Methods, architectures, apparatus and systems for artificial intelligence / machine learning functionality in wireless transmit-receive units

Abstract

Programs, methods, architectures, apparatus, systems, devices, and computer program products are described for a wireless transmit-receive unit (WTRU) in a network for activating artificial intelligence / machine learning (AI / ML) functionality in the WTRU. A WTRU may receive configuration information from a network, the configuration information including information related to at least one AI / ML function that it is to support, and may receive an activation indication from the network related to activation of one or more AI / ML functions by the WTRU. The WTRU may determine at least one AI / ML function that has received the activation indication and may be supported by the WTRU. The WTRU may activate at least one AI / ML function that has received the activation indication and may be supported by the WTRU, and transmit an indication including information related to the activated one or more AI / ML functions to the network.

Description

[0001] Cross-references to related applications This application claims the benefit of U.S. Provisional Patent Application No. 63 / 540464, filed September 26, 2023, which is incorporated herein by reference in its entirety. Background Technology

[0002] This disclosure generally relates to the fields of communications, software, and coding, including, for example, methods, architectures, apparatuses, and systems related to artificial intelligence / machine learning (AI / ML) operations of wireless transmit-receive units (WTRUs) in wireless networks. It is intended to address some of the challenges faced in supporting AI / ML in wireless networks. Summary of the Invention

[0003] The following defines and describes methods and apparatus for improving support for handover and AI / ML functions of wireless transmit-receive units and base stations, and are claimed in accordance with the appended claims. Attached Figure Description

[0004] A more detailed understanding can be obtained through the following detailed description given by way of example, in conjunction with the accompanying drawings. Like the detailed description, the figures in these drawings are illustrative. Accordingly, the figures and detailed description should not be considered limiting, and other equally valid examples are possible and probable. Furthermore, the same reference numerals (“ref”) in the figures indicate the same elements, and wherein: Figure 1A This is a system diagram illustrating an example communication system; Figure 1B The diagram can be found Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) used within a communication system shown; Figure 1C The diagram can be found Figure 1A The system diagram shows an example radio access network (RAN) and an example core network (CN) used within the communication system shown. Figure 1D The diagram can be found Figure 1A The system diagram shows another example RAN and another example CN used in the communication system shown; Figure 2 This is a sequence diagram illustrating the traditional capability reporting of WTRUs in a network; Figure 3 This is a sequence diagram of the handover of WTRU from the source network node to the target network node in a network according to an embodiment; Figure 4 This is a sequence diagram of the handover of WTRU from the source network node to the target network node in a network according to an embodiment; Figure 5 A flowchart of the method according to the embodiment; Figure 6 A flowchart of the method according to the embodiment; Figure 7 A flowchart of the method according to the embodiments; and Figure 8 This is a flowchart of a method according to an embodiment. Detailed Implementation

[0005] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments and / or examples disclosed herein. However, it will be understood that these 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 description below. Furthermore, embodiments and examples not specifically described herein may be practiced in place of or in combination with the embodiments and other examples explicitly, implicitly, and / or inherently described, disclosed, or otherwise provided herein (collectively, the “Provided”). Although various embodiments are described and / or claimed herein (where apparatuses, systems, devices, etc., and / or any elements thereof perform operations, processes, algorithms, functions, etc., and / or any portion thereof), it should be understood that any embodiment described and / or claimed herein assumes that any apparatus, system, device, etc., and / or any element thereof is configured to perform any operation, process, algorithm, function, etc., and / or any portion thereof.

[0006] Abbreviations and acronyms ACK confirmation AI (Artificial Intelligence) BLER block error rate BM Beam Management BWP bandwidth portion CQI Channel Quality Indicator C-RNTI Community - RNTI CSI Channel State Information DL downlink; deep learning DNN (Deep Neural Network) HIT switching interrupt time HO switch LPP LTE positioning protocol LTE Long Term Evolution, for example, from 3GPP LTE R8 and above L1-RSRP Layer 1 -RSRP MAC CE MAC control element ML Machine Learning NACK (Negative ACK) NR New Radio NW Network PDU (Packet Data Unit) PMI Precoding Matrix Indicator PRS Positioning Reference Signal RACH (Random Access Channel or Procedure) RI rank indicator RNTI (Radio Network Temporary Identifier) RRC Radio Resource Control RS reference signal RSRP reference signal received power RSRQ reference signal reception quality RSSI Received Signal Strength Indicator SINR (Signal-to-Interference-plus-Noise Ratio) UE (User Equipment) (see WTRU) UL uplink WTRU Wireless Transmitter-Receiver Unit (see UE).

[0007] Example Communication System The methods, apparatus, and systems provided herein are well-suited for communications involving both wired and wireless networks. (See reference...) Figure 1A-1D An overview of various types of wireless devices and infrastructures is provided, in which various elements of the network can utilize, perform, be arranged according to, and / or be adapted and / or configured for the following: the methods, apparatuses and systems provided herein.

[0008] Figure 1A This is a system diagram illustrating an example communication system 100 that may implement one or more of the disclosed embodiments. Communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, and broadcasting to multiple wireless users. Communication system 100 enables multiple wireless users to access such content by sharing system resources, including wireless bandwidth. For example, communication system 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), Single Carrier FDMA (SC-FDMA), Zero-Tail (ZT) Unique Word (UW) Discrete Fourier Transform (DFT) Spread Spectrum OFDM (ZT UW DTS-s OFDM), Unique Word OFDM (UW-OFDM), Resource Block Filtered OFDM, Filter Bank Multicarrier (FBMC), and the like.

[0009] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112. However, it will be appreciated that the disclosed embodiments are contemplated to 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. For example, WTRU 102a, 102b, 102c, and 102d—any of which can be referred to as a “station” and / or “STA”—can be configured to transmit and / or receive wireless signals and can include (or) user equipment (UE), mobile stations, fixed or mobile subscriber units, subscription-based units, pagers, cellular phones, personal digital assistants (PDAs), smartphones, laptops, netbooks, personal computers, wireless sensors, hotspots or Mi-Fi devices, Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in industrial and / or automated processing chain environments), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, and the like. Any of WTRU 102a, 102b, 102c, and 102d can be interchangeably referred to as a UE.

[0010] The communication system 100 may also include base station 114a and / or base station 114b. Each of base stations 114a and 114b may be any type of device configured to wirelessly interface with at least one of WTRUs 102a, 102b, 102c, and 102d, for example, to facilitate access to one or more communication networks, such as CN106 / 115, Internet 110, and / or Network 112. For example, base stations 114a and 114b may be base transceiver stations (BTS), Node-B (NB), eNode B (eNB), home Node B (HNB), home eNode B (HeNB), gNode-B (gNB), NRNode-B (NR NB), site controllers, access points (APs), wireless routers, and any of the like. Although base stations 114a and 114b are each depicted as a single element, it will be appreciated that base stations 114a and 114b may include any number of interconnected base station and / or network elements.

[0011] Base station 114a may be part of RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as base station controllers (BSCs), radio network controllers (RNCs), relay nodes, etc. Base station 114a and / or base station 114b may be configured to transmit and / or receive radio signals on one or more carrier frequencies, which may be referred to as cells (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 radio services to a specific geographic area, which may be relatively fixed or may change over time. The cell may also be divided into cell sectors. For example, the cell associated with base station 114a may be divided into three sectors. Thus, in one embodiment, base station 114a may include three transceivers, i.e., one transceiver per sector of the cell. In one embodiment, base station 114a may employ multiple-input multiple-output (MIMO) technology and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming can be used to transmit and / or receive signals in a desired spatial direction.

[0012] Base stations 114a and 114b can communicate with one or more of WTRUs 102a, 102b, 102c, and 102d via air interface 116. Air interface 116 can be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). Any suitable radio access technology (RAT) can be used to establish air interface 116.

[0013] More specifically, as described above, the communication system 100 can be a multiple access system and can employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, base stations 114a and WTRUs 102a, 102b, and 102c in RAN 104 / 113 can implement radio technologies such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which can establish an 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).

[0014] In one embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which can establish an air interface 116 using Long Term Evolution (LTE) and / or Advanced LTE (LTE-A) and / or Advanced LTE Pro (LTE-A Pro).

[0015] In one embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as NR radio access, which can establish an air interface 116 using a new radio (NR).

[0016] In one embodiment, base station 114a and WTRUs 102a, 102b, and 102c can implement multiple radio access technologies. For example, base station 114a and WTRUs 102a, 102b, and 102c can implement LTE radio access and NR radio access together, for example, using the dual connectivity (DC) principle. Therefore, the air interface utilized by WTRUs 102a, 102b, and 102c can be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0017] In one embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as IEEE 802.11 (i.e., Wi-Fi), IEEE 802.16 (i.e., Global Microwave Access Interoperability (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Provisional Standard 2000 (IS-2000), Provisional Standard 95 (IS-95), Provisional Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE), GSMEDGE (GERAN), and the like.

[0018] Figure 1ABase station 114b can be, for example, a wireless router, a home Node B, a home eNode B, or an access point, and can utilize any suitable RAT to facilitate wireless connectivity in local areas such as commercial locations, homes, vehicles, campuses, industrial facilities, air corridors (e.g., for drone use), roads, and the like. In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.11 to establish a wireless local area network (WLAN). In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.15 to establish a wireless personal area network (WPAN). In one embodiment, base station 114b and WTRUs 102c, 102d can utilize cellular-based RATs (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-APro, NR, etc.) to establish any of small cells, picocells, or femtocells. Figure 1A As shown, base station 114b can be directly connected to Internet 110. Therefore, base station 114b does not need to access Internet 110 via CN 106 / 115.

[0019] RAN 104 / 113 can communicate with CN 106 / 115, which can be any type of network configured to provide voice, data, application, and / or Voice over Internet Protocol (VoIP) services to one or more of WTRUs 102a, 102b, 102c, and 102d. Data can have different Quality of Service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. CN 106 / 115 can provide call control, billing services, location-based services, prepaid calling, internet connectivity, video distribution, and / or perform advanced security functions such as user authentication. Although in Figure 1A Although not shown, it will be understood that RAN 104 / 113 and / or CN106 / 115 can communicate directly or indirectly with other RANs that use the same RAT as or a different RAT than RAN 104 / 113. For example, in addition to being connected to RAN 104 / 113, which may utilize NR radio technology, CN106 / 115 can also communicate with another RAN (not shown) that uses any of the following radio technologies: GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi.

[0020] CN 106 / 115 can also serve as a gateway for WTRU 102a, 102b, 102c, 102d to access PSTN 108, the Internet 110, and / or other networks 112. PSTN 108 may include a circuit-switched telephone network providing Common Old-Style Telephone Service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices using common communication protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and / or Internet Protocol (IP) from the TCP / IP Internet Protocol suite. Network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, network 112 may include another CN connected to one or more RANs, which may use the same RAT as RAN 104 / 114 or a different RAT.

[0021] Some or all of the WTRUs 102a, 102b, 102c, and 102d in the communication system 100 may include multi-mode capability (e.g., WTRUs 102a, 102b, 102c, and 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). For example... Figure 1A The WTRU 102c shown can be configured to communicate with base station 114a, which can employ cellular-based radio technology, and with base station 114b, which can employ IEEE 802 radio technology.

[0022] Figure 1B This is a system diagram illustrating the example WTRU 102. (Example: ...) Figure 1B As shown, WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keyboard 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power supply 134, a Global Positioning System (GPS) chipset 136, and / or other components / peripherals 138, etc. It will be appreciated that WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with the embodiments.

[0023] Processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, and the like. Processor 118 may perform signal encoding, data processing, power control, input / output processing, and / or any other function that enables WTRU 102 to operate in a wireless environment. Processor 118 may be coupled to transceiver 120, and transceiver 120 may be coupled to transmitting / receiving element 122. Although Figure 1B While the processor 118 and transceiver 120 are depicted as separate components, it will be understood that the processor 118 and transceiver 120 can be integrated together in, for example, an electronic package or chip.

[0024] Transmitting / receiving element 122 can be configured to transmit signals to or receive signals from a base station (e.g., base station 114a) via air interface 116. For example, in one embodiment, transmitting / receiving element 122 can be an antenna configured to transmit and / or receive RF signals. In one embodiment, transmitting / receiving element 122 can be, for example, a transmitter / detector configured to transmit and / or receive IR, UV, or visible light signals. In one embodiment, transmitting / receiving element 122 can be configured to transmit and / or receive both RF and optical signals. It will be appreciated that transmitting / receiving element 122 can be configured to transmit and / or receive any combination of wireless signals.

[0025] Despite Figure 1B While the transmit / receive element 122 is described as a single element, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Therefore, 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 via the air interface 116.

[0026] Transceiver 120 can be configured to modulate signals to be transmitted by transmitting / receiving element 122 and demodulate signals received by transmitting / receiving element 122. As described above, WTRU 102 can have multimode capability. Therefore, transceiver 120 can include multiple transceivers for example enabling WTRU 102 to communicate via multiple RATs (such as NR and IEEE 802.11).

[0027] The processor 118 of WTRU 102 can be coupled to and receive user input data from: a speaker / microphone 124, a keyboard 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) unit or an organic light-emitting diode (OLED) display unit). The processor 118 can also output user data to the speaker / microphone 124, keyboard 126, and / or display / touchpad 128. Furthermore, the processor 118 can access information from and store data in any suitable type of memory (such as non-removable memory 130 and / or removable memory 132). 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. Removable memory 132 may include a subscriber identity module (SIM) card, memory stick, secure digital storage (SD) card, and the like. In other embodiments, the processor 118 can access information from and store data in memory that is not physically located on WTRU 102 (such as a server or home computer (not shown)).

[0028] The processor 118 may receive power from the power supply 134 and may be configured to distribute and / or control power to other components in the WTRU 102. The power supply 134 may be any suitable device for powering the WTRU 102. For example, the power supply 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.

[0029] The processor 118 may also be coupled to a GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) about the current location of the WTRU 102. In addition to, or instead of, information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) via the air interface 116, and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information using any suitable location determination method while remaining consistent with the embodiments.

[0030] Processor 118 may be further coupled to other components / peripherals 138, which may include one or more software and / or hardware modules / units providing additional features, functions, and / or wired or wireless connectivity. For example, component / peripheral 138 may include accelerometers, electronic compasses, satellite transceivers, digital cameras (e.g., for photos and / or video), Universal Serial Bus (USB) ports, vibration devices, television transceivers, hands-free headsets, Bluetooth modules, FM radio units, digital music players, media players, video game player modules, internet browsers, virtual reality and / or augmented reality (VR / AR) devices, activity trackers, and the like. Component / peripheral 138 may include one or more sensors, which may be one or more of the following: gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors, geolocation sensors, altimeters, light sensors, touch sensors, magnetometers, barometers, attitude sensors, biosensors, and / or humidity sensors.

[0031] WTRU 102 may include a full-duplex radio for which transmission and reception of some or all signals (e.g., associated with a specific subframe for both 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 to reduce and / or substantially eliminate self-interference via hardware (e.g., a choke) or via signal processing by a processor (e.g., a separate processor (not shown) or via processor 118). In one embodiment, WTRU 102 may include a half-duplex radio for which transmission and reception of some or all signals (e.g., associated with a specific subframe for either uplink (e.g., for transmission) or downlink (e.g., for reception) may be concurrent.

[0032] Figure 1C This is a system diagram illustrating RAN 104 and CN 106 according to one embodiment. As described above, RAN 104 can communicate with WTRUs 102a, 102b, and 102c via air interface 116 using E-UTRA radio technology. RAN 104 can also communicate with CN 106.

[0033] RAN 104 may include eNode-Bs 160a, 160b, and 160c, although it will be understood that RAN 104 may include any number of eNode-Bs while remaining consistent with the embodiments. eNode-Bs 160a, 160b, and 160c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, eNode-Bs 160a, 160b, and 160c may implement MIMO technology. Thus, for example, eNode-B 160a may use multiple antennas to transmit and receive radio signals from WTRU 102a.

[0034] Each of the eNode-B 160a, 160b, and 160c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, user scheduling in the uplink (UL) and / or downlink (DL), and the like. Figure 1C As shown, eNode-B 160a, 160b, and 160c can communicate with each other via the X2 interface.

[0035] Figure 1C The CN 106 shown may include a Mobility Management Entity (MME) 162, a Serving Gateway (SGW) 164, and a Packet Data Network (PDN) Gateway (PGW) 166. While each of the foregoing elements is depicted as part of CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0036] The MME 162 can connect to each of the eNode-Bs 160a, 160b, and 160c in RAN 104 via the S1 interface and can be used as a control node. For example, the MME 162 can be responsible for authenticating users of WTRUs 102a, 102b, and 102c, bearer activation / deactivation, selecting a specific serving gateway during the initial attachment of WTRUs 102a, 102b, and 102c, and so on. The MME 162 can provide control plane functions for switching between RAN 104 and other RANs (not shown) employing other radio technologies such as GSM and / or WCDMA.

[0037] The SGW 164 can connect to each of the eNode-Bs 160a, 160b, and 160c in RAN 104 via the S1 interface. The SGW 164 can typically route and forward user data packets to / from WTRUs 102a, 102b, and 102c. The SGW 164 can perform other functions such as anchoring the user plane during inter-eNode-B handover, triggering paging when DL data is available for WTRUs 102a, 102b, and 102c, managing and storing the context of WTRUs 102a, 102b, and 102c, and so on.

[0038] The SGW 164 can be connected to the PGW 166, which can provide WTRU 102a, 102b, 102c with access to packet-switched networks (such as Internet 110) to facilitate communication between WTRU 102a, 102b, 102c and IP-enabled devices.

[0039] CN 106 can facilitate communication with other networks. For example, CN 106 can provide WTRU 102a, 102b, 102c with access to a circuit-switched network such as PSTN 108 to facilitate communication between WTRU 102a, 102b, 102c and conventional landline communication equipment. For example, CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) serving as an interface between CN 106 and PSTN 108. Furthermore, CN 106 can provide WTRU 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0040] Despite WTRU in Figures 1A-1D While described as a wireless terminal, it is envisioned that in some representative embodiments, such a terminal may (e.g., temporarily or permanently) use a wired communication interface with a communication network.

[0041] In a representative embodiment, another network 112 may be a WLAN.

[0042] In Infrastructure Basic Services Set (BSS) mode, a WLAN may have an Access Point (AP) for the BSS and one or more Stations (STAs) associated with the AP. The AP may have access to or interfacing with a Distributed System (DS) or carry services within and / or out of the BSS to another type of wired / wireless network. Traffic originating outside the BSS destined for a STA can reach and be delivered to the STA via the AP. Traffic originating from a STA destined outside the BSS can be sent to the AP for delivery to the appropriate destination. For example, traffic between STAs within the BSS can be sent via the AP, where the source STA can send traffic to the AP, and the AP can deliver traffic to the destination STA. Traffic between STAs within the BSS can be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic can be sent between a source STA and a destination STA (e.g., directly between the source STA and the destination STA) using Direct Link Establishment (DLS). In some representative embodiments, the DLS may use 802.11e DLS or 802.11z Tunneled DLS (TDLS). A WLAN using the Standalone BSS (IBSS) mode may not have an access point (AP), and STAs within the IBSS or using the IBSS (e.g., all STAs) can communicate directly with each other. The IBSS communication mode is sometimes referred to as the "self-organizing" communication mode in this document.

[0043] When using 802.11ac infrastructure operating mode or a similar operating mode, the AP can transmit beacons on a fixed channel, such as the primary channel. The primary channel can be of a fixed width (e.g., a wide bandwidth of 20 MHz) or dynamically set via signaling. The primary channel can be the operating channel of the BSS and can be used by the STA to establish a connection with the AP. In some representative embodiments, such as in an 802.11 system, Carrier Sense Multiple Access (CSMA / CA) with collision avoidance can be implemented. For CSMA / CA, each STA, including the AP, can listen on the primary channel. If the primary channel is listened to / detected by a particular STA and / or determined to be busy, that particular STA can back off. A single STA (e.g., only one station) can transmit at any given time within a given BSS.

[0044] High-throughput (HT) STAs can communicate using a 40 MHz wide channel, for example, by combining a primary 20 MHz channel with adjacent or non-adjacent 20 MHz channels.

[0045] Very High Throughput (VHT) STAs can support channels with widths of 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz. 40 MHz and / or 80 MHz channels can be formed by combining adjacent 20 MHz channels. A 160 MHz channel can be formed by combining eight adjacent 20 MHz channels, or by combining two non-adjacent 80 MHz channels—this can be referred to as an 80+80 configuration. For the 80+80 configuration, after channel coding, the data passes through a segment parser, which splits the data into two streams. Each stream can be processed separately using Inverse Fast Fourier Transform (IFFT) and time-domain processing. These streams can be mapped onto two 80 MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above operations for the 80+80 configuration can be reversed, and the combined data can be sent to the Media Access Control (MAC) layer, entities, etc.

[0046] 802.11af and 802.11ah support sub-1 GHz operating modes. Compared to the operating modes used in 802.11n and 802.11ac, the channel operating bandwidth and carrier in 802.11af and 802.11ah are reduced. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV Blank (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support metering-type control / machine-type communication (MTC), such as MTC devices in macro coverage areas. MTC devices may have certain capabilities (e.g., limited capabilities), including support (e.g., only support) certain and / or limited bandwidths. MTC devices may include batteries with a battery life exceeding a threshold (e.g., to maintain a very long battery life).

[0047] WLAN systems that support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) include channels that can be designated as primary channels. The bandwidth of the primary channel can be equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be set and / or limited by the STAs that support the minimum bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for STAs that support (e.g., only support) the 1 MHz mode (e.g., MTC type devices), the primary channel can be 1 MHz wide, 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 Sense and / or Network Assignment Vector (NAV) settings can depend on the status of the primary channel. If the primary channel is busy, for example because an STA (which only supports the 1 MHz operating mode) is transmitting to the AP, the entire available band can be considered busy, even if most of the band remains idle and can be available.

[0048] In the United States, the available frequency bands for 802.11ah are from 902 MHz to 928 MHz. In South Korea, the available bands are from 917.5 MHz to 923.5 MHz. In Japan, the available bands are from 916.5 MHz to 927.5 MHz. The total available bandwidth for 802.11ah is 6 MHz to 26 MHz, depending on the status code.

[0049] Figure 1D This diagram illustrates a system diagram of RAN 113 and CN 115 according to one embodiment. As described above, RAN 113 can communicate with WTRUs 102a, 102b, and 102c via air interface 116 using NR radio technology. RAN 113 can also communicate with CN 115.

[0050] RAN 113 may include gNBs 180a, 180b, and 180c, although it should be understood that RAN 113 may include any number of gNBs while remaining consistent with the embodiments. gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, gNBs 180a, 180b, and 180c may implement MIMO technology. For example, gNBs 180a and 180b may utilize beamforming to transmit signals to and / or receive signals from WTRUs 102a, 102b, and 102c. Thus, for example, gNB 180a may use multiple antennas to transmit radio signals to and / or receive radio signals from WTRU 102a. In one embodiment, gNBs 180a, 180b, and 180c can implement carrier aggregation technology. For example, gNB 180a can transmit multiple component carriers (not shown) to WTRU 102a. A subset of these component carriers may be on unlicensed spectrum, while the remaining component carriers may be on licensed spectrum. In one embodiment, gNBs 180a, 180b, and 180c can implement Coordinated Multipoint (CoMP) technology. For example, WTRU 102a can receive coordinated transmissions from gNBs 180a and 180b (and / or gNB 180c).

[0051] WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using transmissions associated with scalable digitization. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing can differ for different transmissions, different cells, and / or different portions of the radio transmission spectrum. WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using subframes or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing different numbers of OFDM symbols and / or varying absolute durations).

[0052] gNBs 180a, 180b, and 180c can be configured to communicate with WTRUs 102a, 102b, and 102c in standalone and / or non-standalone configurations. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c without access to other RANs (e.g., eNode-B160a, 160b, and 160c). In standalone configuration, WTRUs 102a, 102b, and 102c can utilize one or more of gNBs 180a, 180b, and 180c as mobility anchors. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using signals in unlicensed frequency bands. In a non-standalone configuration, WTRUs 102a, 102b, and 102c can communicate / connect with gNBs 180a, 180b, and 180c, while also communicating / connecting with another RAN such as eNode-Bs 160a, 160b, and 160c. For example, WTRUs 102a, 102b, and 102c can implement DC principles to communicate substantially simultaneously with one or more gNBs 180a, 180b, and 180c, as well as one or more eNode-Bs 160a, 160b, and 160c. In a non-standalone configuration, eNode-Bs 160a, 160b, and 160c can act as mobility anchors for WTRUs 102a, 102b, and 102c, and gNBs 180a, 180b, and 180c can provide additional coverage and / or throughput for serving WTRUs 102a, 102b, and 102c.

[0053] Each of gNBs 180a, 180b, and 180c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, network slicing support, dual connectivity, interoperability between NR and E-UTRA, routing of user plane data to User Plane Functions (UPF) 184a and 184b, routing of control plane information to Access and Mobility Management Functions (AMF) 182a and 182b, and the like. Figure 1D As shown, gNB 180a, 180b, and 180c can communicate with each other via the Xn interface.

[0054] Figure 1DThe CN 115 shown may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and at least one Data Network (DN) 185a, 185b. While each of the foregoing elements is depicted as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0055] AMF 182a and 182b can connect to one or more of gNBs 180a, 180b, and 180c in RAN 113 via the N2 interface and can be used as control nodes. For example, AMF 182a and 182b can be responsible for authenticating users of WTRU102a, 102b, and 102c, supporting network slicing (e.g., handling different Protocol Data Unit (PDU) sessions with different requirements), selecting specific SMF 183a and 183b, managing registration areas, terminating NAS signaling, mobility management, and so on. AMF 182a and 182b can use network slicing, for example, to customize CN support for WTRU102a, 102b, and 102c based on the service types being used by WTRU102a, 102b, and 102c. For example, different network slices can be established for different use cases, such as services relying on Ultra Reliable Low Latency (URLLC) access, services relying on Enhanced Massive Mobile Broadband (eMBB) access, services for MTC access, and / or the like. AMF 162 can provide control plane functions for switching between RAN 113 and other RANs (not shown) employing other radio technologies such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as Wi-Fi.

[0056] SMFs 183a and 183b can connect to AMFs 182a and 182b in CN 115 via the N11 interface. SMFs 183a and 183b can also connect to UPFs 184a and 184b in CN 115 via the N4 interface. SMFs 183a and 183b can select and control UPFs 184a and 184b, and configure service routes through UPFs 184a and 184b. SMFs 183a and 183b can perform other functions, such as managing and assigning UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and so on. PDU session types can be IP-based, non-IP-based, Ethernet-based, and so on.

[0057] UPF 184a and 184b can be connected via an N3 interface to one or more of gNB 180a, 180b, and 180c in RAN 113. This N3 interface can provide WTRU 102a, 102b, and 102c with access to packet-switched networks (such as the Internet 110), for example, to facilitate communication between WTRU 102a, 102b, 102c and IP-enabled devices. UPF 184 and 184b can perform other functions such as routing and forwarding packets, enforcing user plane policies, supporting multi-destination PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and so on.

[0058] CN 115 can facilitate communication with other networks. For example, CN 115 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) acting as an interface between CN 115 and PSTN 108. Furthermore, CN 115 can provide WTRUs 102a, 102b, and 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In one embodiment, WTRUs 102a, 102b, and 102c may be connected to local DNs 185a and 185b via the N3 interface to UPFs 184a and 184b and the N6 interface between UPFs 184a and 184b and data networks (DNs) 185a and 185b.

[0059] Given Figures 1A-1D and Figures 1A-1D The corresponding descriptions herein refer to the functions of WTRU 102a-d, base station 114a-b, eNode-B 160a-c, MME 162, SGW164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other component / device described herein, which may be performed by one or more emulated components / devices (not shown). An emulation device may be one or more devices configured to emulate one or more of the functions described herein. For example, an emulation device may be used to test other devices and / or simulate network and / or WTRU functions.

[0060] Simulation devices can be designed to perform one or more tests on other devices in a laboratory environment and / or a carrier network environment. For example, one or more simulation devices can perform one or more functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. One or more simulation devices can perform one or more functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. Simulation devices can be directly coupled to another device for testing purposes and / or can perform tests using over-the-air wireless communication.

[0061] One or more emulation devices may perform one or more functions (including all functions) but are not implemented / deployed as part of a wired and / or wireless communication network. For example, emulation devices may be used in test scenarios in a test laboratory and / or in non-deployed (e.g., testing) wired and / or wireless communication networks to perform testing of one or more components. One or more emulation devices may be test equipment. Emulation devices may transmit and / or receive data using direct RF coupling and / or wireless communication via RF circuitry (e.g., which may include one or more antennas).

[0062] Introduction / Terminology One or more “baseline” AI / ML (sub) functions and / or (sub) use cases may correspond to any one or more of the following: AI / ML (sub)functions and / or (sub)use cases where traditional operations are not configured in WTRU; AI / ML (sub)functions and / or (sub)use cases where traditional operations are configured in WTRU but may involve significant overhead (e.g., CSI-RS for CSI / beam management, PRS for positioning). AI / ML (sub)functions and / or (sub)use cases, where the traditional operation is configured in WTRU, are understood to be used as a backup option only when the corresponding AI / ML (sub)functions and / or (sub)use cases are unavailable, such as unavailable during handover, unavailable immediately after handover, or when the target cell (target network node, destination network node / cell) of the same set that does not support (one or more) AI / ML (sub)functions and / or (sub)use cases is unavailable. AI / ML (sub)functions and / or (sub)use cases where conventional operations are configured in WTRU, but AI / ML model operations are much more efficient in terms of overhead, accuracy, latency, etc. (for example, when the best beam predicted by the AI / ML model is the actual "best" beam (with the highest RSRP) compared to the best beam found by conventional beam scanning methods).

[0063] "Baseline" AI / ML functionality can be understood as AI / ML functionality to be presented to support a given desired AI / ML model implementation.

[0064] The term "source cell" can be used interchangeably with "source network node" / "gNB" or simply "source".

[0065] The target “cell” can be used interchangeably with the target “network node” / “gNB” or simply “target”.

[0066] The term "traditional" refers to mechanisms based on non-AIML, which serve as possible alternatives to their AI / ML counterparts.

[0067] AIML-related actions / AIML-based actions refer to any action taken by a WTRU or / and associated WTRU behavior that is influenced by predictions of one or more metrics (e.g., radio link quality, buffer level, etc.) made by an AIML model / function. For example, this could be a handover execution, where the handover action is triggered by the satisfaction of a condition of an event associated with the handover action, and the event condition is related to a threshold that is compared to one or more measurements and / or predictions (e.g., measured / predicted RSRP measurements).

[0068] Artificial intelligence (AI). Artificial intelligence can be broadly defined as the behavior exhibited by machines that mimic cognitive functions to sense, reason, adapt, and act.

[0069] Machine Learning (ML): General Principles, Concepts of Deep Learning, Autoencoders, and AI / ML Models.

[0070] ML, General Principles: Machine learning can refer to a type of algorithm that solves problems by learning from experience (“data”) without being explicitly programmed (“configuration of a rule set”). Machine learning can be considered a subset of AI. Different machine learning paradigms can be envisioned based on the nature of the data or feedback available for learning the algorithm. For example, supervised learning methods may involve learning a function that maps inputs to outputs based on labeled training examples, where each training example can be a pair of inputs and corresponding outputs. For example, unsupervised learning methods may involve detecting patterns in data without pre-existing labels. For example, reinforcement learning methods may involve performing a series of actions in an environment to maximize cumulative rewards. In some solutions, combinations or interpolations of the above methods may be used to apply machine learning algorithms. For example, semi-supervised learning methods may use a combination of a small amount of labeled data and a large amount of unlabeled data during training. In this respect, semi-supervised learning lies between unsupervised learning (without labeled training data) and supervised learning (with only labeled training data).

[0071] ML, Deep Learning: Deep learning refers to a class of machine learning algorithms that employ artificial neural networks (especially DNNs), which are largely inspired by biological systems. Deep neural networks (DNNs) are a special type of machine learning model inspired by the human brain, where the input is linearly transformed and passed multiple times through a non-linear activation function. DNNs typically consist of multiple layers, each composed of a linear transformation and a given non-linear activation function. DNNs can be trained using training data via the backpropagation algorithm. Recently, DNNs have demonstrated state-of-the-art performance in various fields (e.g., speech, vision, natural language processing, etc.) and in a variety of supervised, unsupervised, and semi-supervised machine learning settings.

[0072] ML, Autoencoder: An autoencoder is a specific category of DNN that emerges in the context of unsupervised machine learning settings, where a DNN-based encoder nonlinearly transforms high-dimensional data into lower-dimensional latent vectors, and then a nonlinear decoder uses the lower-dimensional latent vectors to regenerate the high-dimensional data. The encoder is represented as... Where x is high-dimensional data and These represent the parameters of the encoder. The decoder is represented as... , where z is a low-dimensional implicit representation and This represents the encoder's parameters. Additionally, training data is used. An autoencoder can be trained by solving the following optimization problem: .

[0073] The above problem can be approximately solved using the backpropagation algorithm. (Trained encoder) It can be used to compress high-dimensional data, and the trained decoder It can be used to decompress implicit representations.

[0074] The terms Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Deep Neural Networks (DNN) are used interchangeably. The methods described in this article are illustrated using examples of learning in wireless communication systems. These methods are not limited to such scenarios, systems, and services, and can be applied to any type of transmission and / or service, etc.

[0075] ML: AI / ML model. Throughout this disclosure, “AIML model,” “AI / ML model,” “ML model,” and “model” are used interchangeably to refer to an artificial intelligence / machine learning model that simulates logical decision-making based on available / collected / requested data.

[0076] Principles and Observations The WTRU for determining the applicability of AI / ML operations can be one or more of the following: AIML features / models used / activated in the source cell; AIML features / models that may be used / activated in the source cell but not activated (but the target cell is now trying to activate them); Any AIML features / models that the target cell is trying to activate; WTRU may have configured some indicators / flags for AIML functions / models, which must be checked for applicability in the target during the HO phase (e.g., in the HO command, even before the HO command in a previous RRC reconfiguration, etc.). How the activation of AI / ML for one function affects the AI / ML capabilities / operations of another function; How does model swapping or regression of one function affect the AI / ML capabilities / operations of another function? How to define mandatory and optional capabilities, and how they affect WTRU behavior; How to indicate dynamic capabilities when the model becomes applicable (e.g., appropriate channel conditions / NW configuration, etc.) or when the use of the model becomes possible (e.g., availability of processing capabilities); The WTRU receives activation instructions from a third party unfamiliar with UL and DL services. The transmission of the model inference output requires resources on the Uu link.

[0077] Components of the embodiment [(one or more) "baseline" AI / ML (sub)functions and / or (sub)use cases] According to one embodiment, the WTRU may be pre-configured with content considered as "baseline" AI / ML (sub)functions and / or (sub)use cases, such that the list of (one or more) "baseline" AI / ML (sub)functions and / or (sub)use cases remains unchanged. According to another embodiment, during RRC (re)configuration, the WTRU may be configured with content considered as "baseline" AI / ML (sub)functions and / or (sub)use cases. According to one embodiment, if there is an update regarding the content of the "baseline" AI / ML (sub)functions and / or (sub)use cases as perceived by the NW, the WTRU may receive the update (e.g., from the NW). For example, after a high-performance AI / ML model for CSI prediction is downloaded (e.g., from the NW), the NW may consider the AI / ML-based CSI prediction as a "baseline" (sub)function and / or (sub)use case, and send an updated list if it was not previously considered a "baseline".

[0078] [WTRU can receive activation instructions] WTRU can receive any one or more of the following activation instructions A)-B) from NW / third party / gNB: A) (one or more) AI / ML models, A1)-A3): A1) For example, WTRU can receive an instruction to activate an AI / ML model for CSI prediction. A2) For example, the WTRU can receive an instruction to activate AI / ML-enabled CSI prediction. This may or may not be accompanied by an identifier of the relevant model to be activated. In the absence of an identifier of the relevant model to be activated, the WTRU can activate any AI / ML model it has for CSI prediction. The WTRU can indicate to the NW / gNB the AI / ML it has already selected for CSI prediction. The model selected for activation by the WTRU may also be subject to the capabilities of the WTRU (e.g., available processing power at the WTRU, the WTRU storage, etc.). A3) When an indication is provided that the relevant model is to be activated, the WTRU can simply activate the relevant model, provided that the WTRU is capable of doing so (subject to the capabilities of the WTRU, such as the WTRU's storage / processing capacity). B) (one or more) AI / ML (sub)functions and / or (sub)use cases, B1)-B3): B1) For example, the WTRU can receive an instruction to activate beam prediction with AI / ML enabled. B2) For example, the WTRU can receive an instruction to activate and enable temporal beam prediction for AI / ML. B3) For example, WTRU can receive an instruction to activate CSI prediction with AI / ML enabled.

[0079] In response to an activation instruction from NW, WTRU may perform any one or more of the following A)-E): A) Activate (one or more) relevant AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models; B) Determine whether it can activate (one or more) related AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models, for example, based on WTRU capabilities (e.g., WTRU processing capacity, WTRU storage, etc.); C) Send an ACK to NW to confirm that it can activate (one or more) relevant AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models; D) Send to the NW a list of one or more AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models that the WTRU can activate. This set may be a subset of the list of one or more AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models indicated by the NW in the activation request. This set may include one or more AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models that are not part of the NW's initial request, but the WTRU may have determined that they can be activated based on, for example, WTRU capabilities; E) Negotiate with NW (E1)-E2): E1) The WTRU can send an indication to the NW that it cannot activate all AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models as indicated by the NW, but may be able to activate them later. E2) WTRU can send an indication to NW that it cannot activate all AI / ML (sub) functions and / or AI / ML (sub) use cases and / or AI / ML models as indicated by NW, but can be activated if it deactivates currently supported features (e.g., XR features / capabilities of PDUs set in AS layer functions).

[0080] Overview See Figure 2 In response to a WTRU capability query (200) from NW (21), WTRU (20) may report its capabilities to the network / network node (gNB) (21) via a WTRU capability information message (201) in RRC.

[0081] Capability reporting is typically done in a semi-static manner. Since the AI / ML capabilities of a WTRU can be a function of dynamic parameters such as WTRU compute resources and storage, a one-off capability report may be insufficient for AI / ML. As a baseline, RAN2 (which is responsible for developing specifications for evolved UTRA, NR radio access (NR), etc.) can start with the RRC and LPP capability frameworks and, as part of a study, consider whether dynamic capability reporting is required for AI / ML.

[0082] RAN1#112 has agreed that, for functional identification, the WTRU capability report will be regarded as the starting point.

[0083] Since the current RRC capability framework does not include any AI / ML-specific instructions, some enhancements to the RRC capability framework are needed.

[0084] Enhancements to the "UE Capability Information" message may be desired to include AI / ML capabilities.

[0085] If an AI / ML capability applies only to a single function / feature or the WTRU has only one AI / ML model, it may be sufficient for the WTRU to report whether it has an AI / ML capability. However, a simple capability indication does not provide information about the functions / features to which that capability is applicable. Therefore, it may be desirable to include information about applicable functions / features in the capability indication.

[0086] Function / feature-specific capability indicators can help support multiple AI / ML function / feature capabilities.

[0087] During handover, capability information is sent from the source gNB to the target gNB as part of the WTRU context. If the target gNB does not support a feature, this can cause RRC reconfiguration to fail. For AI / ML, there are several instances where AI / ML capabilities supported by one gNB may not match those supported by another gNB. To avoid this reconfiguration failure, the WTRU can perform certain actions; AI / ML capabilities can be cell-specific.

[0088] Reporting all possible combinations of supported features / models, their interdependencies, and the network / WTRU conditions to which they are applicable would incur excessive overhead for WTRU and / or the network. Sending the full AI / ML WTRU capability to the network to capture all aspects (validity conditions, interdependencies, etc.) is not feasible / realistic, and therefore we can assume that only a limited WTRU capability is sent to the network at the beginning. This leads to several problems, such as mismatches during handover, the network attempting to activate incompatible models / features simultaneously, etc.

[0089] Switching: The source gNB releases the WTRU after sending the switchover command: Summary The following is a summary of the behavior of WTRU network nodes according to the embodiments. Details of these embodiments can be found in the relevant sections.

[0090] There may be many AI / ML capabilities corresponding to different use cases / functions / features, etc. During handover, the AIML model / function applicable / effective at the source cell / node WTRU may not be applicable at the target cell (e.g., the AIML function / model is not trained for the target cell's frequency, BWP, the target cell / gNB does not provide the inputs (e.g., reference signals) required for AIML model operation, etc.). If the WTRU conveys all possible combinations of AIML model / function capabilities, then, based on the WTRU context / capabilities forwarded from the source to the target, the target will have already calculated what AIML function to configure / activate at the WTRU after the HO. However, conveying all combinations of AIML capabilities is undesirable because (e.g., during connection establishment) the capacity for a single switch from the WTRU to the network becomes very large.

[0091] Based on some applicable scenarios: The target cell does not support some features that are supported by the source cell; The AI / ML model was not trained for the target cell.

[0092] Then, we can investigate how to prevent reconfiguration failures and subsequent rebuilds when switching WTRUs, where AIML functions / models used (or potentially used) at the source cannot be used at the target gNB / cell.

[0093] Summary of the Implementation Example: During HO, if the WTRU receives a configuration that enables / activates AI / ML operations that cannot be performed on the target application, instead of treating it as a reconfiguration failure and triggering a rebuild, the WTRU reverts to the conventional operation of that function and (e.g., in the HO completion message) sends an indication to the target cell.

[0094] According to one embodiment, see Figure 3 : The WTRU (30) receives configuration information related to / related to the handover (HO command) from the network (e.g., the source gNB (31)) (e.g., in the RRC reconfiguration message (300)). This configuration may include information about the target cell (32) for access: at least the target cell ID, new C-RNTI, target gNB security algorithm ID, etc., and AI / ML related information (including basic functions such as CSI, BM, etc.). The WTRU implicitly (e.g., based on the target cell frequency, BWP, reference signal from the target cell, etc.) or explicitly (e.g., based on AIML information included in the HO command) determines (301) the suitability of AI / ML operations at the target node (32) for one or more functions / models: If the AI / ML operation is applicable to the relevant function / model, then WTRU executes the toggle command. If an AI / ML operation is not applicable to one or more of the relevant functions / models, then for the function or the function associated with the model, the WTRU falls back to a non-AIML operation, or the WTRU falls back to the model / function applicable to the target (model / (sub)function exchange (type)). The WTRU sends a HO complete (e.g., RRC reconfiguration complete) message to the target cell (32). If the WTRU has fallen back to traditional operation for one or more AIML functions, the WTRU indicates this to the target cell (32) (302), for example, in the HO complete message or a subsequent RRC message.

[0095] Switching: The source gNB releases the WTRU after sending the switchover command: detailed operation The following is a detailed description of the operation of the WTRU network node behavior according to an embodiment.

[0096] [WTRU receives configuration for handover] The WTRU can receive, for example, a configuration for handover from a source gNB (e.g., in an RRC (re)configuration), which may contain any one or more of the following information to access the target cell A)-E): A) At least one target cell ID; B) At least one C-RNTI for the target cell; C) At least one security algorithm ID for the target cell; D) AI / ML related information (including basic functions) for at least one target cell, such as supporting AI / ML-enabled CSI prediction / CSI compression / beam management / positioning, etc. E) WTRU can be expected to have a time delay (E1)-E2) to activate one or more AI / ML (sub)functions and / or (sub)use cases. E1) As a first example of time delay, prior to handover, when the WTRU might expect to be able to activate one or more AI / ML (sub) functions and / or (sub) use cases, there might be no UE served by the target cell activating some AI / ML (sub) functions and / or (sub) use cases, causing the target cell not to register these AI / ML (sub) functions and / or (sub) use cases as "available" at the target cell. The target cell can send delay information to the source gNB regarding when it should be able to activate one or more such AI / ML (sub) functions and / or (sub) use cases, which the source gNB can then forward to the WTRU as part of the handover configuration. E2) As a second example of time delay, when the WTRU may expect to be able to activate one or more AI / ML (sub) functions and / or (sub) use cases, this may consist of a delay information for activating all AI / ML (sub) functions and / or (sub) use cases served by the source cell, or it may consist of different delay intervals for when the target cell expects to be able to activate each of the (one or more) AI / ML (sub) functions and / or (sub) use cases that are currently deactivated and / or may still be deactivated after the handover to the WTRU.

[0097] The configuration used for handover may have been generated by the target cell, but is forwarded to the WTRU by the source cell on behalf of the target cell. In one embodiment, the source cell may forward information about the best candidate target cell (i.e., the target cell with the highest RSRP). In another embodiment, the source cell may forward information related to two or more best candidate target cells. In one embodiment, the network may determine the best candidate target cell not only based on the target cell with the highest RSRP (as in the conventional approach) but also considering AI / ML applicability; that is, in cases where there may be more than one candidate target cell, the network may select a best candidate target cell based on the AI / ML operations supported by the target cell. This may consist of a list of one or more AI / ML (sub)functions and / or (sub)use cases supported by the target cell and / or the intersection of AI / ML operations between the currently serving source cell and candidate cells. In this case, the network may select the best candidate cell based on the target cell with the largest intersection with one or more AI / ML (sub)functions and / or (sub)use cases supported by the source cell.

[0098] [WTRU determines the applicability of AI / ML operations] The WTRU can determine the suitability of AI / ML operations, which may include determining whether the target cell supports one or more AI / ML (sub)functions and / or (sub)use cases supported by the source cell. According to one embodiment, this determination may be based on implicit information shared as part of the handover configuration, such as the target cell frequency, bandwidth portion, reference signals from the target cell, etc. According to another embodiment, this determination is based on explicit information, which may include any AI / ML-related information that can be included in the handover (re)configuration.

[0099] According to one embodiment, the WTRU can determine the suitability of AI / ML operations for all AI / ML (sub)functions and / or (sub)use cases supported by the WTRU. According to another embodiment, the WTRU can determine only the suitability of AI / ML operations for one or more AI / ML (sub)functions and / or (sub)use cases supported by the current service source gNB. According to yet another embodiment, the WTRU can assume that a list of one or more AI / ML (sub)functions and / or (sub)use cases supported by the current service source gNB will be selected by the network for the target gNB to be switched over, and determine only the AI / ML suitability for one or more AI / ML (sub)functions and / or (sub)use cases supported by the WTRU but not by the current service source gNB.

[0100] According to another embodiment, the WTRU may be configured with a list of one or more AI / ML (sub)functions and / or (sub)use cases for which AI / ML applicability is checked. For example, the WTRU may be configured with a list of one or more “baseline” pairs of “optional” AI / ML (sub)functions and / or (sub)use cases, and the WTRU may be configured to determine the applicability of only the one or more “baseline” AI / ML (sub)functions and / or (sub)use cases. For example, “baseline” AI / ML (sub)functions and / or (sub)use cases may be AI / ML (sub)functions and / or (sub)use cases for which conventional non-AI / ML (sub)functions and / or (sub)use cases are not configured. In one example, the WTRU may be forced to check the applicability of one or more baseline AI / ML (sub) functions and / or (sub) use cases, and opportunistically check only the applicability of any other one or more AI / ML (sub) functions and / or (sub) use cases. For example, if there is still some time remaining in the switch-out-of-service (HIT) period after checking the applicability of one or more baseline AI / ML (sub) functions and / or (sub) use cases, or if the remaining time in the HIT is higher than a pre-configured threshold, the WTRU may determine the applicability of one or more non-baseline AI / ML (sub) functions and / or (sub) use cases.

[0101] According to one embodiment, the WTRU can receive instructions from the network to assist the WTRU in determining the suitability of AI / ML operations. Such instructions may include at least one of A)-D): A) An indication to the WTRU that the set of AI / ML (sub) functions and / or (sub) use cases supported by the target cell matches the set of AI / ML (sub) functions and / or (sub) use cases supported by the source cell; B) Only check the flags / indicators of a subset of AI / ML (sub) functions and / or (sub) use cases that can be enabled in WTRU, for example, the subset may correspond to a list of (one or more) “baseline” AI / ML (sub) functions and / or (sub) use cases; C) A list of one or more AI / ML (sub)functions and / or (sub)use cases for which applicability is checked; D) The granularity of this indication can vary; for example, it can be at the feature group (FG) level and / or feature level and / or function level and / or sub-function level and / or use case level and / or sub-use case level and / or any of the above levels. See D1)-D2): D1) For beam management, the instruction can be any one or more of the following granularities (e.g., D1a) - D1c): D1a) Beam management level, D1b) Spatial domain beam prediction level, time domain beam prediction level D1c) Spatial domain beam prediction option 1 (level), spatial domain beam prediction option 2 (levels D1c1-D1c2). D1c1) For example, Option 1: Select the best beam within beam set A based on measurements of all RS resources or all possible beams in beam set A (exhaustive beam scan). D1c2) For example, option 2: Based on measurements of RS resources from beam set B, select the best beam within beam set A. D2) According to one embodiment, the NW can indicate the granularity level to the WTRU. For example, (1, 0, 0) can represent an indication at the FG level; (0, 1, 0) can represent an indication at the feature level; and (0, 0, 1) can represent an indication at the function level. In one embodiment, the function can be defined as the granularity of the spatial domain beam prediction level or the temporal domain beam prediction level. In another embodiment, the function can be defined as the granularity of option 1 for option 2 spatial domain beam prediction.

[0102] [WTRU actions based on the applicability determined by AI / ML operations] If the AI / ML operation applies to all AI / ML (sub)functions and / or (sub)use cases, the WTRU can execute a handover command to the target cell. If a subset of (one or more) AI / ML (sub)functions and / or (sub)use cases applies to the target cell, where the subset includes all “baseline” AI / ML (sub)functions and / or (sub)use cases, the WTRU can execute a handover command. If the AI / ML operation does not apply to one or more of the relevant (sub)functions / (sub)use cases / models at the target cell, the WTRU can revert to the traditional procedure used for the relevant (sub)functions / (sub)use cases / models.

[0103] The WTRU may send a handover completion message (e.g., RRC reconfiguration complete) to the target gNB to indicate that the handover is complete. If the WTRU has reverted to legacy operation for one or more AI / ML (sub)functions and / or (sub)use cases, the WTRU may indicate this to the target gNB (e.g., in an HO completion message or in one or more subsequent RRC messages, such as in one or more RRC reconfiguration complete messages). This indication may include any one or more of the following A)-I): A) One or more AI / ML (sub) functions and / or (sub) use cases that the source cell supports but the target cell does not; B) One or more AI / ML (sub) functions and / or (sub) use cases that are not supported by the source cell but are supported by the target cell; C) One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU; D) One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU but to be activated later. The indication may also optionally include the expected time when the one or more AI / ML (sub) functions and / or (sub) use cases will be activated; E) One or more AI / ML (sub) functions and / or (sub) use cases that are not currently activated and / or supported by the target cell, for which WTRU uses traditional mechanisms as an alternative; F) One or more AI / ML (sub) functions and / or (sub) use cases that are not activated and / or supported by the source cell, for which WTRU uses the traditional mechanism as an alternative; G) may indicate any of the aforementioned AI / ML (sub)functions and / or (sub)use cases, for example, based on the AI / ML (sub)function ID and / or the AI / ML (sub)use case ID; H) The associated criticality degree of the list of AI / ML (sub)functions and / or (sub)use cases that cannot be activated, for example, each (sub)function and / or (sub)use case may have a criticality degree number attached to it; I) The expected time delay (I1)-I3) for WTRU to activate any of the above-mentioned AI / ML (sub)functions and / or (sub)use cases. I1) For example, prior to the handover, there may not be a UE served by the target cell that has some activated AI / ML (sub) functions and / or (sub) use cases, causing the target cell not to register these AI / ML (sub) functions and / or (sub) use cases as "available" at the target cell. I2) For example, the WTRU can send delay information to the target cell to notify it of the expected activation of these AI / ML (sub)functions and / or (sub)use cases at a given time. This can consist of: a delay message for all AI / ML (sub)functions and / or (sub)use cases currently deactivated in the target cell but activated in the source cell, or different delay messages for each corresponding AI / ML (sub)function and / or (sub)use case. (I3) According to one embodiment, the WTRU may be pre-configured with delay information, for example, allowing the activation of a t1 ms interval in the target cell after handover for function X; and allowing the activation of a t2 ms interval in the target cell after handover for function Y. In another embodiment, the WTRU may have received such information from the source cell before handover.

[0104] According to one embodiment, after handover is complete, the WTRU can receive time delay information (A)-B) from the target cell regarding when the target cell can activate some AI / ML (sub)functions and / or (sub)use cases that may currently be deactivated. A) For example, during this period, if needed, WTRU can use traditional functions as a solution; B) In another example, the WTRU may extend the prediction time window for the relevant AI / ML (sub) function and / or (sub) use case while still being served by the source cell. For example, if the WTRU uses AI / ML for time-domain beam prediction while being served by the source cell, it may extend the prediction window to also include handover interruption time (e.g., extending the prediction window by 50 milliseconds) to account for the fact that time-domain beam prediction capability may not be immediately activated in the target cell during handover.

[0105] [WTRU receives an RRC reconfiguration request with multiple sub-configurations, selects the configuration to apply based on conditions, performs actions based on the selected sub-configuration, and indicates the selected sub-configuration.] According to one embodiment, the WTRU can receive an RRC reconfiguration having a first sub-configuration, a second sub-configuration, and a third sub-configuration. For example, the first sub-configuration may correspond to a full configuration, while the second and third sub-configurations may correspond to incremental configurations. For example, the first sub-configuration may correspond to a non-AIML / traditional configuration, and the second and third sub-configurations may correspond to one or more AIML configurations. For example, the second and third sub-configurations may have different combinations and / or numbers of AIML features, use cases, and / or AIML model configurations.

[0106] According to one embodiment, each sub-configuration can be associated with a priority. For example, the WTRU can select the sub-configuration to apply based on priority. For instance, the WTRU can check if it can apply the highest-priority sub-configuration. If it cannot match the highest-priority sub-configuration, the WTRU checks if it can match the next highest-priority sub-configuration.

[0107] According to one embodiment, each sub-configuration may be associated with a flag to indicate whether the sub-configuration is mandatory or optional. For example, if the WTRU cannot comply with a mandatory sub-configuration, it can declare that the RRC reconfiguration has failed. Conversely, if the WTRU cannot comply with an optional sub-configuration, it can ignore that sub-configuration and continue processing / applying the remaining sub-configurations (if applicable). According to one embodiment, by default, sub-configurations corresponding to the full configuration may be considered mandatory.

[0108] The embodiments described can be extended to multiple AIML sub-configurations, for example, more than two AIML sub-configurations with different combinations of AIML functionalities, use cases, and / or AIML model configurations. In this document, each target cell can be associated with a set of sub-configurations.

[0109] The WTRU can be configured with a logical ID associated with each sub-configuration. According to one embodiment, the WTRU can be configured to indicate the status of a sub-configuration via RRC configuration completion. For example, the WTRU can indicate the logical ID(s) of the sub-configurations it has applied. Alternatively, the WTRU can indicate the logical ID(s) of the sub-configurations it cannot comply with.

[0110] According to one embodiment, the WTRU may be configured with RACH resources, wherein each RACH resource may be associated with a sub-configuration (or a combination of sub-configurations). The WTRU may implicitly indicate the applicable sub-configuration(s) by selecting the RACH resource associated with the applicable sub-configuration(s) and transmitting a preamble on the selected resource.

[0111] According to the first embodiment, upon receiving a synchronized RRC configuration including one or more sub-configurations, the WTRU can determine the applicable sub-configuration based on one or more conditions described herein. The WTRU can apply the selected sub-configuration(s) to trigger random access to the target cell (e.g., possibly based on the selected sub-configuration). Upon successful random access in the target cell, the WTRU can indicate the applicable sub-configuration in the RRC reconfiguration completion message.

[0112] According to the second embodiment, upon receiving a synchronized RRC configuration including one or more sub-configurations, the WTRU can determine the applicable sub-configurations based on one or more conditions described herein. The WTRU can apply a first sub-configuration (e.g., associated with a traditional AIML configuration / non-AIML configuration) to trigger random access to the target cell. Upon successful random access in the target cell, the WTRU can indicate in an RRC reconfiguration complete message a set of sub-configurations that the WTRU can potentially activate in the target cell. In other words, the WTRU can transmit an indication of sub-configurations that the WTRU can activate in the future based on subsequent commands from the target cell. The WTRU can receive a MAC CE from the target cell, which carries an indication (e.g., a logical ID associated with the sub-configuration) of the sub-configurations the WTRU should activate.

[0113] Switchover: Source gNB failed to release WTRU after sending switchover command: Summary The following is a summary of the behavior of WTRU network nodes according to the embodiments. Details of these embodiments can be found in the relevant sections.

[0114] When switching the WTRU to another gNB that supports a different set of AI / ML features, the expected source gNB minimizes reconfiguration and fails.

[0115] Therefore, the source gNB may not release the WTRU immediately after sending the HO command. The source gNB can only release the WTRU after receiving confirmation from the WTRU that a handover may be necessary. The WTRU may send this confirmation only when it determines that AI / ML operations for one or more functions are applicable in the target cell.

[0116] In summary, see Figure 4 : A) The WTRU (40) receives configuration for handover (configuration information related to the handover (HO) command) from the network (e.g., from the source gNB (41)) (e.g., in the RRC reconfiguration message (400)), e.g., the first configuration section and the second configuration sections A1-A2): A1) The first configuration section contains information for accessing the target cell (42): at least the target cell ID, the new C-RNTI, the target gNB security algorithm ID, etc. (e.g., generated by the target). A2) The second configuration section contains configuration information related to, for example, the RSRP threshold (the configured threshold) and the time window used to determine the applicability of the HO; B) WTRU may determine the suitability (401), B1)-B2) of the AI / ML operations of the function at the target node (42) implicitly (e.g., based on frequency, BWP) or explicitly (e.g., based on information contained in the HO command): B1) If AI / ML operations are applicable (402), the WTRU can complete the handover by sending an RRC reconfiguration complete message to the target cell (42). The WTRU can send an acknowledgment (403) to the source gNB (41) that it can perform the HO (e.g., allowing the source to release the WTRU); conventionally, the WTRU will only send an RRC reconfiguration complete message to the target cell (42). In this case, it also sends a message (403) to the source cell (41) so that the source cell (41) can release the WTRU. B2) If the AI / ML operation used for the function is not applicable to the target node (42) (e.g., because WTRU does not support the function), see B2a and B2b): B2a) If the RSRP with the source cell (41) is greater than the configured RSRP threshold (404): The WTRU can send an indication (405) to the source cell (41) indicating that it cannot be transferred to the target cell (e.g., refuse to transfer or handover if some functions (switching mode, etc.) are not supported). B2b) If the RSRP with the source cell (41) is less than the configured RSRP threshold (406), see B2b1 and B2b2): B2b1) The WTRU can complete the HO (407) with the target cell (42) (e.g., if the WTRU can fall back to conventional (non-AIML) operation of a function, and if the WTRU has fallen back to conventional operation of one or more AIML functions, the WTRU can indicate this to the target (42) (e.g., in the HO completion message (407) or in a subsequent RRC message). (B2b2) or WTRU announces reconfiguration failure.

[0117] Note that the RSRP level should be verified as previously, because if the RSRP level of the source cell is good (e.g., RSRP > Th), it may be preferable to keep the WTRU in the source cell to keep the AI / ML function effective, whereas the WTRU cannot be HO'd to the target cell.

[0118] However, if the RSRP of the source cell is poor (e.g., RSRP < Th), then handover seems to be preferred, and due to the low RSRP in the source cell, the AI / ML functions in the source cell may be unsupported, and due to the low RSRP, HO seems to be preferred, and HO is still performed even if the WTRU will fallback to non-AIML operation in the target cell.

[0119] Handover: The source gNB does not release the WTRU after sending the handover command: detailed operation The following is a description of the detailed operation of the WTRU network node behavior according to an embodiment.

[0120] [The WTRU receives the configuration for handover (e.g., generated by the target gNB)] The WTRU can receive, for example, the configuration for handover (configuration information) from the source gNB, e.g., in an RRC (re)configuration, which can contain any one or more of the following information for accessing the target cell, A)-F): A) The cell ID of at least one target cell; B) The C-RNTI of at least one target cell; C) The security algorithm ID of at least one target cell; D) The AI / ML related information (including basic functions) of at least one target cell, e.g., supporting AI / ML enabled CSI prediction / CSI compression / beam management / location, etc.; E) The time delay that the WTRU can expect to be able to activate one or more AI / ML (sub)functions and / or (sub)use cases (e.g., E1), e.g., E1), E2): E1) For example, before handover, there may not be a UE served by the target cell that activates some AI / ML (sub)functions and / or (sub)use cases, such that the target cell does not register these AI / ML (sub)functions and / or (sub)use cases as "available" at the target cell. The target cell can send the delay information to the source gNB regarding when it should be able to activate one or more such AI / ML (sub)functions and / or (sub)use cases, and the source gNB can then forward this information to the WTRU as part of the handover configuration. E2) For example, this can consist of one delay information for activating all AI / ML (sub)functions and / or (sub)use cases served by the source cell, or it can consist of different delay intervals for each of the (one or more) AI / ML (sub)functions and / or (sub)use cases that the target cell expects to be able to activate currently deactivated and / or still potentially deactivated after the handover of the WTRU is completed; F) Reference signals, for example, the target cell can generate reference signals (e.g., CSI-RS, PRS), which the source cell can forward to the WTRU. The WTRU can use the reference signals to perform measurements (e.g., measuring CSI parameters, measuring WTRU location).

[0121] The configuration used for handover may have been generated by the target cell, but is forwarded to the WTRU by the source cell on behalf of the target cell. In one embodiment, the source cell may forward information about the best candidate target cell (i.e., the target cell with the highest RSRP). In another embodiment, the source cell may forward information about two or more best candidate target cells. In one embodiment, the network may determine the best candidate target cell not only based on the target cell with the highest RSRP (as in the conventional approach) but also considering AI / ML applicability; that is, in cases where there may be more than one candidate target cell, the network may select a best candidate target cell based on the AI / ML operations supported by the target cell. This may consist of a list of one or more AI / ML (sub)functions and / or (sub)use cases supported by the target cell and / or the intersection of AI / ML operations between the currently serving source cell and candidate cells. In this case, the network may select the best candidate cell based on the target cell that has the largest intersection with one or more AI / ML (sub)functions and / or (sub)use cases supported by the source cell.

[0122] [WTRU receives configuration for AI / ML support during handover (e.g., generated by the source gNB)] In addition to information typically generated by the target gNB and forwarded to the WTRU by the source gNB, the WTRU may receive information generated by the source gNB. This may include any one or more of the following A)-C): A) Configuration regarding any conditions that will enable / trigger the switch when met (A1)-A4): A1), for example, the RSRP thresholds for the source cell (A1a)-A1b). A1a) For example, when a threshold is reached / exceeded, if the target cell does not support all or a subset of the AI / ML (sub)functions and / or (sub)use cases supported by the source cell, the WTRU can have the flexibility not to switch to the target cell. A1b) The WTRU can be configured to switch to the target cell based on all or a subset of (one or more) AI / ML (sub)functions and / or (sub)use cases, based on, for example, the criticality of (one or more) relevant AI / ML (sub)functions and / or (sub)use cases that cannot be activated (A1b1)-A1b2). (A1b1) For example, (sub)features and / or (sub)use cases without legacy programs can have high criticality scores compared to cases where legacy programs are configured in addition to enabling AI / ML features. (A1b2), for example, each (sub)function and / or (sub)use case can have a criticality number attached to it. A2), for example, the thresholds A2a)-A2b corresponding to the CSI parameters (e.g., CQI, PMI, RI) of the Uu link with the source cell: A2a) For example, if any CSI parameter (e.g., CQI) of the Uu link with the source cell is higher than a pre-configured threshold, then the WTRU can be configured to delay handover to the target cell if the target cell cannot immediately activate all AI / ML (sub)functions and / or (sub)use cases activated at the source cell. A2b) For example, if the CQI of the Uu link with the source cell is higher than a pre-configured threshold, the WTRU can be configured to delay handover to the target cell if the target cell cannot immediately activate all “baseline” AI / ML (sub) functions and / or (sub) use cases activated at the source cell. The WTRU can be configured with content considered as “baseline” AI / ML (sub) functions and / or (sub) use cases. A3) For example, regarding the RSRP threshold for the target cell, if the RSRP threshold for the target cell is lower than a pre-configured threshold, which is relatively low but still higher than the RSRP threshold that triggers a handover to the target cell, then the WTRU may complete the handover only if all or a subset of the AI / ML (sub) functions and / or (sub) use cases supported by the source cell are also supported at the target cell. A4) For example, regarding the WTRU location / location threshold of the target cell, for example, if the WTRU location / location / distance is relatively far from the target cell, i.e., within a specific distance greater than the pre-configured threshold, then the WTRU can be configured to delay the switch to the target cell if the target cell cannot immediately activate all AI / ML (sub) functions and / or (sub) use cases activated in the source cell. B) A time window for determining applicability, for example, the WTRU may receive a time window (e.g., a time window of X milliseconds) from the NW to determine the applicability of AI / ML operations in the target cell. If, within the time window, the WTRU is unable to assess whether all or a subset of the AI / ML (sub)functions and / or (sub)use cases activated in the source cell are also supported in the target cell and / or immediately supported in the target cell at handover, the WTRU may delay the handover, for example, to give the target cell time to activate one or more AI / ML (sub)functions and / or (sub)use cases. In another embodiment, the WTRU may do this only if the RSRP of the source cell is higher than a pre-configured threshold; C) Regarding the configuration of any conditions that can be relaxed to delay the switch: C1)-C2): C1), for example, through its delayed switching time window C1a)-C1b): C1a) For example, if the target cell does not support all or a subset of the AI / ML (sub) functions and / or (sub) use cases supported by the source cell, the NW can send handover tolerable time delay information to the WTRU (even if the target cell's RSRP currently meets the threshold for handover). C1b) For example, if the time required for the target cell to activate some AI / ML functions is longer than a pre-configured threshold, the network can delay the handover of the WTRU to the target cell (even if the target cell's RSRP currently meets the threshold for handover). C2) For example, if the expected handover interruption time is > t ms, then if the RSRP with the source cell is higher than a threshold, the WTRU can be configured to delay the handover to the target cell until a later time.

[0123] [WTRU determines the applicability of AI / ML operations] The WTRU can determine the suitability of AI / ML operations, which may include determining whether the target cell supports one or more AI / ML (sub)functions and / or (sub)use cases supported by the source cell. In one embodiment, this determination may be based on implicit information shared as part of the handover configuration, such as the target cell frequency, bandwidth portion, reference signals from the target cell, etc. In another embodiment, this determination is based on explicit information, which may include any AI / ML-related information that can be included in the handover (re)configuration.

[0124] According to one embodiment, the WTRU can determine the suitability of AI / ML operations for all AI / ML (sub)functions and / or (sub)use cases supported by the WTRU. In another embodiment, the WTRU can determine only the suitability of AI / ML operations for one or more AI / ML (sub)functions and / or (sub)use cases supported by the current service source gNB. In yet another embodiment, the WTRU can assume that a list of one or more AI / ML (sub)functions and / or (sub)use cases supported by the current service source gNB will be selected by the network for the target gNB to be switched, and determine only the AI / ML suitability for one or more AI / ML (sub)functions and / or (sub)use cases supported by the WTRU but not by the current service source gNB.

[0125] According to another embodiment, the WTRU may be configured with a list of one or more AI / ML (sub)functions and / or (sub)use cases for which AI / ML applicability is checked. For example, the WTRU may be configured with a list of one or more “baseline” pairs of “optional” AI / ML (sub)functions and / or (sub)use cases, and the WTRU may be configured to determine the applicability of only the one or more “baseline” AI / ML (sub)functions and / or (sub)use cases. For example, “baseline” AI / ML (sub)functions and / or (sub)use cases may be AI / ML (sub)functions and / or (sub)use cases for which conventional non-AI / ML (sub)functions and / or (sub)use cases are not configured. In one example, the WTRU may be forced to check the applicability of one or more baseline AI / ML (sub) functions and / or (sub) use cases, and opportunistically check only the applicability of any other one or more AI / ML (sub) functions and / or (sub) use cases. For example, if there is still some time remaining in the switch-out-of-service (HIT) period after checking the applicability of one or more baseline AI / ML (sub) functions and / or (sub) use cases, or if the remaining time in the HIT is higher than a pre-configured threshold, the WTRU may determine the applicability of one or more non-baseline AI / ML (sub) functions and / or (sub) use cases.

[0126] According to any embodiment, the WTRU may receive instructions from the network to assist the WTRU in determining the applicability of AI / ML operations. Such instructions may include any one or more of the following: The notification to the WTRU indicates that the set of AI / ML (sub) functions and / or (sub) use cases supported by the target cell matches the set of AI / ML (sub) functions and / or (sub) use cases supported by the source cell; Only check the flags / indicators of a subset of AI / ML (sub) functions and / or (sub) use cases that can be enabled in WTRU, for example, the subset may correspond to a list of (one or more) "baseline" AI / ML (sub) functions and / or (sub) use cases; Check the applicability of one or more AI / ML (sub)functions and / or (sub)use cases; The granularity of this indication can vary; for example, it can be at the feature group (FG) level and / or feature level and / or function level and / or sub-function level and / or use case level and / or sub-use case level and / or any of the above levels.

[0127] [WTRU actions based on the applicability determined by AI / ML operations] If AI / ML operations are applicable—that is, all or a subset of the AI / ML (sub) functions and / or (sub) use cases supported in the source cell are also supported in the target cell—the WTRU can send an acknowledgment message to the source gNB to indicate that it can perform a handover. This acknowledgment message can trigger the source cell to release the WTRU. In one embodiment, the source cell may not release the WTRU until it receives an acknowledgment message from the WTRU: For example, in order for WTRU to send an acknowledgment message, a subset of the AI / ML (sub) functions and / or (sub) use cases that need to be supported can correspond to (one or more) "baseline" AI / ML (sub) functions and / or (sub) use cases; For example, in order for the WTRU to send an acknowledgment message, a subset of the AI / ML (sub) functions and / or (sub) use cases that need to be supported can be configured in the WTRU and / or sent from the source cell to the WTRU as part of a handover command.

[0128] The WTRU can complete the handover process by sending an RRC reconfiguration complete message to the target cell. For example, when performing a handover using only a subset of AI / ML (sub) functions and / or (sub) use cases, the WTRU can send additional information to the target cell as part of the handover complete message, since only that subset applies to the target cell. The WTRU can also optionally instruct the target cell A)-I) on one or more of the following: A) One or more AI / ML (sub) functions and / or (sub) use cases that the source cell supports but the target cell does not; B) One or more AI / ML (sub) functions and / or (sub) use cases that are not supported by the source cell but are supported by the target cell; C) One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU; D) One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU but to be activated later. The indication may also optionally include the expected time when the one or more AI / ML (sub) functions and / or (sub) use cases will be activated; E) One or more AI / ML (sub) functions and / or (sub) use cases that are not currently activated and / or supported by the target cell, for which WTRU uses traditional mechanisms as an alternative; F) One or more AI / ML (sub) functions and / or (sub) use cases that are not activated and / or supported by the source cell, for which WTRU uses the traditional mechanism as an alternative; G) may indicate any of the aforementioned AI / ML (sub)functions and / or (sub)use cases, for example, based on the AI / ML (sub)function ID and / or the AI / ML (sub)use case ID; H) The associated criticality degree of the list of AI / ML (sub)functions and / or (sub)use cases that cannot be activated, for example, each (sub)function and / or (sub)use case may have a criticality degree number attached to it; I) The expected time delay (I1)-I3) for WTRU to activate any of the above-mentioned AI / ML (sub)functions and / or (sub)use cases. I1) For example, prior to the handover, there may not be a UE served by the target cell that has some activated AI / ML (sub) functions and / or (sub) use cases, causing the target cell not to register these AI / ML (sub) functions and / or (sub) use cases as "available" at the target cell. I2) For example, the WTRU can send delay information to the target cell to notify it of the expected activation of these AI / ML (sub)functions and / or (sub)use cases at a given time. This can consist of: a delay message for all AI / ML (sub)functions and / or (sub)use cases currently deactivated in the target cell but activated in the source cell, or different delay messages for each corresponding AI / ML (sub)function and / or (sub)use case. (I3) According to one embodiment, the WTRU may be pre-configured with delay information, for example, allowing the activation of a t1 ms interval in the target cell after handover for function X; and allowing the activation of a t2 ms interval in the target cell after handover for function Y. In another embodiment, the WTRU may have received such information from the source cell before handover.

[0129] If AI / ML operations are not applicable at the target cell—that is, at least one of the AI / ML (sub) functions and / or (sub) use cases supported in the source cell is not supported in the target cell—the WTRU can be configured with conditions for whether to perform a handover to the target cell. Such conditions could be, for example, the RSRP relative to the source cell. For instance, if the RSRP with the source cell is higher than a pre-configured threshold, the WTRU can determine not to perform a handover or delay the handover for a pre-configured time period (assuming the RSRP with the source cell remains higher than the pre-configured threshold throughout the time period). If the WTRU determines to delay and / or cancel the handover to the target cell, the WTRU can send an indication to the source cell that it cannot transfer to the target cell. This indication could be, for example, refusing the handover or handover to the target cell without supporting some AI / ML (sub) functions and / or (sub) use cases. In one embodiment, the WTRU can request an AI / ML model switch and / or model download from the source cell to replace the AI / ML (sub) functions that are not available at the target cell. The WTRU may not perform a handover to the target cell until a new AI / ML model is received.

[0130] If AI / ML operations are not applicable in the target cell, but the measured RSRP with the source cell is below a pre-configured threshold, the WTRU may not be allowed to delay and / or reject handover commands from the network. The WTRU may have to complete the handover command regardless of whether support for at least one AI / ML (sub)function and / or (sub)use case is missing. In this case, the WTRU may fall back to the traditional procedures of (one or more) the relevant AI / ML (sub)function and / or (sub)use case. In one embodiment, the WTRU may be configured with a time window during which handover can be performed. If AI / ML operations are not applicable in the target cell, and the measured RSRP with the source cell is below a pre-configured threshold, but the handover threshold is expected to be exceeded at a future time within the pre-configured time window, the WTRU may delay the handover and send an indication of the delay window to the source cell. In another embodiment, if AI / ML operations are not applicable in the target cell and the measured RSRP with the source cell is below a pre-configured threshold and is expected to remain below the handover threshold throughout the pre-configured time window, the WTRU may perform a handover to the target cell and revert to conventional procedures for one or more AI / ML (sub) functions and / or (sub) use cases not supported by the target cell.

[0131] According to one embodiment, if AI / ML operations are not applicable in the target cell, but the measured RSRP of the source cell is below a pre-configured threshold and / or is expected to remain below the threshold through a pre-configured window to perform a handover, the WTRU may declare a reconfiguration failure.

[0132] Switch: Dynamic Capability Indicator: Summary First exemplary embodiment The following is a summary of the behavior of WTRU network nodes in relation to dynamic capability indications according to a first exemplary embodiment. Details of these embodiments can be found in the relevant sections.

[0133] WTRU may not be able to support AI / ML operations across different features / functions simultaneously. Activating an AI / ML operation for one feature / function may result in the deactivation of another feature / function. From a programmatic perspective, understanding the following is of interest: How the activation of AI for one function affects the AI / ML capabilities / operations of another function; How does model swapping or regression of one function affect the AI / ML capabilities / operations of another function? How to define mandatory and optional capabilities, and how they affect WTRU behavior; How to indicate dynamic capabilities when the model becomes applicable (e.g., appropriate channel conditions / NW configuration, etc.) or when the use of the model becomes possible (e.g., availability of processing capabilities); The WTRU receives activation instructions from a third party unfamiliar with UL and DL services. The transmission of the model inference output requires resources on the Uu link.

[0134] Therefore, according to the embodiments described in detail in the dedicated section, AI / ML capabilities are dynamic, for example, a function of available processing power and storage, which change dynamically (even with the same set of supported functions / models). The WTRU is configured with priorities for functions to be activated and / or rules for selecting functions to be activated, which include all variable conditions (WTRU processing power, storage, radio conditions).

[0135] According to one embodiment, WTRU performs A)-G): A) The WTRU receives configuration from the network / third party, including the priorities of the AI / ML functions to be supported (e.g., BM Case 1 = Priority #1, CSI Compression = Priority #2, etc.) and the minimum periodicity / duration of the evaluation (e.g., timer / slot / periodity) and the reporting configuration (e.g., report content + trigger); for example, if the WTRU cannot activate a function of the first priority as determined by the network, it only reports to the network; B) WTRU receives activation indications for functions / models from NW / third parties; C) The WTRU determines the functions it can support, for example, based on priority and / or applicable channel conditions or available processing capacity or storage. For example, processing capacity is less than a threshold; D) WTRU activates one or more AI / ML functions from among the functions activated by the network for the identified functions; E) If the WTRU is unable to activate the entire set of functions / models as requested by the NW, send an instruction to the NW; for example, including a list of activated AI / ML functions; F) Under configured periodic instances (e.g., WTRUs determined based on the configured evaluation duration or periodicity), the WTRUs perform evaluations of the supported AI / ML functions (F1)-F2). F1) For example, given current computing resources and / or storage, WTRU determines whether it can update currently active AI / ML functions. F2) WTRU activates / deactivates features and / or models based on F2a)-F2b) by increasing / decreasing priority (e.g., stepwise demotion): The accuracy of the F2a) model, or Priority of F2b) AI / ML functions; G) WTRU sends an instruction to NW to update the list of AI / ML functions that have been activated.

[0136] Second exemplary embodiment The following is a summary of the behavior of WTRU network nodes related to dynamic capability indication according to a second exemplary embodiment. Details of these embodiments can be found in the relevant sections.

[0137] It's important to note that with each release of the relevant 3GPP specifications, the list of WTRU capabilities becomes longer. When the set of features that the WTRU must report becomes too large, this can cause the WTRU to be unable to generate the "UE Capability Information" message with the correct structure. This can also cause the NW to be unable to correctly decode the verbose capability indications from the WTRU (verbose messages are more likely to be corrupted upon reception).

[0138] Summary of the examples: WTRU does not report all possible combinations of content it can support.

[0139] Therefore, WTRU may be A)-E): A) WTRU can report to network capabilities, including AI / ML-related capabilities (initial high-level capabilities). B) WTRU can receive activation of functions / models (e.g., model #m1, function #f1, etc.) (e.g., from the network or a third party); C) WTRU can activate functions / models, such as model #m1 and function #f1; D) WTRU can receive activation of features / models (e.g., model #m2, feature #f2) (e.g., from the network or a third party); E) WTRU can determine whether it can simultaneously support the latest activation requests from the network along with other activated features / models (E1)-E2). E1) If yes, then WTRU completes the latest activation request from the network. E2) If not, the WTRU sends an indication to the network that it is incompatible with the currently supported functions / models (e.g., the function / model that caused the conflict, the reason for the conflict (e.g., processing capacity limitations, power limitations, etc.)).

[0140] Switch: Dynamic Capability Indicator: Detailed Operation The following is a detailed description of the operation of WTRU network node behavior related to dynamic capability indication according to an embodiment.

[0141] [WTRU receives configurations to help WTRU determine the AI / ML features to support and the associated reporting configurations.] WTRU may receive configuration (e.g., from NW / gNB / third parties) to assist WTRU in identifying one or more AI / ML (sub)functions and / or (sub)use cases to be supported, which may include any one or more of the following A)-C): A) Priority for supporting AI / ML functions A1)-A4): A1) For example, Beam Management (BM) = Priority #1, CSI = Priority #2, Positioning = Priority #3. A2) For example, BM spatial prediction = priority #1, CSI compression = priority #2, BM temporal prediction = priority #3, CSI prediction = priority #4, etc. A3) For example, WTRU can receive a complete list of all AI / ML enabled (sub)functions and / or (sub)use cases supported by the network, as well as the corresponding priority for enabling each (sub)function and / or (sub)use case. A4) For example, priority can be a function of radio conditions; B) Determine the rules / conditions for the AI / ML functions to be supported, which may depend on any one or more of the following B1)-B4): B1) WTRU capabilities: For example, if the WTRU supports full-duplex, then activating spatial beam prediction with AI / ML is the first priority; otherwise, activating temporal beam prediction with AI / ML is the first priority. B2) Model type, for example, the processing required for inference can be a function of the model type (e.g., DNN to UNN to CNN to RNN, etc.). B3) WTRU business type, B4) Measurement. For example, a WTRU may be configured with resources on which to perform at least one measurement. The WTRU may compare the at least one measurement with at least one threshold. The at least one threshold may be configurable. If the at least one measurement is greater than or less than the at least one threshold, the WTRU may determine to activate a certain AI / ML function. Activation of the AI / ML function may be associated with at least one measurement threshold. The measurement may include at least one of B4a) - B4m): B4a) Location, speed, direction of movement, B4b) L1 or L3 measurements, such as RSRP, RSSI, RSRQ, SINR, CO, RI, CQI, PMI, LI, B4c) Interference measurement, B4d) Doppler, Doppler spread, delay spread, number of multipaths, B4e) Coherence time, coherence bandwidth, B4f) Beam direction, beam width, beam set (e.g., elements in a set of cardinality of the set), B4g) Rate of successful channel access attempts. For example, the WTRU may track the number / percentage of successful LBT attempts over a period of time. The period of time may be dynamically determined (e.g., a sliding window). For example, a number / percentage of successful LBT attempts below a threshold may determine the (one or more) AI / ML (sub) functions and / or (sub) use cases supported by the WTRU, B4h) Rate of NACKs. For example, the WTRU may maintain a measurement of the number or percentage of NACKs over a period of time. The period of time may be dynamically determined (e.g., a sliding window), B4i) Path loss. For example, if path loss > X, activate AI / ML-enabled spatial beam prediction as a first priority, and if X < path loss < Y, activate AI / ML-enabled temporal beam prediction as a first priority, B4j) Whether the path is line-of-sight or non-line-of-sight, B4k) Throughput, B4l) BLER, B4m) Delay; C) Comparison with traditional functions: For example, WTRU can compare the performance of an AIML model / AIML-enabled function with the expected performance of performing the function using a baseline (e.g., non-AIML) method. WTRU can determine the rate of error events using the AIML model / AIML-enabled function. Error events can be identified when the difference between the AIML model's output and the baseline method is greater than or less than a threshold. If the rate of error events is greater than or less than the threshold, WTRU can determine the priority of the AIML model / AIML-enabled function. If the difference between the AIML model's output and the baseline model's output is greater than or less than the threshold, WTRU can determine the priority / order of activating which AI / ML-enabled function.

[0142] WTRU can receive configuration (e.g., from NW / gNB / third parties) regarding when / whether to prioritize / order AI / ML (sub)functions and / or (sub)use cases. For example, WTRU can be configured to perform evaluations based on any one or more of the following: Periodically, with a configured periodicity; Semi-periodic; Non-periodic / event-triggered.

[0143] The WTRU can receive configuration (e.g., from NW / gNB / third parties) regarding when / whether to report the above evaluation results. For example, the WTRU can be configured to report the evaluation results based on any one or more of the following A)-E): A) After each assessment; B) Periodically, with a configurable period; C) When the timer expires; D) Semi-periodic; E) Non-periodic / event-triggered / condition-based (one or more) conditions: E1) For example, if the WTRU cannot activate a first-priority function as determined by the network, it only reports to the NW. E2) For example, if the WTRU cannot activate the top N priority functions as determined by the network, it only reports to the NW, where N can be any integer. E3) For example, if at the cell edge, the WTRU only reports to the NW. E4) For example, if the WTRU cannot activate a first-priority function as determined by the network when it is at the cell edge, it only reports to the NW.

[0144] [WTRU identifies one or more (sub)functions and / or (sub)use cases to be supported] WTRU can determine one or more AI / ML (sub)functions and / or (sub)use cases to be supported based on one or more of A)-E): A) Priority A1)-A2): A1) If indicated by NW, A2) As determined by WTRU based on rules / configuration received from NW; B) Applicable conditions B1)-B2): B1) "Applicability conditions" or "suitability criteria" can refer to the fact that an AI / ML function / model that is "applicable" in one set of configurations / scenarios / datasets may no longer be "applicable" in another set of configurations / scenarios / datasets. Examples of applicable conditions (B2) may include: B2a) Applicable scenarios, such as channel conditions, channel model, carrier frequency, WTRU distribution within the cell, WTRU mobility level, etc. B2b) Applicable configurations, such as WTRU / gNB configuration, bandwidth, bandwidth portion, antenna configuration, antenna port layout, etc. (B2c) Applicable sites, such as location, positioning, the tracking area where the WTRU is located, and attributes of the site where the model is trained. (B2c1) For example, if a model is trained in a rural area, it may not be suitable to deploy / use the model for inference in an urban area. (B2c2) For example, at the cell edge, in order to ensure a smoother transition with neighboring cells, the WTRU can request and receive reference signals (e.g., CSI-RS, PRS) from neighboring cells before the handover procedure. C) Availability / status of WTRU internal conditions (e.g., processing power, storage, memory, battery, other hardware limitations). For example, if processing power < a configured threshold, the WTRU can determine that it can support a certain set of (one or more) (sub)functions and / or (sub)use cases, while when processing power > a configured threshold, the WTRU can determine that it can support a different set of (one or more) (sub)functions and / or (sub)use cases. D) WTRU can perform an evaluation to identify one or more AI / ML (sub)functions and / or (sub)use cases to support when a timer expires (e.g., based on a configured period). For example, given current compute resources and / or storage, WTRU determines whether it can update currently supported AI / ML functions. E) WTRU can activate (one or more) AI / ML (sub)functions and / or AI / ML (sub)use cases and / or AI / ML models in a descending priority manner (gradual demotion) until WTRU can revert to traditional mechanisms / operations. E1) Less accurate models, or E2) Lower priority functions.

[0145] [WTRU sends instruction to NW] According to one embodiment, the WTRU can send an indication to the NW, for example, whether it is unable to activate the entire set of features / models as requested by the NW. For example, the indication may include the following: One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU; One or more AI / ML (sub) functions and / or (sub) use cases supported by WTRU but to be activated later. The indication may also optionally include the expected time when the one or more AI / ML (sub) functions and / or (sub) use cases will be activated; For AI / ML (sub) functions and / or (sub) use cases that are not currently activated and / or supported by WTRU, WTRU uses traditional mechanisms as an alternative. It can indicate any of the aforementioned AI / ML (sub)functions and / or (sub)use cases, for example, based on the AI / ML (sub)function ID and / or the AI / ML (sub)use case ID; The associated criticality level of the list of AI / ML (sub) functions and / or (sub) use cases that cannot be activated, for example, each (sub) function and / or (sub) use case may have a criticality level number attached to it; WTRU anticipates the time delay required to activate any of the above-mentioned AI / ML (sub) functions and / or (sub) use cases. The reason it cannot support one or more AI / ML (sub) functions and / or (sub) use cases is, for example, the WTRU may send an indication to the network that it is incompatible with the currently supported functions / models (e.g., the indication of the conflicting functions / use cases / models, the reason for the conflict, such as processing power limitations, power limitations, storage limitations, etc.).

[0146] Upon receiving an activation request from NW for an AI / ML-based feature / use case, WTRU may send such an instruction to NW at any time when it determines whether one or more AI / ML (sub)features and / or (sub)use cases can or cannot be supported.

[0147] Figure 5 This is a flowchart of method 500 according to an embodiment.

[0148] This method can be implemented by a wireless transmit-receive unit (WTRU) in the network. The method includes: In step 501, configuration information related to the handover of the WTRU from the source network node to the target network node is received from the network. In 502, it is determined that the AI / ML operation of the WTRU used for at least one artificial intelligence / machine learning (AI / ML) function cannot be supported by the WTRU at the target network node; In 503, the WTRU is configured to operate at the target network node in non-AI / ML operating mode; and In 504, a handover completion message is sent to the target network node, indicating to the target network node that the WTRU is configured to operate in non-AI / ML operating mode.

[0149] According to an embodiment of method 500, the AI / ML operation of the WTRU that determines the target network node cannot support at least one AI / ML function of the WTRU at the target network node is based on AI / ML information related to at least one AI / ML function, which is included in the received configuration information related to the handover of the WTRU from the source network node to the target network node.

[0150] According to an embodiment of the method, the AI / ML operation of the WTRU that determines the target network node cannot support at least one AI / ML function of the WTRU at the target network node is based on at least one of the following: the cell frequency of the target network node; the bandwidth portion allocated to the target network node; and the reference signal received from the target network node.

[0151] According to an embodiment of the method, instructing the target network node that the WTRU is configured to operate in a non-AI / ML operating mode is accomplished by including an indication that the WTRU is configured to operate in a non-AI / ML operating mode in the handover completion message.

[0152] According to an embodiment of the method, instructing the target network node that the WTRU is configured to operate in a non-AI / ML operating mode is accomplished by including an indication that the WTRU is configured to operate in a non-AI / ML operating mode in a Radio Resource Control (RRC) message sent after the handover completion message is sent.

[0153] According to an embodiment of the method, the at least one AI / ML function is included in AI / ML related information, which is included in received configuration information related to the handover of the WTRU from the source network node to the target network node.

[0154] An embodiment of a wireless transmit-receive unit (WTRU) in a network is also disclosed, the WTRU including at least one processor configured to: Receive configuration information from the network related to the handover of the WTRU from the source network node to the target network node; The AI / ML operation of the WTRU used for at least one artificial intelligence / machine learning (AI / ML) function is determined to be unsupported by the WTRU at the target network node; Configure WTRU to operate the WTRU at the target network node in non-AI / ML operation mode; and Send a handover completion message to the target network node and indicate to the target network node that the WTRU is configured to operate in non-AI / ML operation mode.

[0155] According to one embodiment, the at least one processor is configured to determine, based on AI / ML information related to the at least one AI / ML function, that the AI / ML operation of the WTRU for at least one AI / ML function of the WTRU at the target network node is not supported by the WTRU at the target network node, wherein the at least one AI / ML function is included in the received configuration information related to the handover of the WTRU from the source network node to the target network node.

[0156] According to one embodiment, the at least one processor is configured to determine, based on at least one of the following, that the AI / ML operation of the WTRU at the target network node cannot support at least one AI / ML function of the WTRU at the target network node: the cell frequency of the target network node; the bandwidth portion allocated to the target network node; and a reference signal received from the target network node.

[0157] According to one embodiment, the at least one processor is configured to indicate to the target network node that the WTRU is configured to operate in the non-AI / ML operation mode by including in the handover completion message an indication that the WTRU is configured to operate in the non-AI / ML operation mode.

[0158] According to one embodiment, the at least one processor is configured to indicate to the target network node that the WTRU is configured to operate in the non-AI / ML operating mode by including an indication in a Radio Resource Control (RRC) message sent after the handover completion message that the WTRU is configured to operate in the non-AI / ML operating mode.

[0159] According to one embodiment, the at least one AI / ML function is included in AI / ML related information, which is included in receive configuration information related to the handover of the WTRU from the source network node to the target network node. Figure 6 This is a flowchart of a method according to an embodiment.

[0160] Figure 6 This is a flowchart of method 600 according to an embodiment.

[0161] This method can be implemented by a wireless transmit-receive unit (WTRU) in the network and may include: In step 601, configuration information related to the handover of the WTRU from the source network node to the target network node is received from the network. In 602, it is determined that the reference signal received power RSRP of the source network node is greater than the configured RSRP value / range; In section 603, it is determined that the AI / ML operation of a WTRU used for at least one AI / ML function cannot be supported by the WTRU at the target network node; and In 604, an indication is sent to the source network node, instructing the WTRU to refuse to switch to the target network node.

[0162] According to an embodiment of method 600, the AI / ML operation of the WTRU that determines the target network node cannot support at least one AI / ML function of the WTRU at the target network node is based on AI / ML information related to at least one AI / ML function, which is included in the received configuration information related to the handover of the WTRU from the source network node to the target network node.

[0163] According to an embodiment of method 600, the configuration information includes information for accessing the target network node and RSRP values / ranges.

[0164] According to an embodiment of method 600, the configuration information includes a time window for activating the AI / ML operation of the WTRU at the target network node, and determining that the AI / ML operation of the WTRU with at least one AI / ML function of the WTRU at the target network node cannot be supported by the WTRU at the target network node includes considering the time window for activating the AI / ML operation of the WTRU at the target network node.

[0165] An embodiment of a wireless transmit-receive unit (WTRU) in a network is also disclosed, the WTRU including at least one processor configured to: Receive configuration information from the network related to the handover of the WTRU from the source network node to the target network node; Determine that the reference signal received power (RSRP) of the source network node is greater than the configured RSRP value / range; Determine that the AI / ML operation of the WTRU used for at least one artificial intelligence / machine learning (AI / ML) function cannot be supported by the WTRU at the target network node; and Send an indication to the source network node that the WTRU refuses to switch to the target network node.

[0166] According to one embodiment, the at least one processor is configured to determine, based on AI / ML information related to the at least one AI / ML function, that the AI / ML operation of the WTRU for at least one AI / ML function of the WTRU at the target network node is not supported by the WTRU at the target network node, wherein the at least one AI / ML function is included in received configuration information related to the handover of the WTRU from the source network node to the target network node.

[0167] According to one embodiment, the configuration information includes information for accessing the target network node and RSRP values / ranges.

[0168] According to one embodiment, the at least one processor is configured to determine a time window that takes into account the activation of AI / ML operations of the WTRU at the target network node, where the WTRU at the target network node cannot support the at least one AI / ML function of the WTRU at the target network node, and the configuration information includes the time window.

[0169] Figure 7 This is a flowchart of method 700 according to one embodiment.

[0170] This method can be implemented by a wireless transmit-receive unit (WTRU) in the network. The method may include: In step 701, configuration information is received from the network, the configuration information including information related to at least one AI / ML function supported by the WTRU; In step 702, an activation indication related to the activation of at least one AI / ML function by the WTRU is received from the network; In 703, at least one AI / ML function that has received an activation instruction and is supported by the WTRU is identified, and the at least one AI / ML function that has received the activation instruction and is supported by the WTRU is activated; and In 704, an instruction is sent to the network, which includes information related to at least one activated AI / ML function.

[0171] According to an embodiment of method 700, the configuration information includes at least one of the following: the priority of at least one AI / ML function supported by WTRU; the minimum cycle / duration for evaluating at least one AI / ML function supported by WTRU; and the configuration for reporting instructions.

[0172] According to an embodiment of method 700, the configuration information includes the priority and reporting configuration of the at least one AI / ML function supported by the WTRU, and wherein, when the WTRU is unable to activate the first priority of the AI / ML function that has received activation information, the WTRU reports to the network according to the reporting configuration.

[0173] According to an embodiment of method 700, the configuration information includes the minimum period / duration of the evaluation of at least one function supported by the WTRU, and based on the minimum period / duration of the evaluation, the method includes: Evaluate the supported AI / ML features; At least one supported AI / ML function is activated and at least one unsupported AI / ML function is deactivated. The instruction is sent to the network, the instruction including information related to at least one activated AI / ML function.

[0174] A wireless transmit-receive unit (WTRU) in a network is also disclosed, the WTRU including at least one processor, the at least one processor being configured to: Receive configuration information from the network, the configuration information including information related to at least one AI / ML function supported by the WTRU; Receive from the network an activation instruction related to the activation of at least one AI / ML function by the WTRU; Identify at least one AI / ML function that has received an activation instruction and can be supported by a WTRU, and activate at least one AI / ML function that has received an activation instruction and can be supported by a WTRU; and Send an instruction to the network, the instruction including information related to at least one activated AI / ML function.

[0175] According to one embodiment, the configuration information includes at least one of the following: the priority of at least one AI / ML function supported by WTRU; the minimum cycle / duration for evaluating at least one AI / ML function supported by WTRU; and the configuration for reporting instructions.

[0176] According to one embodiment, the at least one processor is configured to report to the network according to a reporting configuration when the WTRU fails to activate the first priority of the AI / ML function that received the activation information, the configuration information including the priority of the at least one AI / ML function supported by the WTRU and the reporting configuration.

[0177] According to one embodiment, the configuration information includes a minimum cycle / duration for evaluating at least one function supported by the WTRU, and the at least one processor is configured to perform the evaluation based on the minimum cycle / duration: Evaluate the supported AI / ML features; Activate at least one supported AI / ML function and deactivate any unsupported AI / ML functions; The instruction is sent to the network, the instruction including information related to at least one activated AI / ML function.

[0178] Figure 8 This is a flowchart of method 800 according to an embodiment. This method can be implemented by a WTRU in a network.

[0179] The method may include: In step 801, configuration information is received from the network, the configuration information including information related to artificial intelligence / machine learning (AI / ML) functions supported by WTRU; In 802, an activation instruction related to the activation of two or more AI / ML functions by the WTRU is received from the network; In 803, it is determined based on conditions that at least the first AI / ML function among two or more AI / ML functions can be supported by WTRU, and at least the second AI / ML function among two or more AI / ML functions cannot be supported by WTRU; In 804, activate at least the first AI / ML function; and In step 805, an instruction is sent to the network, which includes information related to at least the first activated AI / ML function.

[0180] According to an embodiment of the method, the conditions include at least one of the following: The available processing capacity of WTRU; Available storage capacity of WTRU; Radio conditions observed by WTRU; and Channel conditions observed by WTRU.

[0181] According to one embodiment, the conditions also include the priority of AI / ML functions as indicated in the configuration information.

[0182] According to one embodiment, the configuration information includes at least one of the following: the priority of AI / ML functions supported by WTRU; the periodicity of the evaluation of AI / ML functions supported by WTRU; and the configuration for reporting instructions to the network.

[0183] According to one embodiment, the configuration information includes the priority and reporting configuration of AI / ML functions supported by WTRU, wherein the WTRU reports to the network the priority of AI / ML functions that have received activation indications but cannot be activated due to the conditions, according to the reporting configuration.

[0184] According to an embodiment, the configuration information includes the periodicity of WTRU's evaluation of AI / ML functions supported by the WTRU, and the method includes, based on the periodicity of the evaluation: a) Evaluate AI / ML capabilities supported by WTRU; b) Based on the assessment, activate at least one supported AI / ML function and deactivate any unsupported AI / ML functions; and c) Send a list of activated AI / ML functions to the network.

[0185] The WTRU in the network is also disclosed and described, and the WTRU includes at least one processor. The at least one processor is configured to: Receive configuration information from the network, the configuration information including information related to artificial intelligence / machine learning (AI / ML) functions supported by the WTRU; Receive activation instructions from the network related to the activation of two or more AI / ML functions by WTRU; Based on the conditions, it is determined that at least a first AI / ML function among the two or more AI / ML functions can be supported by the WTRU, and at least a second AI / ML function among the two or more AI / ML functions cannot be supported by the WTRU; Activate at least the first AI / ML function; and Send an instruction to the network, the instruction including information related to at least one activated AI / ML function.

[0186] According to an embodiment of WTRU, the conditions include at least one of the following: The available processing capacity of WTRU; Available storage capacity of WTRU; Radio conditions observed by WTRU; and Channel conditions observed by WTRU.

[0187] According to an embodiment of WTRU, the conditions also include the priority of AI / ML functions as indicated in the configuration information.

[0188] According to an embodiment of WTRU, the configuration information includes at least one of the following: the priority of AI / ML functions supported by WTRU; the periodicity of the evaluation of AI / ML functions supported by WTRU; and the configuration for reporting instructions to the network.

[0189] According to an embodiment of WTRU, the configuration information includes the priority and reporting configuration of AI / ML functions supported by WTRU, wherein WTRU reports to the network the priority of AI / ML functions that have received activation instructions but cannot be activated due to conditions, according to the reporting configuration.

[0190] According to an embodiment of WTRU, the configuration information includes the periodicity of WTRU's evaluation of AI / ML functions supported by WTRU, and wherein at least one processor is configured to: Evaluate AI / ML capabilities supported by WTRU; Based on the evaluation, activate at least one supported AI / ML function and deactivate any unsupported AI / ML functions; Send a list of activated AI / ML features to the network.

[0191] in conclusion Although features and elements have been provided above in specific combinations, those skilled in the art will appreciate that each feature or element can be used alone or in combination with other features and elements. This disclosure is not limited to the specific embodiments described herein, which are intended to illustrate various aspects. Many modifications and variations can be made without departing from the spirit and scope of the invention, as will be apparent to those skilled in the art. No element, action, or instruction used in the description of this application should be construed as critical or essential to the invention unless explicitly provided so. Based on the foregoing description, functionally equivalent methods and apparatuses within the scope of this disclosure will be apparent to those skilled in the art, in addition to those listed herein. Such modifications and variations are intended to fall within the scope of the appended claims. This disclosure is limited only by the terms of the appended claims and the full scope of their equivalents. It should be understood that this disclosure is not limited to any particular method or system.

[0192] For simplicity, the foregoing embodiments have been discussed in terms of terminology and structure for devices with wireless communication capabilities (e.g., radio wave transmitters and receivers). However, the embodiments discussed are not limited to these systems, but can be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves (e.g., sound waves).

[0193] It should also 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 "image" can refer to any one of a snapshot, a single image, and / or multiple images displayed on a time-based basis. As another example, when referred to herein, the term "user equipment" and its abbreviation "WTRU," the term "remote," and / or the term "head-mounted display" and its abbreviation "HMD" can mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of several embodiments of a WTRU; (iii) a device with wireless and / or wired capabilities (e.g., tetherable) configured with some or all of the structure and functions of a WTRU; (iv) a device configured with fewer than all the structure and functions of a WTRU that supports wireless and / or wired connections; or (v) something like that. Figure 1A-1D Details of an example WTRU, representative of any WTRU described herein, are provided. As another example, the various embodiments disclosed above and below are described as utilizing a head-mounted display. Those skilled in the art will recognize that devices other than head-mounted displays can be utilized, and some or all of this disclosure and the various disclosed embodiments can be modified accordingly without excessive experimentation. Examples of such other devices may include drones or other devices configured to stream information to provide an adaptive, realistic experience.

[0194] Furthermore, the methods provided herein can be implemented in computer programs, software, or firmware, which are incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROMs and digital multifunction discs (DVDs). The processor associated with the software can be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0195] Modifications to the methods, apparatus, and systems described above may be made without departing from the scope of the invention. Given the various applicable embodiments, it should be understood that the illustrated embodiments are merely examples and should not be construed as limiting the scope of the appended claims. For example, embodiments provided herein include handheld devices that may include, or be used in conjunction with, any suitable voltage source providing any suitable voltage, such as a battery, and the like.

[0196] Furthermore, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices, including processors, are specified. These devices may include at least one central processing unit (“CPU”) and memory. According to the practice of those skilled in the art of computer programming, references to actions and symbolic representations of operations or instructions can be executed by various CPUs and memories. Such actions and operations or instructions may be referred to as “executed,” “computer-executed,” or “CPU-executed.”

[0197] Those skilled in the art will appreciate that the actions and symbolic representations of operations or instructions include the CPU's manipulation of electrical signals. Electrical systems represent data bits that can lead to the eventual conversion or reduction of electrical signals and are held at memory locations in a memory system, thereby reconfiguring or otherwise altering the operation of the CPU and other signal processing. The memory location that maintains the data bits is a physical location having specific electrical, magnetic, optical, or organic properties corresponding to or representing the data bits. It should be understood that the embodiments are not limited to the platforms or CPUs described above, and other platforms and CPUs may support the provided methods.

[0198] Data bits can also be stored on computer-readable media, including disks, optical disks, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage systems readable by the CPU. Computer-readable media can include cooperative or interconnected computer-readable media that reside exclusively on the processing system or are distributed across multiple interconnected processing systems, which can be located locally or remotely. It should be understood that the embodiments are not limited to the aforementioned memories, and other platforms and memories can support the provided methods.

[0199] In illustrative embodiments, any operations, processes, etc., described herein may be implemented as computer-readable instructions stored on a computer-readable medium. These computer-readable instructions may be executed by a processor of a mobile unit, network element, and / or any other computing device.

[0200] There is little difference between the hardware and software implementations of various aspects of the system. The use of hardware or software is often (but not always, as the choice between hardware and software may become important in certain contexts) a design choice representing a trade-off between cost and efficiency. Various means may exist to potentially implement the processes and / or systems and / or other technologies described herein (e.g., hardware, software, and / or firmware), and the preferred means may vary depending on the context of the deployment of the processes and / or systems and / or other technologies. For example, if the implementer determines that speed and accuracy are of paramount importance, the implementer may choose a primarily hardware and / or firmware approach. If flexibility is of paramount importance, the implementer may choose a primarily software implementation. Alternatively, the implementer may choose some combination of hardware, software, and / or firmware.

[0201] The foregoing detailed description illustrates various embodiments of the apparatus and / or process using block diagrams, flowcharts, and / or examples. Within the scope of such block diagrams, flowcharts, and / or examples encompassing one or more functions and / or operations, those skilled in the art will understand that each function and / or operation in such block diagrams, flowcharts, or examples can be implemented individually and / or collectively by various hardware, software, firmware, or virtually any combination thereof. In one embodiment, several portions of the subject matter described herein can be implemented using application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), and / or other integration formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein can be implemented, in whole or in part, equivalently in an integrated circuit, 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 substantially as any combination thereof, and that designing circuitry and / or writing code for software and / or firmware in accordance with this disclosure will be entirely within the skill of those skilled in the art. Furthermore, those skilled in the art will appreciate that the mechanisms of the subject matter described herein can be distributed as various forms of program products, and that the illustrative embodiments of the subject matter described herein are applicable to any particular type of signal-bearing medium actually used to perform the distribution. Examples of signal-bearing media include, but are not limited to, the following: recordable media, such as floppy disks, hard disk drives, CDs, DVDs, digital magnetic tapes, computer memory, etc.; and transmission media, such as digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0202] Those skilled in the art will recognize that it is common practice in the art to describe devices and / or processes in the manner set forth herein, and then to integrate such described devices and / or processes into data processing systems using engineering practice. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system through a reasonable number of experiments. Those skilled in the art will recognize that a typical data processing system typically includes one or more of the following: a system unit housing, a video display device, memory such as volatile and non-volatile memory, a processor such as a microprocessor and a digital signal processor, a computing entity such as an operating system, drivers, a graphical user interface, and applications, one or more interactive devices such as a touchpad or screen, and / or a control system including feedback loops and control motors (e.g., feedback for sensing position and / or speed, control motors for moving and / or adjusting components and / or quantities). A typical data processing system can be implemented using any suitable commercially available components (e.g., components commonly found in data computing / communication and / or network computing / communication systems).

[0203] The topics described herein sometimes illustrate that different components are contained within or connected to different other components. It should be understood that the architectures depicted are merely examples, and many other architectures can indeed be implemented to achieve the same functionality. Conceptually, any arrangement of components that achieve the same function is effectively “associated” to enable the desired functionality. Therefore, any two components combined herein to achieve a particular function can be considered “associated” with each other to enable the desired functionality, regardless of the architecture or intermediate components. Similarly, any two components so associated can also be considered “operably connected” or “operably coupled” to each other to achieve the desired functionality, and any two components that can be so associated can also be considered “operably coupled” to each other to achieve the desired functionality. Specific examples of operational coupling include, but are not limited to, physically matable and / or physically interactive components and / or wirelessly interactive components and / or logically interactive components.

[0204] Regarding the use of virtually any plural and / or singular terms in this document, those skilled in the art can translate plural into singular and / or from singular into plural depending on the context and / or application. For clarity, various singular / plural permutations may be clearly illustrated herein.

[0205] Those skilled in the art will understand that, in general, the terminology used herein, and especially the terminology used in the appended claims (e.g., the body of the appended claims), is typically intended as “open-ended” terminology (e.g., the term “comprising” should be interpreted as “including but not limited to,” the term “having” should be interpreted as “having at least,” the term “including” should be interpreted as “including but not limited to,” etc.). Those skilled in the art will further understand that if there is an intent to introduce a particular number of claim statements, such intent will be explicitly stated in the claims, and the absence of such a statement will not indicate such intent. For example, the term “single” or similar language may be used when only one item is intended. To aid understanding, the appended claims and / or the description herein may include the use of introductory phrases “at least one” and “one or more” to introduce claim statements. However, the use of such phrases should not be construed as implying that a claim statement introduced by the indefinite article “a” or “an” will limit any particular claim that includes such an introduced claim statement to only one embodiment of such a statement, even if 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 as meaning “at least one” or “one or more”). The same applies to the use of definite articles used to introduce claim statements. Furthermore, even if a specific number of introduced claim statements is explicitly stated, those skilled in the art will recognize that such a statement should be interpreted as meaning at least a number of statements (e.g., the simple statement “two statements” without other modifiers means at least two statements, or two or more statements). Furthermore, in instances where a convention similar to "at least one of A, B, and C" is used, this construction is generally intended to be understood by a person skilled in the art in the sense of the convention (e.g., "a system having at least one of A, B, and C" will include, but is not limited to, systems having a single A, a single B, a single C, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). In instances where a convention similar to "at least one of A, B, or C" is used, this construction is generally intended to be understood by a person skilled in the art in the sense of the convention (e.g., "a system having at least one of A, B, or C" will include, but is not limited to, systems having a single A, a single B, a single C, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). Those skilled in the art will further understand that, whether in the specification, claims, or drawings, any separating words and / or phrases that represent two or more alternative terms should be understood to include the possibility of including one of the terms, any one of the terms, or both of the terms. For example, the phrase “A or B” would be understood to include the possibility of “A” or “B” or “A and B”.Furthermore, as used herein, the term “any one” preceding a list of multiple items and / or multiple item categories is intended to include items alone or in combination with other items and / or other item categories, as well as any combination of “any one”, “any combination of”, “any multiple”, and / or “any combination of multiples of”. Additionally, as used herein, the term “set” is intended to include any number of items, including zero. Furthermore, as used herein, the term “quantity” is intended to include any quantity, including zero. And as used herein, the term “multiple” is intended to be synonymous with “plural”.

[0206] Furthermore, when features or aspects of this disclosure are described in accordance with the Markush Group, those skilled in the art will recognize that this disclosure is also described in accordance with any individual member or subgroup of the Markush Group.

[0207] As those skilled in the art will understand, for any and all purposes, such as for providing a written description, all scopes disclosed herein also encompass any and all possible subscopes and combinations thereof. Any listed scope can be readily considered sufficiently descriptive and makes it possible to decompose the same scope into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each scope discussed herein can be readily decomposed into a lower third, a middle third, and an upper third, etc. Those skilled in the art will also understand that all language (such as “at most,” “at least,” “greater than,” “less than,” and the like) includes the listed numbers and refers to a scope that can subsequently be decomposed into subscopes as described above. Finally, as those skilled in the art will understand, a scope includes each individual member. Thus, for example, a group with 1-3 cells means a group with 1, 2, or 3 cells. Similarly, a group with 1-5 cells means a group with 1, 2, 3, 4, or 5 cells, and so on.

[0208] Furthermore, unless otherwise stated, the claims should not be construed as limited to the provided order or elements. Additionally, the use of the term "means for..." in any claim is intended to refer to 35 USC §112, ¶ 6 or the claim format of means plus function, and any claim without the term "means for..." is not intended to be so.

Claims

1. A method implemented by a wireless transmit-receive unit (WTRU) in a network, wherein the method includes: Receive configuration information from the network, the configuration information including information related to artificial intelligence / machine learning (AI / ML) functions to be supported by WTRU; Receive activation instructions from the network related to the activation of two or more AI / ML functions by WTRU; Based on the conditions, it is determined that at least a first AI / ML function among the two or more AI / ML functions can be supported by WTRU, and at least a second AI / ML function among the two or more AI / ML functions cannot be supported by WTRU; Activate at least the first AI / ML function; and Send an instruction to the network, the instruction including information related to at least one activated AI / ML function.

2. The method of claim 1, wherein the condition includes at least one of the following: The available processing capacity of WTRU; Available storage capacity of WTRU; Radio conditions observed by WTRU; and Channel conditions observed by WTRU.

3. The method of claim 2, wherein the condition further includes the priority of AI / ML functions as indicated in the configuration information.

4. The method of claim 1, wherein the configuration information includes at least one of the following: priority of AI / ML functions supported by WTRU; periodicity of evaluation of AI / ML functions supported by WTRU; and configuration for reporting instructions to the network.

5. The method according to any one of claims 1 to 3, wherein the configuration information includes priority and reporting configuration of AI / ML functions supported by WTRU, and wherein the WTRU reports to the network, according to the reporting configuration, the priority of AI / ML functions that have received activation indications and cannot be activated due to the conditions.

6. The method of claim 1, wherein the configuration information includes the periodicity of WTRU evaluations of AI / ML functions supported by WTRU, and the method comprises, based on the periodicity of the evaluations: Evaluate AI / ML capabilities supported by WTRU; Based on the assessment, activate at least one supported AI / ML function and deactivate any unsupported AI / ML functions. Send a list of activated AI / ML features to the network.

7. A wireless transmit-receive unit (WTRU) in a network, comprising at least one processor, said at least one processor being configured to: Receive configuration information from the network, the configuration information including information related to artificial intelligence / machine learning (AI / ML) functions supported by the WTRU; Receive activation instructions from the network related to the activation of two or more AI / ML functions by WTRU; Based on the conditions, it is determined that at least a first AI / ML function among the two or more AI / ML functions can be supported by WTRU, and at least a second AI / ML function among the two or more AI / ML functions cannot be supported by WTRU; Activate at least the first AI / ML function; and Send an instruction to the network, the instruction including information related to at least one activated AI / ML function.

8. The WTRU of claim 7, wherein the condition includes at least one of the following: The available processing capacity of WTRU; Available storage capacity of WTRU; Radio conditions observed by WTRU; and Channel conditions observed by WTRU.

9. The WTRU of claim 8, wherein the condition further includes the priority of AI / ML functions as indicated in the configuration information.

10. The WTRU of claim 7, wherein the configuration information includes at least one of the following: priority of AI / ML functions supported by the WTRU; periodicity of evaluation of AI / ML functions supported by the WTRU; and configuration for reporting instructions to the network.

11. The WTRU according to any one of claims 7 to 9, wherein the configuration information includes priority and reporting configuration of AI / ML functions supported by the WTRU, and wherein the WTRU reports to the network, according to the reporting configuration, the priority of AI / ML functions that have received activation instructions and cannot be activated due to the conditions.

12. The WTRU of claim 7, wherein the configuration information includes the periodicity of the WTRU's evaluation of AI / ML functions supported by the WTRU, and wherein the at least one processor is configured to, according to the periodicity of the evaluation: Evaluate AI / ML capabilities supported by WTRU; Based on the assessment, activate at least one supported AI / ML function and deactivate any unsupported AI / ML functions. Send a list of activated AI / ML features to the network.

Images