams (SS / PBCH block below) or Channel State Information Reference Signal (CSI-RS) beams.

[0072] From 3GPP TS 38.331 V17.4.0 (2023-03):The WTRU shall: l>for each layer 3 beam filtered measurement quantity to be derived based on SS / PBCH block;2>derive each configured beam measurement quantity based on SS / PBCH block as described in TS 38.215[9], and apply layer 3 beam filtering as described in 5.5.3.2; l>for each layer 3 beam filtered measurement quantity to be derived based on CSI-RS;2> derive each configured beam measurement quantity based on CSI-RS as described in TS 38.215 [9], and apply layer 3 beam filtering as described in 5.5.3.2.

[0073] The network may configure the WTRU in RRC CONNECTED mode to derive Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ) and Signal to Interference and Noise (SINR) measurement results per cell associated with NR measurement objects based on parameters configured in the measObject (e.g., maximum number of beams to be averaged and beam consolidation thresholds) and in the reportConfig (rsType to be measured, SS / PBCH block or CSI-RS).

[0074] The network may configure the WTRU in RRC IDLE mode or in RRC INACTIVE mode to derive RSRP and RSRQ measurement results per cell associated with NR carriers based on parameters configured in measIdleCarrierListNR within VarMeasIdleConfig for measurements performed according to 3GPP TS 38.331 V17.4.0 (2023-03), section 5.5.3.3a, quoted below.The WTRU shall:1> for each cell measurement quantity to be derived based on SS / PBCH block:2>if nrofSS-BlocksToAverage is not configured in the associated measObject in RRC CONNECTED or in the associated entry in measIdleCarrierListNR within VarMeasIdleConfig in RRC IDLE / RRC INACTIVE; or2>if absThreshSS-BlocksConsolidation is not configured in the associated measObject in RRC CONNECTED or in the associated entry in measIdleCarrierListNR within VarMeasIdleConfig in RRC IDLE / RRC INACTIVE; or2>if the highest beam measurement quantity value is below or equal to absThreshSS-BlocksConsolidation:3>derive each cell measurement quantity based on SS / PBCH block as the highest beam measurement quantity value, where each beam measurement quantity is described in TS 38.215 [9];2>else:3>derive each cell measurement quantity based on SS / PBCH block as the linear power scale average of the highest beam measurement quantity values above absThreshSS-BlocksConsolidation where the total number of averaged beams shall not exceed nrofSS-BlocksToAverage, and where each beam measurement quantity is described in TS 38.215 [9];2>if in RRC CONNECTED, apply layer 3 cell fdtering as described in 5.5.3.2 ; l>for each cell measurement quantity to be derived based on CSI-RS:2 > consider a CSI-RS resource to be applicable for deriving cell measurements when the concerned CSI-RS resource is included in the csi-rs-CellMobility including the physCellld of the cell in the CSI-RS-ResourceConfigMobility in the associated measObject;2>ifnrofCSI-RS-ResourcesToAverage in the associated measObject is not configured; or 2>if absThreshCSI-RS-Consolidation in the associated measObject is not configured; or 2>if the highest beam measurement quantity value is below or equal to absThreshCSI- RS-Consolidation:3>derive each cell measurement quantity based on applicable CSI-RS resources for the cell as the highest beam measurement quantity value, where each beam measurement quantity is described in TS 38.215 [9];2>else:3>derive each cell measurement quantity based on CSI-RS as the linear power scale average of the highest beam measurement quantity values above absThreshCSI-RS- Consolidation where the total number of averaged beams shall not exceed nrofCSI- RS-ResourcesToAverage ;2> apply layer 3 cell filtering as described in 5.5.3.2.

[0075] Quoting from 3GPP TS 38.331 V17.4.0 (2023-03), section 5.5.3.2:The WTRU shall: l>for each cell measurement quantity, each beam measurement quantity, each sidelink measurement quantity as needed in clause 5.8.10, for each CLI measurement quantitythat the WTRU performs measurements according to 5.5.3.1, and for each candidate L2 U2N Relay WTRU measurement quantity according to 5.5.3.4:2> filter the measured result, before using for evaluation of reporting criteria or for measurement reporting, by the following formula:Fn = (l - a) *Fn-l + a*Mn whereMnis the latest received measurement result from the physical layer;Fnis the updated filtered measurement result, that is used for evaluation of reporting criteria or for measurement reporting;Fn-i is the old filtered measurement result, where Fo is set to Mi when the first measurement result from the physical layer is received; and for MeasObjectNR, a = l / 2(ki / 4), where la is the filterCoefficient for the corresponding measurement quantity of the i:th QuantityConfigNR in quantityConfigNR-List, and i is indicated by quantityConfiglndex in MeasObjectNR; for other measurements, a = l / 2(kfr where k is the filterCoefficient for the corresponding measurement quantity received by the quantityConfig; for UTRA-FDD, a = 1 / 2^4),where k is the filterCoefficient for the corresponding measurement quantity received by quantityConfigUTRA-FDD in the QuantityConfig;2> adapt the filter such that the time characteristics of the filter are preserved at different input rates, observing that the filterCoefficient k assumes a sample rate equal to X ms; The value of X is equivalent to one intra-frequency LI measurement period as defined in TS 38.133

[0014] assuming non-DRX operation, and depends on frequency range.

[0076] The MAC entity may be configured by RRC per Serving Cell or per Beam Failure Detection Reference Signal (BFD-RS) set with a beam failure recovery procedure that is used for indicating to the serving gNB of a new SSB or CSI-RS when beam failure is detected on the serving SSB(s) / CSI-RS(s). Beam failure is detected by counting beam failure instance indication from the lower layers to the MAC entity. If beamFailureRecoveryConfig is reconfigured by upper layers during an ongoing Random Access procedure for beam failure recovery for SpCell, the MAC entity shall stop the ongoing Random Access procedure and initiate a Random Access procedure using the new configuration. The Serving Cell is configured with two BFD-RS sets if and only if iailur eDetectionSet 1 and failureDetectionSet2 are configured for the active downlink Bandwidth Part (BWP) of the Serving Cell. When the Secondary Cell Group (SCG) is deactivated,the WTRU performs beam failure detection on the PSCell if bfd-and-RLM (Radio Link Monitoring) is set to true.

[0077] RRC configures the following parameters in the beamFailureRecoveryConfig, beamFailureRecoverySpCellConfig, beamFailureRecoverySCellConfig and the radioLinkMonitoringConfig for the Beam Failure Detection and Recovery procedure:- beamFailurelnstanceMaxCount for the beam failure detection (per Serving Cell or per BFD- RS set of Serving Cell configured with two BFD-RS sets);- beamFailureDetectionTimer for the beam failure detection (per Serving Cell or per BFD-RS set of Serving Cell configured with two BFD-RS sets);- beamFailureRecoveryTimer for the beam failure recovery procedure for SpCell;- rsrp-ThresholdSSB'. an RSRP threshold for the SpCell beam failure recovery;- rsrp-ThresholdBFR'. an RSRP threshold for the SCell beam failure recovery or for the beam failure recovery of BFD-RS set of Serving Cell;- power RampingStep'. power RampingStep for the SpCell beam failure recovery;- powerRampingStepHighPriority. powerRampingStepHighPriority for the SpCell beam failure recovery;- preambleReceivedTargetPower. preambleReceivedTargetPower for the SpCell beam failure recovery;- preambleTransMax'. preambleTransMax for the SpCell beam failure recovery;- scalingFactorBP. scalingFactorBI for the SpCell beam failure recovery;- ssb-perRACH-Occasiorr. ssb-perRACH-Occasion for the SpCell beam failure recovery using contention-free Random Access Resources;- ra-ResponseWindow. the time window to monitor response(s) for the SpCell beam failure recovery using contention-free Random Access Resources;- prach-Configurationlndex'. prach-Configurationlndex for the SpCell beam failure recovery using contention-free Random Access Resources;- ra-ssb-OccasionMasklndex'. ra-ssb-OccasionMasklndex for the SpCell beam failure recovery using contention-free Random Access Resources;- ra-OccasionList'. ra-OccasionList for the SpCell beam failure recovery using contention-free Random Access Resources;- candidateBeamRSLis . list of candidate beams for SpCell beam failure recovery;- candidateBeamRS-List-rl6'. list of candidate beams for SCell beam failure recovery or list of candidate beams for beam failure recovery of a Serving Cell for BFD-RS set one;candidateBeamRS-List2-rl7'. list of candidate beams for beam failure recovery of a Serving Cell for BFD-RS set two.

[0078] The following WTRU variables are used for the beam failure detection procedure:- BFI COUNTER (per Serving Cell or per BFD-RS set of Serving Cell configured with two BFD-RS sets): counter for beam failure instance indication which is initially set to 0.

[0079] Supervised learning AI / ML (Artificial Intelligence / Machine Learning) models that can anticipate beam related quantities may be fundamentally difficult to train due to the nature of SSB and CSI-RS beams, which provide for a smaller coverage area than a cell. This makes the window of opportunity to collect useful beam related data and with that, to train models, smaller when compared to cell level related AI / ML models.

[0080] The current mechanisms for data collection for beam related data follow a traditional threshold configuration approach. Beam related measurement collection may not be sufficiently configurable to allow for beam related measurement data collection, thereby creating a bottleneck to AI / ML beam related enhancements.

[0081] Typical reported measurements may include cell level measurements which are a result of the averaging of more than one beam. This is used mostly in mobility contexts, where the cell measurements are more important. For beam management purposes, it would logically be more interesting to have access to more beam level measurements that can serve the purpose of training AI / ML models. The current 5G system would be able to do this, but at the cost of significant signaling and especially measurement reporting overhead on the air interface. Data collection mechanisms come therefore at a significant cost.

[0082] On the other hand, if there is an AI / ML model functionality availability in the WTRU, the WTRU can then execute AI / ML operations instead of reporting measurements so the network can then execute any actions with it, e.g., training of the model.

[0083] New methods are thus desirable to enable training, model performance monitoring and data collection aspects to cover AI / ML beam management related identified gaps.

[0084] The terms beam and cell are used mostly interchangeably in the following description. While the description focuses on beam related aspects, the features and aspects discussed below generally can be applied to cells as well.

[0085] An LI measurement herein may comprise (e.g., consist of) a measurement of RSRP, RSRQ, Received Signal Strength Indicator (RSSI), etc., performed by a WTRU of a cell, beam, set of cells, or set of beams. Such LI measurement may be similar to L3 measurements reportedin Radio Resource Management (RRM), with differences in the filtering, reference signals measured, reporting mechanisms, etc.

[0086] Herein, LI measurement can apply also to RRM reporting. Measurements may refer to LI measurements for Lower-layer Triggering Mobility (LTM). Certain features herein may apply also to RRM / L3 measurements, as well as other measurements (e.g., measurements of speed, location, height, traffic, etc.).

[0087] In a simple mobility scenario, a WTRU in mobility may read the current serving cell’s RSRP and report it to the network. If the WTRU is moving to an area approaching the serving cell’s edge, it may record that RSRP values are decreasing. These values may be communicated to the network via measurement reports for the network to make a decision.

[0088] The network may have a pre-trained AI / ML model that is able to produce predictions of air-interface measurements (RSRP, RSRQ, SINR, etc.) of serving and / or neighbor cells (any cell, basically). These predictions may be used as a tool herein to anticipate the radio conditions that the WTRU will experience, instead of waiting for the WTRU to report them.

[0089] In order to produce more meaningful predictions in this context, the network predicts conditions (e.g., RSRP) may be in a time series manner. This means that, from the moment the network predictions are triggered, the WTRU may produce several prediction outputs over a future time span, and with a certain granularity or time step.

[0090] FIG. 3 shows an AI / ML model illustrating a time series prediction for RSRP as an example. As seen, the AI / ML model may take as its inputs current and previous RSRP measurements (and any other relevant data) and may predict future RSRPs at various time instances in the future (possibly also including a predicted error tolerance of the predicted RSRPs).

[0091] The predictions can also be done for one point in time (e.g., only) or can extend over several time steps. In many scenarios, prediction with time series output may be more beneficial than single value predictions, as it may be difficult to match the prediction with, e.g., a network configured event with a single prediction point.

[0092] This may raise a practical issue about the granularity of the timestamp associated with a prediction. Particularly, if the WTRU or the network predict one or more future values, a timestamp will, in principle, be associated with each prediction, e.g., a timestamp for t+1, t+2, etc. The granularity of that timestamp may depend on the AI / ML model in use and other ML related settings. Terminology like “predicted value”, “inferred value”, “future value” and others are used in this description to refer to future predicted values that may or not have an associated timestamp, and if they do have a timestamp, the timestamp may be considered a small delta timeinterval within which the predicted value is considered to be accurate or valid, either completely or with a certain degree of confidence. In all WTRU-network exchanges, we may consider that predictions can be represent by a tuple such as [“predicted value”; timestamp - delta; timestamp + delta],

[0093] A WTRU may be configured to predict future measurements based on current and / or historical measurements. For example, the WTRU may be configured with a trained AI / ML model that is able to produce predictions for radio interface radio signal levels. In certain embodiments, the AI / ML model at the WTRU may be implementation based. In other embodiments, the AI / ML model the WTRU may obtain the AI / ML model from the network. In some embodiments, the AI / ML model may be configured to take as an input current and / or historical RSRP measurements. In other embodiments, the AI / ML model may be configured to take additional inputs such as WTRU location information, WTRU mobility, etc. In some embodiments, the AI / ML model may be configured to produce single value predictions - e.g., RSRP at a future time instant t. In other embodiments, the AI / ML model may be configured to predict a series of RSRP values corresponding to future time instances t+1, t+2, so on up to t+t_fb.

[0094] A model may be offline trained or online trained. Also, models may be exchanged in a preconfiguration step, not detailed in this description.

[0095] For any predicted value, either by the network or the WTRU, the predicted value itself may be associated and / or represented by a confidence or error value, and may be represented by an average, peak, minimum value, etc. along a small time window representing the validity of that prediction.

[0096] The above details relate to prediction of measurement values, i.e., for models that perform regression. In this description, the model output may have different functionalities.

[0097] The model output may have functionalities related to radio measurement regression at beam / cell levels (one or more predicted values).

[0098] The model output may have functionalities related to classification of beams, e.g., as a good beam (above absThreshSS-BlocksConsolidation). Good beam is a current system concept, and it may mean that, after averaging LI measurements, the WTRU shall consider (e.g.; only) beams that are above absThreshSS-BlocksConsolidation. It is a metric of how good the beam is in terms of signal strength

[0099] The model output may have functionalities related to clustering of a set of beams (outputting number of good beams). This would relate to, e.g., the WTRU or the network, givena set of beams, clustering a subset of these beams into a group of good beams and the remainder as “non-good beams”.

[0100] The model output may have functionalities related to beam failure detection. Beam failure may be detected by counting beam failure instance indications from the lower layers to the MAC entity. A model that could detect beam failure would, as an example, be able to predict if the physical layer count of beam failure indications would exceed a network configured threshold.

[0101] There are configuration aspects relevant to all embodiments discussed herein. Typically, these are criteria that the WTRU is meant to assess in order to perform a determined action. All configuration and criteria described in this description can be associated in a multitude of ways.

[0102] A general example of how the different configurations could be applied is that the WTRU may receive different groupings of configurations. For example, the WTRU may receive a first group configuration comprising (1) a criterion that is being assessed that relates to measurements, and (2) another criteria being assessed that may relate to any one or more upper layers metric.

[0103] The WTRU may receive concurrently a second group configuration comprising (1) a buffer status (amount of data in the UL buffer) for a specific application ID and / or radio bearer to be monitored and (2) a L1 / L3 measurement criteria for any one or more cells to be monitored at the same time.

[0104] The evaluation of the different groups could be done in different ways. In one example, the WTRU could receive a set comprising three groupings of monitoring criteria and be configured to consider that a certain requirement for the WTRU to perform an action is satisfied when, e.g., the criteria for any two of the three groups is satisfied or any one of the three groups is satisfied (or, for that matter, when all of the criteria of all of the groups are satisfied).

[0105] In another example, the WTRU may be configured with a start time and / or a validity timer for each grouping, which would serve as a window of opportunity for the WTRU to monitor the related conditions. This aspect could be provided to the WTRU in forms other than time, like an e.g., RSRP range, a distance, a geo-location, an amount of UL data starting from any network indicated time or UL buffer report, an amount of DL data, etc.

[0106] If more than one criterion needs to be met for the WTRU to execute the action, the different criteria may be grouped together. In some embodiments, the WTRU may receive a grouping of criteria with an associated validity value for each criterion in the grouping, in which case all the criteria in the group must be met for the group requirements to be met. In other embodiments, (e.g., only) some a subset of the criteria in the grouping must be met in order for the for the group requirements to be considered met.

[0107] In some other embodiments, some criteria in the grouping may have associated hard thresholds while other criteria in the grouping have soft thresholds. For example, the hard threshold may be assessed for the fulfilment of the criteria and, if met, the criteria for the grouping may be considered to be met. If the hard threshold is not met, the criteria of the grouping can still be deemed to be met if, for instance, a number of the soft thresholds are met. As an example, the WTRU may receive a group of criteria for current measurements and current buffer status for a specific one or more radio bearers, with hard and soft thresholds. The criteria could be considered met if the values for measurements are below / above a hard threshold, regardless of the current buffer status for any one or more radio bearers from the bearer group. The criteria for the grouping may be considered met even if the hard measurement criteria may not be met, but buffer status of all of the radio bearers meet some soft criteria.

[0108] The criteria configured at the WTRU may be specific for inference activation and / or for training purposes, i.e., used to configure solely the activation of training or inference functionalities, or both. The criteria thresholds may be the same as any legacy thresholds that may be configured in the WTRU for the purpose of RRM procedures (e.g., for the purpose of measurements) or new criteria, or any combination of both.

[0109] Cell measurements result from the combination of one or more beams, as described above. Consequently, beam coverage may be smaller than the coverage of a cell. This means that the availability of beam related data, e.g., measurements, may be smaller than that of a cell. It is already a difficult task for a network to collect enough data to perform sufficient training for having models that are able to predict cell related aspects. It is even more difficult to do so in the case of beams. Because if their coverage area may be smaller, a WTRU may have less opportunity to perform measurements on them.

[0110] Moreover, to generalize a model properly so that it can output good predictions, vast amounts of data may be required for training. An overload of the air interface in terms of data collection should be avoided. It may be much more efficient in some cases to allow a WTRU to perform Al related tasks such as training and model monitoring, and reporting the results from that process, than to create data collection mechanisms from a WTRU towards the network.

[0111] The methods and apparatus disclosed in this description benefit the overall radio access network by enabling training, model monitoring, and optimal dataset design at the user equipment, thus reducing the amount of monitoring data (such as data collection itself) that the network requires.

[0112] Another benefit is that, if the WTRU performs an action related to a model, because of, e.g., having certain radio link conditions, then the execution of that pre-emptively configured action may be much faster than if the action required a network command or instruction.

[0113] Methods and apparatus are provided to perform an action, inference or training of an AI / ML model based on configured criteria and report either beam prediction or training procedure related information to the network.

[0114] The methods, apparatus, and techniques disclosed herein anticipate network resource allocation in terms of beam coverage by leveraging the WTRU’s capability for beam related predictions. The WTRU may have a trained (or “semi -trained”) AI / ML model capable of different prediction types. Examples of model outputs include: radio measurement regression at beam / cell levels, one or more predicted values; classification of beams, e.g., as a good beam (above absThreshSS-BlocksConsolidation); clustering of a set of beams, outputting number of good beams; beam failure detection; etc.

[0115] Beam management procedures can be enhanced at the network side with the help of the WTRU. One of the primary features in this disclosure is that the WTRU will make useful beam related predictions based on imminence of a handover (HO) or by assessment of coverage from neighbors. These predictions will be beam related, and by reporting them, the network can more optimally perform SSB and CSI-RS resource allocation. In case the predictions are not good, or simply because the model is “semi -trained”, the WTRU can also start an AI / ML training process and report the results to the network.

[0116] A WTRU may be configured with cross layer related criteria, for example, including monitoring of L3 and LI events, where, upon determination that the criteria is met, the WTRU will either perform inference, and / or will train an AI / ML model, reporting on both the predictions and / or the training process.

[0117] The WTRU may receive one or more measurement configurations (e.g., immediate / logged MDT (Minimization of Drive Test), L3 measurement configuration).

[0118] The WTRU may receive a configuration with a set of AI / ML models (1 or more) associated with a set of functions and a set of events for the WTRU to monitor to trigger, e.g., AI / ML model inference and / or training and / or other actions and reporting criteria, including one or more of the following: (1) upper layer inference / training / other function activation triggers; (2) lower layer inference / training / other function activation trigger; (3) time related activation triggers; (4) beam ID related activation conditions; (5) WTRU inference process configuration; and (6) predictive measurement reporting configuration.

[0119] In the case of upper layer inference / training / other function activation triggers, the WTRU may monitor L3 events, e.g., Al to A6, Bl, B2, II, Cl, C2: each of inference / training / other function may have a specific measurement threshold.

[0120] Lower layer inference / training / other function activation trigger may comprise any of: (1) absolute / relative thresholds for buffer status values (MAC layer); (2) Absolute / relative thresholds for RSRP used for beam failure detection, e.g., Ll-RSRP, Ll-RSRP difference threshold; and (3) absolute / relative thresholds the variance of consecutive Ll-RSRP samples for a specific CSLRS resource.

[0121] Time related activation triggers may comprise any of: (1) start inference / training / other action if configured start time is now; (2) stop at time x, (e.g., where x may be a function of the length of time it took to perform the training of the model in recent training instances); and (3) start training if a timer expires, (e.g., where the length of the timer may be configured based on historical training durations for the model).

[0122] Beam ID related activation conditions may comprise any of: (1) detection of specific SSB beam ID(s); (2) detection of specific CSI-RS resources; (3) detection of number of (good) beams greater than threshold; (4) if the number of detectable beams is less than x; (5) start training if any beam within the good beams group is under an RSRP threshold; and (6) if Ll-RSRP consecutive samples’ variance is higher than threshold.

[0123] WTRU inference process configuration (e.g., via AI / ML model), wherein the configuration for inference may include one or more of the following: (1) target desired output; and (2) time horizon.

[0124] Target desired output may comprise any of:(1) number and / or identity of predicted SSBs available; (2) number of CSLRS resources available; (3) number and / or identity of predicted good SSB beams; (4) number and / or identity of predicted good CSLRS beams; (5) SSB ID(s) radio quantity (e.g., RSRP); (6) CSI-RS beam(s) radio quantity (e.g., RSRP); (7) SSB beam failure detection (with SSB beam ID for e.g.); and (8) CSI-RS beam failure detection.

[0125] Time horizon may comprise any of: (1) time validity of a predictions (e.g., number of future time slot to infer); (2) confidence value for prediction horizon length; and (3) input training data related (e.g., number of input samples to use).

[0126] Predictive measurement reporting configuration, may including one or more of the following: (1) prediction results; (2) timestamps; and (3) legacy configured measurements.

[0127] The WTRU may determine if a trigger condition is satisfied and, based on the satisfied trigger condition, the WTRU may determine 1) an associated function (e.g., beam management, CSI reporting, positioning, etc.) and / or 2) AI / ML model, and 3) the activated procedure (e.g., using AI / ML model for inference for the associated function, or training an AI / ML model of an associated function).

[0128] For example, a WTRU may trigger inference on a first model based on a higher layer event being satisfied.

[0129] For example, a WTRU may activate AI / ML model inference procedure, after determining that the criteria in the received configuration has been met, or via indication from the NW.

[0130] For example, a WTRU may activate AI / ML model training procedure, after determining that the criteria in the received configuration has been met, or via indication from the NW.

[0131] For example, a WTRU may perform measurements required for inputs to model training.

[0132] The WTRU may report (e.g., via Uplink Control Information (UCI) indication, or MAC CE, or RRC message) information related to one or more of: (1) determined associated function or AI / ML model; and (2) information related to the inference / training / other function process.

[0133] Information from inference may comprise any of: Prediction results, timestamps, legacy configured measurements.

[0134] Information from training may comprise any of: hyper parameters, number of training iterations executed, number of L1 / L3 input samples used in training, batch size, time to train to achieve accuracy, number of skipped training rounds due to RSRP criteria not met.

[0135] The WTRU may receive one or more measurement configurations (e.g., immediate / logged MDT, L3 measurement configuration). This step may refer to any currently existing measurement configuration that a WTRU could receive. It would entail all the required configuration in terms of cells, beams, measurement quantities (e.g., RSRP), measurement periodicity, measurement gaps, etc., i.e., all the information required so that the WTRU can perform measurements. This configuration may be (e.g., always) deployed to a WTRU and servs as a basis for reporting and RRM procedures.

[0136] The WTRU may receive a configuration with a set of AI / ML models (1 or more) associated with a set of functions and a set of events, a set of events for the WTRU to monitor to trigger, e.g., AI / ML model inference and / or training and / or other actions and reporting criteria,

[0137] In an embodiment, the WTRU will either perform training of a model, inference, or both. It will then report results from either of the processes, or both. Hence, essentially, the following describes the criteria that may trigger any of these action on the WTRU side.In the case of upper layer inference / training / other function activation triggers, the WTRU may monitor any of L3 events, e.g., Al to A6, Bl, B2, II, Cl, C2: (1) event Al (Serving cell becomes better than threshold); (2) event A2 (Serving cell becomes worse than threshold); (3) event A3 (Neighbor cell becomes offset better than SpCell); (4) event A4 (Neighbor cell becomes better than threshold); (5) event A5 (SpCell becomes worse than threshold 1 and neighbor becomes better than threshold2); (6) event A6 (Neighbour cell becomes offset better than SCell); (7) event B 1 : Inter-RAT neighbor cell becomes better than the threshold; (8) event B2: P Cell becomes worse than threshold 1 and inter-RAT neighbor becomes better than threshold 2; (9) event II : Interference becomes higher than the threshold; (10) event Cl : The NR Sidelink channel busy ratio is above a threshold; and (11) event C2: The NR Sidelink channel busy ratio is below the threshold.

[0138] The purpose is to leverage useful information from these legacy events to trigger a WTRU inference process. All events should be monitored and included for inference. Some events are, technically, more useful than others though. For example, if criteria for A3, A4, or A6 (Neighbor becomes better than threshold), that means the WTRU has at least one neighbor cell and at least an UL / DL beam pair available to it. The availability is a strong reason for the WTRU to trigger beam related predictions as it could indicate a mobility procedure is imminent. Events A2 and A5 could indicate radio link quality decreasing, and would also clearly justify inference procedures to be triggered. For Al, the serving cell’s radio link quality is increasing, and inference can be justified for example, for the purpose of load balancing or energy savings, where the network would want to guarantee the WTRU could stay connected to that serving cell for longer time.

[0139] The threshold given in this step follows the principles described above.

[0140] In the configuration of lower layer inference / training / other function activation trigger, the WTRU may get additional lower layer parameters that could be useful to assess in addition to the previously explained events.

[0141] Four lower layer aspects are given focus to, namely: (1) buffer status values (MAC layer); (2) variance of Ll-RSRP samples for a specific CSI-RS resource (Physical layer); (3) RSRP used for beam failure detection, e.g., Ll-RSRP (Physical layer); and (4) a soft threshold for beamFailurelnstanceMaxCount (MAC).

[0142] Nothing should prevent the WTRU from training, inferring, or doing both, if the right conditions / criteria are met. However, some cases are more plausible than others, with a few examples given below. This may be dictated by the configuration.

[0143] For example, if mobility is imminent, or simply if a neighbor cell becomes better than a certain level, then it would make sense for the WTRU to inspect other lower layer parameters, in order to make a decision e.g., whether to perform inference and / or training.

[0144] In one embodiment, the WTRU, upon determination that any one or more events related to a neighbor cell’ s link has become better than a threshold (e.g., better that the current serving cell’ s link), may assess the buffer levels. It may then decide to commence training of an AI / ML model if the buffer levels were lower than a threshold or infer beam related aspects if the buffer levels were higher than a threshold. The rationale for this is service based. Particularly, in principle, the network would want to provide better resources to the WTRU when buffer levels are high. Therefore, the WTRU would infer and report the results of the inference as soon as possible.

[0145] In another set of embodiments, the WTRU may assess the variance of Ll-RSRP for, e.g., a CSI-RS resource. Particularly, if radio measurements are degrading, the WTRU may assess thresholds for the variance to determine instability of the LI measurements and start inference or training. In this case, both functions are useful as the beam resource is degrading and a mobility action will follow. Hence, because the availability of the unstable measurements is limited, the model benefits from training and / or inference to help with the mobility action.

[0146] In other embodiments, the WTRU may start assessing the RSRP for a particular beam resource (the same rationale as for the variance case applies here too), where the WTRU may trigger inference or training by determination of soft or hard thresholds for the configured RSRP used for beam failure detection.

[0147] In another set of embodiments, if the radio link for the serving cell deteriorates, e.g., A2 is detected, it is almost certain that the network will need to provide the WTRU with better beam resources. It would then make sense to inspect a soft threshold for beamFailurelnstanceMaxCount, where the WTRU could, in certain embodiments, activate training until the soft threshold for the parameter is reached, and then activate inference.

[0148] Time related activation triggers, and beam ID related activation conditions are provided.

[0149] A few extra configuration options for training may be provided, the rationale being that the network may have a database used for training, and an inspection of that database and regular data manipulation and assessment can easily lead to the detection of conditions that would be useful for training, but are simply not available in the database. The network can then configure the WTRU in those cases, for example, with training configuration targeting a specific beam resource.

[0150] Extra training configuration options may include any of: time related; start training if configured start time is now; stop at time x; start training if a timer expires; Beam ID related;Specific SSB beam ID(s); Specific CSI-RS resources; Start training if beam ID(s) are detectable; if the number of detectable beams is less than x; if number of good beams available is under a threshold etc.; Radio quantity related; start training if any beam within the good beams group is under an RSRP threshold; and if Ll-RSRP consecutive samples’ variance is higher than threshold).

[0151] The WTRU inference process configuration (e.g., via AI / ML model) may serve the purpose of defining the target output of the predictions. As stated in section above, there are several possible options, and the configuration should reflect the target prediction for the case of inference (as well as the output in general, which also dictates the target model(s)). The definition of the target output may, in turn, determine one or a group of AI / ML models for the WTRU to select from. There could be an (e.g., explicit) indication of specific models to use, e.g., A.R.I.M.A., decision tree, xg-boost, or the WTRU may select any model for the particular output from a set of models capable of producing such output. Available options for the desired target output include: number of predicted SSBs available; number of CSI-RS resources available; number of predicted good SSB beams; number of predicted good CSI-RS beams; SSB ID(s) radio quantity (e.g., RSRP); CSI-RS beam(s) radio quantity (e.g., RSRP); SSB beam failure detection; CSI-RS beam failure detection; etc.

[0152] The WTRU may also receive a time horizon configuration as well as thresholds for decision making between inference, training, or both.

[0153] Section above details how the WTRU may infer in different ways, e.g., one or more data points in the case of regression, number of good beams, etc. The predictive measurement reporting configuration may indicate in different forms the contents that the WTRU should report. Particularly in the case of regression, the reported data can be further filtered based on threshold, averaging formulas, weighted averaging formulas, specific number of points to report, etc.

[0154] With each reported data point, the WTRU may associate other information such as a timestamp, an accuracy and / or error value, beam ID(s), other forms of identification of the predicted values like a MeasID configuration, etc.

[0155] The WTRU may proceed with training activation configuration (which can happen alternatively or concurrently to inference).

[0156] The WTRU may determine if a trigger condition is satisfied and, based on the satisfied trigger condition, may determine any of 1) an associated function (e.g., Beam management, CSI reporting, positioning, etc.) and / or 2) AI / ML model, and 3) the activated procedure (e.g., usingAI / ML model for inference for the associated function, or training an AI / ML model of an associated function).

[0157] The WTRU may determine that the criteria detailed in the previous steps has been met. The configuration in the previous steps may be linked one or more specific function(s), one or more specific AI / ML model(s), and / or one or more specific procedure(s).

[0158] The WTRU may report (e.g., via UCI indication, or MAC CE, or RRC message) information

[0159] The information to be reported by the WTRU in relation to inference has been described in previous sections of the description.

[0160] Information related to the training process that the WTRU may report includes one or more of: (1) Hyperparameter-related (e.g., aggregated resulting hyperparameter(s)); (2) training-related (e.g., number of training iterations executed; number of L1 / L3 input samples used in training; batch size); and (3) training convergence-related (e.g., time to train to achieve specific accuracies; number of skipped training rounds due to RSRP criteria not met).

[0161] Hyperparameters may be intrinsic quantities of a model, i.e., each model type may have its own hyperparameters, and they can assume many different values, depending on the target output and training stage (or the training data the model has seen, in other words). Given a specific model ID and a set of hyperparameters, the same result model can be obtained in different network nodes (or computing nodes to be more precise).

[0162] Batch size may refer to how many data points are used in one go when it comes to model training rounds.

[0163] According to embodiments, the WTRU may monitor the performance of a beam related AI / ML model and report performance monitoring information to the network.

[0164] The WTRU may receive one or more measurement configurations (e.g., immediate / logged MDT, L3 measurement configuration).

[0165] The WTRU may receive a configuration for an AI / ML model and / or a set of parameters associated with AI / ML model training, monitoring, and performance reporting procedures, including any of the following: (1) training and performance monitoring configuration; and (2) reporting procedure configuration.

[0166] The training and performance monitoring configuration (definition / size / format of inputs, outputs, models, and performance monitoring criteria) may include any of parameters related to: (1) model input related; (2) target desired output; (3) model specific; and (4) prediction accuracy metrics.

[0167] Model input related parameters may include any of: (1) number of input samples (e.g., an explicit indication from the network of how many samples to use); (2) specific data features selection for input (e.g., an explicit indication from the network of what data features to use); and (3) WTRU-based feature selection-related.

[0168] WTRU-based feature selection-related may indicate any of the following methods: (1) parameters for wrapper; (2) parameters for filter methods; (3) parameters for intrinsic methods; and (4) parameters for other relevant methods.

[0169] Parameters for wrapper may include any of: (1) forward feature selection; (2) backward feature elimination; (3) exhaustive feature selection; and (4) recursive feature elimination.

[0170] Parameters for filter methods may include any of: (1) information gain; (2) Chi-square test; (3) Fisher’s score; (4) correlation coefficient; (5) variance threshold; (6) mean absolute difference (MAD); (7) mean absolute error; (8) dispersion ratio; and (9) cosine similarity.

[0171] Parameters for intrinsic methods may include a combination of the above methods

[0172] Parameters for other relevant methods may include any of: (1) F-regression score; (2) power control algorithm (PCA) indication; and (3) correlation thresholds.

[0173] The target desired output may include any of the following parameters: (1) number and / or identity of predicted SSBs available; (2) number of CSI-RS resources available; (3) number and / or identity of predicted good SSB beams; (4) number and / or identity of predicted good CSI- RS beams; (5) SSB ID(s) radio quantity (e.g., RSRP); (6) CSI-RS beam(s) radio quantity (e.g., RSRP); (7) SSB beam failure detection (e.g., with SSB beam ID); and (8) CSI-RS beam failure detection.

[0174] The model specific may include any of the following parameters: (1) model ID(s); (2) model metadata; (3) model functionality (e.g., cluster, classify, regress); and (4) hyperparameter set.

[0175] Model metadata may include any one or more of the following, for example: (1) WTRU vendor info; (2) network vendor info; (3) applicable scenario, configuration, site information, supported use case; (4) model performance indicators, model accuracy, model bias, model variance; and (5) model size.

[0176] Prediction accuracy metrics may include absolute / relative thresholds for accuracy metrics (e.g., RMSE, MAE, per beam(s), cell(s) - these are all model and output type dependent -metrics can change per model type, e.g., MSE / Cosine similarity for CSI use case, beam quality for beam management use case, etc.).

[0177] The reporting procedure configuration may include any of the following parameters: (1) prediction accuracy metric-related; (2) prediction accuracy-related; and (3) triggers for reporting.

[0178] Prediction accuracy metric-related may: (1) report RSME if RSME>threshold for any model; and / or (2) report RSRP and timestamp for RMSE>threshold.

[0179] Prediction accuracy-related may report number of predicted values with estimated error below threshold.

[0180] Triggers for reporting may include any of the following: (1) radio quantity, e.g., RSRP thresholds; (2) on timer expiry; (3) if inference criteria are not met anymore; (4) number of repetitions of the process; and (5) if accuracy is below threshold.

[0181] The WTRU may determine current or predicted future model performance values of the configured AI / ML model based on the training and performance monitoring configuration

[0182] Based on the current or predicted future model performance, the WTRU may determine one or more of: current or predicted future performance monitoring related information; and / or absence of a specific model with the configured inference inputs.

[0183] Current or predicted future performance monitoring related information, including one or more of: (1) model ID(s), e.g., filter by x best performing models; (2) number of bad performing predicted values, for example, the number of beams with Ll-RSRP less than a threshold; (3) good performing predicted values, for example, the number of beams with Ll-RSRP greater than a threshold; (4) bad performing predicted values, for example, the WTRU may use traditional beam management framework to compare the output of the AI / ML model with and determine than the model is not performing well; (5) training time; and (6) minimum / maximum estimated accuracy / error.

[0184] The WTRU may transmit indication of one or more of: current or predicted future performance monitoring related information or absence of a specific model with the configured inference inputs (e.g., via MAC CE, UCI or RRC messages).

[0185] The WTRU may receive one or more measurement configurations (e.g., immediate / logged MDT, L3 measurement configuration).

[0186] The WTRU may receive a configuration for an AI / ML model and a set of parameters associated with AI / ML model training, monitoring and performance reporting procedures.

[0187] A goal of in one or more embodiments is performance monitoring. The WTRU may receive configuration containing metrics on how to assess the model performance. A main focus in one or more embodiments is on how the WTRU will determine this based on the input data for the model.

[0188] Supervised learning models, or AI / ML models (typical 3GPP terminology), can estimate and associate accuracy and errors for each prediction they output. In the case of time series predictions, each predicted value can have a different error / accuracy associated with it. However, once a model is model is trained, even if partially, when an inference method is executed, the model may, given the same state (e.g., same set of current radio measurements in different computing / networking nodes), output the same predictions and accuracies / errors estimations.

[0189] For this reason, the input data to the training process may play a major role in the performance of the model. Typically, the more data the model is trained with, the better. But this can be counterproductive in many ways. Training with more data may lead to longer training time and may use more memory space in devices, as well as longer and more intense data treatment functions, computationally speaking. It is therefore useful to address the input to the training of a model before assessing its performance, to balance between the mentioned downsides and the network / WTRU desired accuracies.

[0190] Configuration option in the following description address this problem.

[0191] Training and performance monitoring configuration (definition / size / format of inputs, outputs, models, and performance monitoring criteria) may include model input related parameters, for example, a number of input samples (e.g., an explicit indication from the network on how many samples to use).

[0192] This can be an indication for any data feature (see next step) that the WTRU may use for training purposes. It can be the same for all features, or a different number for any one or more features.

[0193] Training and performance monitoring configuration (definition / size / format of inputs, outputs, models, and performance monitoring criteria) may include specific data features selection for input (e.g., an explicit indication from the network on what data features to use).

[0194] The network may easily specify the exact data features that the WTRU may use, and may indicate those to the WTRU under any representation, e.g., a specific name like “RSRP”, a category like “Radio quantity ID 1”, an abstract ID that is interpreted by both network and WTRU, etc.

[0195] The previous configuration reflects network specific indications. In other methods, the network may configure the WTRU with feature selection methods, where, given method specific thresholds, the WTRU would be able to determine the right features (both in quantity and the specific features) to use for training. The methods are all different, but the principle is similar. One example of such a principle is F-regression. Applying F-regression to a dataset will result intwo outcomes. First, the mathematics of the method will sort the features in order of importance. Order of importance means the features that provide a greater contribution to an accurate inferred output are ranked higher than features provide a lesser contribution to an accurate inferred output. Second, a value attribute of their importance is associated with each feature. Hence, with a threshold value for F-regression, the WTRU would be able to determine the N most important features, filtered by having an associated score higher / lower than the F-regression configured threshold. A list of methods is provided below.

[0196] WTRU-based feature selection-related may indicate any of the following methods: (1) parameters for wrapper; (2) parameters for filter methods; (3) parameters for intrinsic methods; and (4) parameters for other relevant methods.

[0197] Parameters for wrapper may include any of: (1) forward feature selection; (2) backward feature elimination; (3) exhaustive feature selection; and (4) recursive feature elimination.

[0198] Parameters for filter methods may include any of: (1) information gain; (2) Chi-square test; (3) Fisher’s score; (4) correlation coefficient; (5) variance threshold; (6) mean absolute difference (MAD); (7) mean absolute error; and (8) dispersion ratio.

[0199] Parameters for intrinsic methods may include a combination of the above methods

[0200] Parameters for other relevant methods may include any of: (1) F-regression score; (2) power control algorithm (PCA) indication; and (3) correlation thresholds.

[0201] Other training configuration options may include target desired output (e.g., similar to previous embodiments).

[0202] The network may configure the WTRU with a specific model to use for training with any related options given below: (1) model id(s); (2) model functionality (e.g., cluster, classify, regress); and (3) hyperparameter set.

[0203] Model ID(s) may include any explicit or implicit identification form for a specific one or more models. The WTRU may also be configured to train and monitor more than one model and report on all models, a subset, or simply the best performing model

[0204] Model functionality (e.g., cluster, classify, regress) may include some models able to perform more than one inference task and hence there could be a need to distinguish the output type, in association with, e.g., the model ID.

[0205] As stated above, a trained model can be identified by model type and a hyperparameter set of values for that model. The state or set of hyperparameters could be explicitly indicated to the WTRU, i.e., indicating values or ranges for each of the hyperparameters, or for a subset of them,or, e.g., a pre-configured table could be used where, for each one or more hyperparameter, an index value would be used to map hyperparameter values or ranges with that index value.

[0206] The WTRU may be configured with specific prediction accuracy metrics to determine the performance of the one or more models, including, for example: prediction accuracy metrics. Prediction accuracy metrics may comprise absolute / relative thresholds for accuracy metrics, e.g., Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), per beam(s), cell(s) - these are all model and output type dependent. Lis could be extended as the metrics can change per model type, but the principle is the same, one or more metrics for performance assessment.

[0207] In the reporting procedure configuration , some examples of triggers for reporting and the information to be included in the report were given above.

[0208] The WTRU may determine current or predicted future model performance values of the configured AI / ML model based on the training and performance monitoring configuration.

[0209] The WTRU may assess the performance, and may do so for one or more predicted values, if that is the target output.

[0210] Based on the current or predicted future model performance, the WTRU may determine current or predicted future performance monitoring related information and / or absence of a specific model with the configured inference input.

[0211] The WTRU may determine that no such model as configured exists, and report that information to the network. On the other hand, if such a model does exist, the WTRU may determine the model performance-related information, wherein a few examples are given below. Performance monitoring related information may include one or more of: (1) model ID(s), e.g., filter by x best performing models; (2) number of bad performing predicted values (3) good performing predicted values; (4) bad performing predicted values; (5) training time; and (6) minimum / maximum estimated accuracy / error.

[0212] The WTRU may transmit indication of one or more of current or predicted future performance monitoring related information or absence of a specific model with the configured inference inputs.

[0213] The WTRU may transmit indication of one or more of: absence of a specific model with the configured inference inputs, or performance monitoring related information, e.g., via MAC CE, UCI or RRC messages.

[0214] Methods and apparatus are provided for an enhanced data collection process where a WTRU may request (e.g., further) CSLRS resources and / or may transmit collected measurement data towards the network, for network-side AI / ML model training

[0215] If the network uses (e.g., needs) data, e.g., in order to train a model, mechanisms are desired to ensure that data is collected (e.g., only) when necessary and in the most efficient way possible to minimize data transmitted over the air interface. For this, specific new conditions are desired so that the WTRU can trigger data collection reporting. These approaches may lead to more efficient data collection processes. There are various factors that can affect the accuracy of a model and its predicted values. One of them is if the model has been exposed with particular input data characteristics. In these cases, more accurate predictions may be obtained with, e.g., fewer data points as input in training.

[0216] According to embodiments, a WTRU may determine the optimal dataset (e.g., in terms of size and characteristics) for WTRU to network direction data collection purposes based on the determination of sub-optimal performance of an AI / ML model. The WTRU may test different settings for model performance, with a focus on the input data. If the available resource set is not available such that the WTRU cannot comply with the data collection request (the determination of the optimal dataset), the WTRU may trigger a new request to the network to be provided with the required missing or unavailable resource set (e.g., when determining current available dataset is not sufficient to achieve a desired performance, the WTRU will request he network to transmit to the WTRU, e.g., more CSI-RS resources).

[0217] The WTRU may receive one or more measurement configurations (e.g., immediate / logged MDT, L3 measurement configuration).

[0218] The WTRU may receive a configuration with measurement resources and a set of parameters associated with dataset construction, including at least one of the following: (1) criteria for the WTRU to start inferring; (2) performance monitoring configuration (definition of inputs, outputs, models and performance monitoring criteria); (3) reporting criteria (WTRU dataset construction); (4) when to report configuration; and (5) beam related measurements data collection.

[0219] Criteria for the WTRU to start inferring may include any of the following: (1) time related; (2) beam ID related; (3) radio quantity related; (4) layer-sample related; (5) cross layer related; and (6) reception of an indication from the network, explicit (e.g., an indication to start inference) and / or implicit (e.g., reception of reference signals, e.g., CSI-RS from the gNB).

[0220] The performance monitoring configuration (definition of inputs, outputs, models and performance monitoring criteria) may include any of parameters related to: (1) model input related; (2) target desired output; (3) model specific; and (4) prediction accuracy metrics.

[0221] Model input related parameters may include any of: (1) number of input samples (e.g., an explicit indication from the network of how many samples to use); (2) specific data features selection for input (e.g., an explicit indication from the network of what data features to use); and (3) WTRU-based feature selection-related.

[0222] WTRU-based feature selection-related may indicate any of the following methods: (1) parameters for wrapper; (2) parameters for filter methods; (3) parameters for intrinsic methods; and (4) parameters for other relevant methods.

[0223] Parameters for wrapper may include any of: (1) forward feature selection; (2) backward feature elimination; (3) exhaustive feature selection; and (4) recursive feature elimination.

[0224] Parameters for filter methods may include any of: (1) information gain; (2) Chi-square test; (3) Fisher’s score; (4) correlation coefficient; (5) variance threshold; (6) mean absolute difference (MAD); (7) mean absolute error; (8) dispersion ratio; and (9) cosine similarity.

[0225] Parameters for intrinsic methods may include a combination of the above methods

[0226] Parameters for other relevant methods may include any of: (1) F-regression score; (2) power control algorithm (PCA) indication; and (3) correlation thresholds.

[0227] The target desired output may include any of the following parameters: (1) number and / or identity of predicted SSBs available; (2) number of CSI-RS resources available; (3) number and / or identity of predicted good SSB beams; (4) number and / or identity of predicted good CSI- RS beams; (5) SSB ID(s) radio quantity (e.g., RSRP); (6) CSI-RS beam(s) radio quantity (e.g., RSRP); (7) SSB beam failure detection (e.g., with SSB beam ID); and (8) CSI-RS beam failure detection.

[0228] The model specific may include any of the following parameters: (1) associated data configuration or scenario;(2) model ID(s); (3) model metadata; (4) model functionality (e.g., cluster, classify, regress); and (5) hyperparameter set.

[0229] Model metadata may include any one or more of the following, for example: (1) WTRU vendor info; (2) network vendor info; (3) applicable scenario, configuration, site information, supported use case; (4) model performance indicators, model accuracy, model bias, model variance; and (5) model size.

[0230] Prediction accuracy metrics may include absolute / relative thresholds for accuracy metrics (e.g., RMSE, MAE, per beam(s), cell(s) - these are all model and output type dependent -metrics can change per model type, e.g., MSE / Cosine similarity for CSI use case, beam quality for beam management use case, etc.).

[0231] Reporting criteria (WTRU dataset construction) may include any of the following:(1) data features to report (e.g., WTRU to include model input related or other filters to consider);(2) a specific NW configured number of past samples and / or past samples over a specific NW configured time period; and (3) a specific NW configured number of predicted values to report.

[0232] The configuration may be reported on any of the following: (1) report on state transition;(2) report every time number of samples is higher than threshold; (3) report with good radio conditions (e.g., report when SNR>X, RSRP>Y, for any cell, beam); and (4) report via specific NW indication (e.g., via DCI, MAC CE, or RRC messages).

[0233] The beam related measurements data collection may include any of the following: (1) minimum resource set for available SSB beams, e.g., a minimum number of SSB beams; (2) minimum resource set for available CSI-RS beams, e.g., a minimum number of CSI-RS beams;(3) absolute / relative thresholds and / or threshold difference for SSB beams, e.g., RSRP minimum threshold, a specific LI -RSRP variance, LI -RSRP threshold difference between two different beams or for the same beam between two time instances; (4) absolute / relative thresholds for CSI- RS beams; and (5) a time window for the validity of the previous thresholds for any beam, e.g., a time within which the previous thresholds shall hold, a number of consecutive samples to assess the variance, etc.

[0234] The WTRU may determine a first dataset for AI / ML model training based on the set of parameters for dataset construction and configured measurement resources.

[0235] The WTRU may classify the elements of the first dataset into groups, each representing a different data configuration.

[0236] The WTRU may determine whether a group has sufficient data to train an AI / ML model based on configured performance monitoring configuration.

[0237] The WTRU may transmit an indication of one or more of: the first dataset, the identity or a parameter of the set of groups with insufficient data, the identity or a parameter of the set of groups with sufficient data.

[0238] The WTRU may receive a configuration with measurement resources and a set of parameters associated with dataset construction.

[0239] A focus of this embodiment is to have the WTRU determine the optimal dataset for an optimal data collection process. As understood from the previous embodiment, the dataset used for training may influence the performance of a model. On the one hand, it may be useful that the right level of accuracy be achieved. On the other hand, the less data that is collected from the WTRU, the less data collection signaling overhead. So, to strike the balance in this trade-off optimization, the WTRU may be configured in this step with similar parameters as in the previousembodiment for determining the dataset characteristics. This configuration may be explicitly indicated by the network (so the WTRU can determine the dataset itself). The result may be a dataset that can be used for training, and inference procedure, from which will result a performance assessment. This is executed in step 3 by the WTRU.

[0240] The WTRU may determine a first dataset for AI / ML model training based on the set of parameters for dataset construction and configured measurement resources.

[0241] Based on the received input data configuration, the first dataset may be used for the WTRU to train and assess the performance of one or more models.

[0242] The WTRU may classify the elements of the first dataset into groups each representing a different data configuration.

[0243] The WTRU may make this classification by first starting with a target output accuracy and assessing if the first dataset is enough to achieve the desired accuracy. The different groups may represent combinations of features and data input volume. A maximum number of groups may be considered to be all possible data feature combinations with all possible values for number of input data points for each feature. It may be impractical to consider extreme cases like 3 or 4 data points for a feature, as that would not be theoretically sufficient to properly train a model, but all possibilities may be open.

[0244] The WTRU may determine whether a group has sufficient data to train an AI / ML model based on configured performance monitoring configuration.

[0245] The WTRU may partition / classify, with support from network configuration, the different groups with different combinations. From the assessment of the first dataset, there can be two outcomes, namely that the dataset is sufficient, or it is not.

[0246] If it is sufficient, the WTRU may further attempt to reduce its size. This could be done incrementally, e.g., by removing one feature at a time, or by removing a certain number of features. The same principle may be applied with respect to the number of input data points. This may be executed with support from network configuration.

[0247] If it is not sufficient, the WTRU may determine the resources missing in the dataset. This may be done based on assessing, e.g., the correlation values between the target output and the first dataset features, where the WTRU may determine that a number of features have weak correlation. The network may pre-configure the WTRU or the WTRU may have internal knowledge of what are the data features that most highly correlate (this is typically know in the study and training phase of any model before live system deployment).

[0248] The WTRU may also determine, with or without network configuration support, whether highly correlated features have enough training data points. The WTRU may estimate the missing number of data points for a feature, e.g., based on known data wrangling and analysis methods. The WTRU would then be in a position to indicate to the network what the missing resources are so that further data can be collected. The WTRU might indicate that another feature is required / desirable for the model to achieve sufficient accuracy and / or that more datapoints are required / desirable (e.g., by estimating a time period during which those resources would need to be made available so that the estimated number of data points could be collected to enrich the dataset). A simple example of this would be the WTRU assessing the measurement configuration, determining that the configuration instructs it to measure a CSI-RS resource RSRP periodically every 120 ms, estimating that 100 RSRP data points are required to attain a sufficiently accurate output, determining the CSI-RS resource would need to be made available during at least 11.2 seconds, and then performing the data collection for that amount of time.

[0249] The WTRU may transmit an indication of one or more of the first dataset, the identity or a parameter of the set of groups with insufficient data, and the identity or a parameter of the set of groups with sufficient data.

[0250] The WTRU may report to the network informing the network of the determined parameters, and may also include a request for the network to provide the specific resources.

[0251] According to embodiments, the WTRU may perform inference or training of AI / ML model based on configured criteria and reports to network.

[0252] FIG. 4 is a flowchart illustrating an exemplary process for operating an AI / ML model in a WTRU in accordance with at least some of the principles set forth hereinabove.

[0253] At step 401, the WTRU may receive beam measurement configuration information from the network. Such information may comprise such parameters as which reference signals to monitor, which parameters of those reference signals are to be measured (e.g., RSRP, RSRQ, etc.), and how frequently to measure such beam parameters.

[0254] At step 403, the WTRU may receive from the network AI / ML configuration information. This information may comprise one or more AI / ML models to use for beam management, operational parameters of any such AI / ML models, trigger conditions for commencing training of any such models, trigger conditions for generating an inference using any such model, what information to report back to the network about or generated by the AI / ML model, etc.

[0255] Next, in step 405, the WTRU may determine when one of the trigger conditions has been satisfied. The trigger condition(s), for instance, may be a condition indicative of a likelyimpending handover, which, in turn, indicates the likely need for evaluating, configuring, predicting, and / or determining one or more beam-related metrics. Merely as one example, a trigger condition might be a signal strength from the serving cell of the WTRU falling below a threshold.

[0256] Responsive to the detection of the trigger condition, in step 407, the WTRU may trigger the AI / ML model to perform some function, such as generating a beam management-related inference or commencing training.

[0257] At step 409, the WTRU may transmit a report to the network that includes information about or from the AI / ML model that is useful to the network, such as for beam management operations. Such information may comprise, for instance, any output inference of the AI / ML model, training data, etc. The report may be transmitted, for instance, via UCI indication, MAC CE, RRC message, etc.

[0258] According to embodiments, the WTRU may monitor the performance of a beam related AI / ML Model and may report performance monitoring information to the network

[0259] FIG. 5 is a flowchart illustrating a process for evaluating the operation of an AI / ML model in a wireless network in accordance with at least some of the principles set forth hereinabove.

[0260] In step 501, the WTRU may receive beam measurement configuration information from the network. Such information may comprise such parameters as which reference signals to monitor, which parameters of those reference signals are to be measured (e.g., RSRP, RSRQ, etc.), and how frequently to measure such beam parameters.

[0261] In step 503, the WTRU may receive from the network AI / ML configuration information, including AI / ML model performance monitoring configuration information. The performance monitoring configuration information is information that can be used to determine the level of performance of the AI / ML model (e.g., how accurate the inference predictions of the model are). It may, for instance, comprise any one or more of a number of input samples to the AI / ML model, a specific one or more features or a feature selection method with an associated one or more thresholds for input to the AI / ML model, a number and / or identity of predicted System Synchronization Blocks (SSBs) available, a number of Channel State Information Reference Signal (CSI-RS) resources available, a number and / or identity of predicted good SSB beams, a number and / or identity of predicted good CSI-RS beams, a target desired output of the AI / ML model, and a hyperparameter set.

[0262] In step 505, the WTRU may determine at least one performance characteristic of the AI / ML model based on the performance monitoring configuration.

[0263] In step 507, based on the performance characteristic of the AI / ML model, the WTRU may determine performance monitoring related information of the AI / ML model. This may be information that is directly indicative of the accuracy of the model’s predictions. Some examples of potential performance monitoring related information are an identity of the AI / ML model, a number of bad performing predicted values of the AI / ML model, a number of bad performing predicted values of the AI / ML model, bad performing predicted values of the AI / ML model, a training time of the AI / ML model, and an estimated accuracy of the AI / ML model.

[0264] At step 509, the WTRU may transmit the performance monitoring related information to the network.

[0265] Enhanced data collection process is described wherein a WTRU may request further CSL RS Resources and may transmit collected measurement data to the network for network-side AI / ML model training.

[0266] FIG. 6 is a flowchart illustrating a process for determining an optimal dataset for training an AI / ML model in accordance with at least some of the principles set forth hereinabove.

[0267] In step 601, the WTRU may receive beam measurement configuration information from the network. Such information may comprise such parameters as which reference signals to monitor, which parameters of those reference signals are to be measured (e.g., RSRP, RSRQ, etc.), and how frequently to measure such beam parameters.

[0268] In step 603, the WTRU may receive from the network a configuration with measurement resources and a set of parameters associated with input dataset construction for an AI / ML model, including a performance monitoring configuration. The performance monitoring configuration, for example, may comprises definitions of AI / ML inputs, outputs, models, and performance monitoring criteria.

[0269] Next, in step 605, the WTRU may determine a first AI / ML input dataset for training the AI / ML model based on the set of parameters associated with input dataset construction for the AI / ML model. The set of parameters associated with input dataset construction for the AI / ML model may take many forms. For instance, it may comprises a number of input samples to use to train the AI / ML model and / or specific input data features constructed with feature selection methods configuration to use to train the AI / ML model.

[0270] In step 607, the WTRU may form / determine the elements of the first AI / ML input dataset into groups, each group representing a different data configuration comprising a different subset of the elements of the first AI / ML dataset.

[0271] In step 609, the WTRU may determine whether each group has sufficient data to train the AI / ML model based on a configured performance monitoring configuration. The performance monitoring configuration may, for instance, comprise definitions of AI / ML inputs, outputs, models, and performance monitoring criteria. Determining whether each group has sufficient data to train the AI / ML model may comprises training the AI / ML model using each group as the input dataset and evaluating whether the output generated by the AI / ML model using that input dataset meets a performance target.

[0272] At step 611, the WTRU may transmit to the network how the AI / ML model performed for each dataset group. For instance, this data may comprise one or more of the first AI / ML input dataset, an identity of a set of groups with insufficient data to adequately train the AI / ML model, an identity of a set of groups with sufficient data to adequately train the AI / ML model.

[0273] FIG. 7 is a flowchart illustrating an exemplary process for operating an AI / ML model in a WTRU in accordance with at least some of the principles set forth hereinabove.

[0274] In step 710, the WTRU may receive, from a network, at least one measurement configuration for performing measurements of beam parameters.

[0275] In step 720, the WTRU may receive, from the network, configuration information for configuring at least one AI / ML model for predicting beam management parameters in the network, the configuration information including at least one trigger condition for at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model.

[0276] In step 730, the WTRU may determine that the at least one trigger condition has been satisfied, and responsively activating the at least one AI / ML model to at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model.

[0277] In step 740, the WTRU may transmit, to the network, a report comprising first information relating to at least one of: (1) training of the at least one AI / ML model and (2) predictions generated by the at least one AI / ML model.

[0278] According to embodiments, the configuration information for the at least one AI / ML model may comprise at least one of: (1) configuration parameters for operation of the at least one AI / ML model, and (2) second information generated by the at least one AI / ML model that the WTRU is to report to the network.

[0279] According to embodiments, the at least one trigger condition is a condition indicative of a likelihood of an impending handover.

[0280] According to embodiments, the at least one trigger condition is a signal strength from a neighboring cell becomes stronger than a signal strength of a serving cell.

[0281] According to embodiments, the at least one trigger condition is associated with a layer 3 event.

[0282] According to embodiments, the at least one trigger condition is associated with a layer 1 event.

[0283] According to embodiments, the at least one trigger condition is associated with an amount of data in an uplink buffer.

[0284] According to embodiments, the measurements of beam parameters comprise RSRP of at least one beam.

[0285] According to embodiments, the predictions generated by the AI / ML model comprise any of: (1) a number of predicted SSBs available, (2) a number of CSI-RS resources available, (3) a number of predicted SSB beams meeting a first criteria, (4) a number of predicted CSI-RS beams meeting a second criteria, (5) a SSB ID(s) radio quantity, (6) a CSI-RS beam(s) radio quantity, (7) a SSB beam failure detection, and (8) a CSI-RS beam failure detection.

[0286] Although features and elements are provided above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. The present disclosure is not to be limited in terms of the particular embodiments described in this application, which are intended as illustrations of various aspects. Many modifications and variations may be made without departing from its spirit and scope, as will be apparent to those skilled in the art. No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly provided as such. Functionally equivalent methods and apparatuses within the scope of the disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing descriptions. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is to be understood that this disclosure is not limited to particular methods or systems.

[0287] The foregoing embodiments are discussed, for simplicity, with regard to the terminology and structure of infrared capable devices, i.e., infrared emitters and receivers. However, the embodiments discussed are not limited to these systems but may be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves such as acoustic waves.

[0288] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting. As used herein, the term “video” or the term “imagery” may mean any of a snapshot, single image and / or multiple images displayed over a time basis. As another example, when referred to herein, the terms “user equipment” and its abbreviation “UE”, the term “remote” and / or the terms “head mounted display” or its abbreviation “HMD” may mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of a number of embodiments of a WTRU; (iii) a wireless-capable and / or wired-capable (e.g., tetherable) device configured with, inter alia, some or all structures and functionality of a WTRU; (iii) a wireless-capable and / or wired-capable device configured with less than all structures and functionality of a WTRU; or (iv) the like. Details of an example WTRU, which may be representative of any WTRU recited herein, are provided herein with respect to FIGs. 1 A- 1D. As another example, various disclosed embodiments herein supra and infra are described as utilizing a head mounted display. Those skilled in the art will recognize that a device other than the head mounted display may be utilized and some or all of the disclosure and various disclosed embodiments can be modified accordingly without undue experimentation. Examples of such other device may include a drone or other device configured to stream information for providing the adapted reality experience.

[0289] In addition, the methods provided herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer- readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, MME, EPC, AMF, or any host computer.

[0290] Variations of the method, apparatus and system provided above are possible without departing from the scope of the invention. In view of the wide variety of embodiments that can be applied, it should be understood that the illustrated embodiments are examples only, and should not be taken as limiting the scope of the following claims. For instance, the embodiments provided herein include handheld devices, which may include or be utilized with any appropriate voltage source, such as a battery and the like, providing any appropriate voltage.

[0291] Moreover, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices that include processors are noted. These devices may include at least one Central Processing Unit (“CPU”) and memory. In accordance with the practices of persons skilled in the art of computer programming, reference to acts and symbolic representations of operations or instructions may be performed by the various CPUs and memories. Such acts and operations or instructions may be referred to as being “executed”, “computer executed” or “CPU executed”.

[0292] One of ordinary skill in the art will appreciate that the acts and symbolically represented operations or instructions include the manipulation of electrical signals by the CPU. An electrical system represents data bits that can cause a resulting transformation or reduction of the electrical signals and the maintenance of data bits at memory locations in a memory system to thereby reconfigure or otherwise alter the CPU’s operation, as well as other processing of signals. The memory locations where data bits are maintained are physical locations that have particular electrical, magnetic, optical, or organic properties corresponding to or representative of the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs and that other platforms and CPUs may support the provided methods.

[0293] The data bits may also be maintained on a computer readable medium including magnetic disks, optical disks, and any other volatile (e.g., Random Access Memory (RAM)) or non-volatile (e.g., Read-Only Memory (ROM)) mass storage system readable by the CPU. The computer readable medium may include cooperating or interconnected computer readable medium, which exist exclusively on the processing system or are distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories and that other platforms and memories may support the provided methods.

[0294] In an illustrative embodiment, any of the operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer-readable instructions may be executed by a processor of a mobile unit, a network element, and / or any other computing device.

[0295] There is little distinction left between hardware and software implementations of aspects of systems. The use of hardware or software is generally (but not always, in that in certain contexts the choice between hardware and software may become significant) a design choice representing cost versus efficiency tradeoffs. There may be various vehicles by which processes and / or systems and / or other technologies described herein may be effected (e.g., hardware, software, and / orfirmware), and the preferred vehicle may vary with the context in which the processes and / or systems and / or other technologies are deployed. For example, if an implementer determines that speed and accuracy are paramount, the implementer may opt for a mainly hardware and / or firmware vehicle. If flexibility is paramount, the implementer may opt for a mainly software implementation. Alternatively, the implementer may opt for some combination of hardware, software, and / or firmware.

[0296] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of block diagrams, flowcharts, and / or examples. Insofar as such block diagrams, flowcharts, and / or examples include one or more functions and / or operations, it will be understood by those within the art that each function and / or operation within such block diagrams, flowcharts, or examples may be implemented, individually and / or collectively, by a wide range of hardware, software, firmware, or virtually any combination thereof. In an embodiment, several portions of the subject matter described herein may be implemented via Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), digital signal processors (DSPs), and / or other integrated formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein, in whole or in part, may be equivalently implemented in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and / or writing the code for the software and or firmware would be well within the skill of one of skill in the art in light of this disclosure. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein may be distributed as a program product in a variety of forms, and that an illustrative embodiment of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually carry out the distribution. Examples of a signal bearing medium include, but are not limited to, the following: a recordable type medium such as a floppy disk, a hard disk drive, a CD, a DVD, a digital tape, a computer memory, etc., and a transmission type medium such as a digital and / or an analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).

[0297] Those skilled in the art will recognize that it is common within the art to describe devices and / or processes in the fashion set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least aportion of the devices and / or processes described herein may be integrated into a data processing system via a reasonable amount of experimentation. Those having skill in the art will recognize that a typical data processing system may generally include one or more of a system unit housing, a video display device, a memory such as volatile and non-volatile memory, processors such as microprocessors and digital signal processors, computational entities such as operating systems, drivers, graphical user interfaces, and applications programs, one or more interaction devices, such as a touch pad or screen, and / or control systems including feedback loops and control motors (e.g., feedback for sensing position and / or velocity, control motors for moving and / or adjusting components and / or quantities). A typical data processing system may be implemented utilizing any suitable commercially available components, such as those typically found in data computing / communication and / or network computing / communication systems.

[0298] The herein described subject matter sometimes illustrates different components included within, or connected with, different other components. It is to be understood that such depicted architectures are merely examples, and that in fact many other architectures may be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality may be achieved. Hence, any two components herein combined to achieve a particular functionality may be seen as “associated with” each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated may also be viewed as being “operably connected”, or “operably coupled”, to each other to achieve the desired functionality, and any two components capable of being so associated may also be viewed as being “operably couplable” to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and / or physically interacting components and / or wirelessly interactable and / or wirelessly interacting components and / or logically interacting and / or logically interactable components.

[0299] With respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.

[0300] It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as “open” terms (e.g., the term “including” should be interpreted as “including but not limited to,”the term “having” should be interpreted as “having at least,” the term “includes” should be interpreted as “includes but is not limited to,” etc.) and / or “permissive” terms (e.g., the term “is” and / or the term “are” may be interpreted as “may” and / or “might”, the terms ”"refer(s)" may be interpreted as "may refer" and / or "might refer", the terms "receive(s)" may be interpreted as "may receive" and / or "might receive", the terms "support(s)" may be interpreted as "may support" and / or "might support", the terms "interface(s)" may be interpreted as "may interface" and / or "might interface", the terms "transmit(s)" may be interpreted as "may interface" and / or "might interface", "may transmit" and / or "might transmit", the terms "send(s)" may be interpreted as "may send" and / or "might send", the terms "does not refer" (and / or the like) may be interpreted as "may not refer" and / or "might not refer", the terms "does not receive" (and / or the like) may be interpreted as "may not receive" and / or "might not receive", the terms "does not support" (and / or the like) may be interpreted as "may not support" and / or "might not support", the terms "does not interface" (and / or the like) may be interpreted as "may not interface" and / or "might not interface", the terms "does not transmit" (and / or the like) may be interpreted as "may not transmit" and / or "might not transmit", the terms "does not send" (and / or the like) may be interpreted as "may not send" and / or "might not send", etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, where only one item is intended, the term "single" or similar language may be used. As an aid to understanding, the following appended claims and / or the descriptions herein may include usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim including such introduced claim recitation to embodiments including only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an" (e.g., "a" and / or "an" should be interpreted to mean "at least one" or "one or more"). The same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number (e.g., the bare recitation of "two recitations," without other modifiers, means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a systemhaving at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). In those instances where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase "A or B" will be understood to include the possibilities of "A" or "B" or "A and B." Further, the terms "any of followed by a listing of a plurality of items and / or a plurality of categories of items, as used herein, are intended to include "any of," "any combination of," "any multiple of," and / or "any combination of multiples of the items and / or the categories of items, individually or in conjunction with other items and / or other categories of items. Moreover, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, the term "number" is intended to include any number, including zero. And the term "multiple", as used herein, is intended to be synonymous with "a plurality".

[0301] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0302] As will be understood by one skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily recognized as sufficiently describing and enabling the same range being broken down into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed herein may be readily broken down into a lower third, middle third and upper third, etc. As will also be understood by one skilled in the art all language such as "up to," "at least," "greater than," "less than," and the like includes the number recited and refers to ranges which can be subsequently broken down into subranges as discussed above. Finally, as will be understood by one skilled in the art, a range includes each individual member. Thus, for example, a group having 1-3 cells refers to groups having 1, 2, or 3 cells. Similarly, a group having 1-5 cells refers to groups having 1, 2, 3, 4, or 5 cells, and so forth.

[0303] Moreover, the claims should not be read as limited to the provided order or elements unless stated to that effect. In addition, use of the terms "means for" in any claim is intended to invoke 35 U.S.C. §112, T] 6 or means-plus-function claim format, and any claim without the terms "means for" is not so intended.

[0304] Suitable processors include, by way of example, 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), Application Specific Standard Products (ASSPs); Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), and / or a state machine.

[0305] The WTRU may be used in conjunction with modules, implemented in hardware and / or software including a Software Defined Radio (SDR), and other components such as a camera, a video camera module, a videophone, a speakerphone, a vibration device, a speaker, a microphone, a television transceiver, a hands free headset, a keyboard, a Bluetooth® module, a frequency modulated (FM) radio unit, a Near Field Communication (NFC) Module, a liquid crystal display (LCD) display unit, an organic light-emitting diode (OLED) display unit, a digital music player, a media player, a video game player module, an Internet browser, and / or any Wireless Local Area Network (WLAN) or Ultra Wide Band (UWB) module.

[0306] Although the various embodiments have been described in terms of communication systems, it is contemplated that the systems may be implemented in software on microprocessors / general purpose computers (not shown). In certain embodiments, one or more of the functions of the various components may be implemented in software that controls a general- purpose computer.

[0307] In addition, although the invention is illustrated and described herein with reference to specific embodiments, the invention is not intended to be limited to the details shown. Rather, various modifications may be made in the details within the scope and range of equivalents of the claims and without departing from the invention.

Claims

CLAIMS1. A method implemented in a wireless transmit / receive unit (WTRU), the method comprising: receiving, from a network, at least one measurement configuration for performing measurements of beam parameters; receiving, from the network, configuration information for configuring at least one artificial intelligence / machine learning (AI / ML) model for predicting beam management parameters in the network, the configuration information including at least one trigger condition for at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model; determining that the at least one trigger condition has been satisfied, and responsively activating the at least one AI / ML model to at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model; and transmitting, to the network, a report comprising first information relating to at least one of: (1) training of the at least one AI / ML model and (2) predictions generated by the at least one AI / ML model.

2. The method according to claim 1, wherein the configuration information for the at least one AI / ML model comprises at least one of: (1) configuration parameters for operation of the at least one AI / ML model, and (2) second information generated by the at least one AI / ML model that the WTRU is to report to the network.

3. The method according to any of claims 1-2 wherein the at least one trigger condition is a condition indicative of a likelihood of an impending handover.

4. The method according to any of claims 1-2 wherein the at least one trigger condition is a signal strength from a neighboring cell becomes stronger than a signal strength of a serving cell.

5. The method according to any of claims 1-2, wherein the at least one trigger condition is associated with a layer 3 event.

6. The method according to any of claims 1-2, wherein the at least one trigger condition is associated with a layer 1 event.

7. The method according to any of claims 1-2, wherein the at least one trigger condition is associated with an amount of data in an uplink buffer.

8. The method according to any of claims 1-7, wherein the measurements of beam parameters comprise reference signal received strength (RSRP) of at least one beam.

9. The method according to any of claims 1-8, wherein the predictions generated by the AI / ML model comprise any of: (1) a number of predicted synchronization signal blocks (SSBs) available, (2) a number of channel state information reference signal (CSI-RS) resources available, (3) a number of predicted SSB beams meeting a first criteria, (4) a number of predicted CSI-RS beams meeting a second criteria, (5) a SSB ID(s) radio quantity, (6) a CSI-RS beam(s) radio quantity, (7) a SSB beam failure detection, and (8) a CSI-RS beam failure detection.

10. A wireless transmit / receive unit (WTRU) comprising circuitry, including a transmitter, a receiver, a processor and memory, the WTRU configured to: receive, from a network, at least one measurement configuration for performing measurements of beam parameters; receive, from the network, configuration information for configuring at least one artificial intelligence / machine learning (AI / ML) model for predicting beam management parameters in the network, the configuration information including at least one trigger condition for at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model; determine that the at least one trigger condition has been satisfied, and responsively activating the at least one AI / ML model to at least one of: (1) generating the at least one AI / ML model for inference and (2) training the at least one AI / ML model; and transmit, to the network, a report comprising first information relating to at least one of: (1) training of the at least one AI / ML model and (2) predictions generated by the at least one AI / ML model.

11. The WTRU according to claim 10, wherein the configuration information for the at least one AI / ML model comprises at least one of (1) configuration parameters for operation of the at least one AI / ML model, and (2) second information generated by the at least one AI / ML model that the WTRU is to report to the network.

12. The WTRU according to any of claims 10-11, wherein the at least one trigger condition is a condition indicative of a likelihood of an impending handover.

13. The WTRU according to any of claims 10-11, wherein the at least one trigger condition is a signal strength from a neighboring cell becomes stronger than a signal strength of a serving cell.

14. The WTRU according to any of claims 10-11, wherein the at least one trigger condition is associated with a layer 3 event.

15. The WTRU according to any of claims 10-11, wherein the at least one trigger condition is associated with a layer 1 event.

16. The WTRU according to any of claims 10-11, wherein the at least one trigger condition is associated with an amount of data in an uplink buffer.

17. The WTRU according to any of claims 10-16, wherein the measurements of beam parameters comprise reference signal received strength (RSRP) of at least one beam.

18. The WTRU according to any of claims 10-17, wherein the predictions generated by the AI / ML model comprise any of (1) a number of predicted synchronization signal blocks (SSBs) available, (2) a number of channel state information reference signal (CSLRS) resources available, (3) a number of predicted SSB beams meeting a first criteria, (4) a number of predicted CSLRS beams meeting a second criteria, (5) a SSB ID(s) radio quantity, (6) a CSI-RS beam(s) radio quantity, (7) a SSB beam failure detection, and (8) a CSLRS beam failure detection.

Images