Methods and apparatuses for switching location of artificial intelligence (AI) / machine learning (ML) operations

Abstract

A wireless transmit / receive unit (WTRU) comprises a processor configured to receive, from a network device, configuration information. The configuration information may indicate one or more reference signals (RSs) for measurement and a priority configuration of an artificial intelligence (AI) / machine learning (ML) (AI / ML) operation location at which an AI / ML operation is to be performed. The AI / ML operation location may be at the WTRU or at the network device. The processor may be configured to determine a WTRU prediction quality based on measurement values associated with the one or more RSs, determine a network prediction quality, determine a preferred AI / ML location based on the WTRU prediction quality, the network prediction quality, and the priority configuration, and send an indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation.

Description

METHODS AND APPARATUSES FOR SWITCHING LOCATION OF ARTIFICIAL INTELLIGENCE (AI)ZMACHINE LEARNING (ML) OPERATIONSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional Application No. 63 / 610,816 filed on December 15, 2023, the entire contents of which are incorporated herein by reference.BACKGROUND

[0002] Beam management technology may be a foundation in improving performance and complexity in conventional beam management aspects, including beam prediction in time, and / or spatial domain for overhead and latency reduction, beam selection accuracy improvement, etc.

[0003] Due to high complexity and / or computation requirement(s) of AI / ML operations (e.g., inference and / or training), a base station (e.g., gNB) may have a limitation on the number of wireless transmit / receive units (WTRUs) (e.g., one or more user equipment (UEs)) the base station can serve through AI / ML mode with a base station-side AI / ML model. If the total number of WTRUs the base station can serve is greater than its AI / ML mode WTRU-serving capacity, the base station may serve additional WTRUs in non-AI / ML (or legacy) mode of operation. However, this mode of operation may result loss of throughput for WTRUs served through legacy mode. In some examples, one method to minimize loss of throughput may be to enable WTRU-side AI / ML operations based on WTRUs’ AI / ML capability performance. WTRU-side AI / ML operations may allow the base station to serve other WTRUs (e.g., one or more WTRUs which do not have a WTRU-side AI / ML or have low WTRU-side AI / ML performance), with its own (e.g., base station-side) AI / ML model. Therefore, a WTRU procedure to assist the base station or the network to move / switch the location of AI / ML operations from base station to WTRU may be desired.SUMMARY

[0004] A wireless transmit / receive unit (WTRU) may comprise a processor. The processor may be configured to receive, from a network device, configuration information. The configuration information may indicate, for example, one or more reference signals (RSs) for measurement and a priority configuration of an artificial intelligence (Al) / machine learning (ML) (AI / ML) operation location at which an AI / ML operation is to be performed. The AI / ML operation location may be, for example, at the WTRU or at the network device. The processor may be configured to determine a WTRU prediction quality based on measurement values associated with the one or more RSs. The WTRU prediction quality may indicate, for example, a prediction quality associated with beam selection using the AI / ML operation location at the WTRU. The processor may be configured to determine a network prediction quality. The network prediction quality mayindicate, for example, a prediction quality associated with the beam selection using the AI / ML operation location at the network device. The processor may be configured to determine a preferred AI / ML location based on the WTRU prediction quality, the network prediction quality, and the priority configuration. The preferred AI / ML location may be, for example, at the WTRU or at the network device. The processor may be configured to send an indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation. The priority configuration of the AI / ML operation location may include, for example, an offset.

[0005] The processor may be configured to determine predicted beam IDs or predicted measurement values based on measurement values associated with the one or more RSs. The processor may be configured to determine the WTRU prediction quality based on the predicted beam IDs or predicted measurement values.

[0006] The processor may be configured to receive an indication of the network prediction quality from the network device. The processor may be configured to determine the network prediction quality based on the indication of the network prediction quality received from the network device.

[0007] The processor may be configured to determine a measurement value of a network devicepredicted best beam. The measurement value of the network device-predicted best beam may be, for example, determined by the WTRU measuring one or more RSs associated with an indicated transmission configuration indicator (TCI) state. The processor may be configured to determine a network prediction accuracy based on the determined measurement value of the network device-predicted best beam. The processor may be configured to compare a predicted measurement value indicated by the WTRU and the determined measurement value of the network device-predicted best beam. The processor may be configured to determine the network prediction quality based on the difference between the predicted measurement value and the determined measurement value of the network device-predicted best beam.

[0008] The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, the network prediction quality.

[0009] The processor may be configured to determine the preferred AI / ML location to be at the WTRU based on the WTRU prediction quality being less than a combination of the network prediction quality and an offset indicated by the priority configuration.

[0010] The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, a flag indicating that the WTRU’s preferred location of AI / ML operation is at the WTRU or at the network device. The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, an indication of one or more WTRU predicted beams. The indication of the preferred AI / MLlocation to the network device for performing the beam selection using the AI / ML operation may include, for example, an indication of the WTRU prediction quality.

[0011] A WTRU may be configured to perform a method that includes one or more of the following steps. The method may include receiving, from a network device, configuration information. The configuration information may indicate, for example, one or more reference signals (RSs) for measurement and a priority configuration of an artificial intelligence (Al)Zmachine learning (ML) (AI / ML) operation location at which an AI / ML operation is to be performed. The AI / ML operation location may be, for example, at the WTRU or at the network device. The method may include determining a WTRU prediction quality based on measurement values associated with the one or more RSs. The WTRU prediction quality may indicate, for example, a prediction quality associated with beam selection using the AI / ML operation location at the WTRU. The method may include determining a network prediction quality. The network prediction quality may indicate, for example, a prediction quality associated with the beam selection using the AI / ML operation location at the network device. The method may include determining a preferred AI / ML location based on the WTRU prediction quality, the network prediction quality, and the priority configuration. The preferred AI / ML location may be, for example, at the WTRU or at the network device. The method may include sending an indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation. The priority configuration of the AI / ML operation location may include, for example, an offset.

[0012] The method may include determining predicted beam IDs or predicted measurement values based on measurement values associated with the one or more RSs. The method may include determining the WTRU prediction quality based on the predicted beam IDs or predicted measurement values.

[0013] The method may include receiving an indication of the network prediction quality from the network device. The method may include determining the network prediction quality based on the indication of the network prediction quality received from the network device.

[0014] The method may include determining a measurement value of a network device-predicted best beam. The measurement value of the network device-predicted best beam may be, for example, determined by the WTRU measuring one or more RSs associated with an indicated transmission configuration indicator (TCI) state. The method may include determining a network prediction accuracy based on the determined measurement value of the network device-predicted best beam. The method may include comparing a predicted measurement value indicated by the WTRU and the determined measurement value of the network device-predicted best beam. The method may include determining the network prediction quality based on the difference between the predicted measurement value and the determined measurement value of the network device-predicted best beam.

[0015] The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, the network prediction quality.

[0016] The method may include determining the preferred AI / ML location to be at the WTRU based on the WTRU prediction quality being less than a combination of the network prediction quality and an offset indicated by the priority configuration.

[0017] The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, a flag indicating that the WTRU’s preferred location of AI / ML operation is at the WTRU or at the network device. The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, an indication of one or more WTRU predicted beams. The indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation may include, for example, an indication of the WTRU prediction quality.BRIEF DESCRIPTION OF THE DRAWINGS

[0018] A more detailed understanding may be had from the detailed description below, given by way of example in conjunction with drawings appended hereto. Figures in such drawings, like the detailed description, are examples. As such, the Figures (FIGs.) and the detailed description are not to be considered limiting, and other equally effective examples are possible and likely. Furthermore, like reference numerals ("ref.") in the FIGs. indicate like elements, and wherein:

[0019] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0020] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0021] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0022] FIG. 1 D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0023] FIG. 2 is a diagram illustrating an example of beam groups and beams from set B, according to an embodiment.DETAILED DESCRIPTION

[0024] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of embodiments and / or examples disclosed herein. However, it will be understood that suchembodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components and circuits have not been described in detail, so as not to obscure the following description. Further, embodiments and examples not specifically described herein may be practiced in lieu of, or in combination with, the embodiments and other examples described, disclosed or otherwise provided explicitly, implicitly and / or inherently (collectively "provided") herein. Although various embodiments are described and / or claimed herein in which an apparatus, system, device, etc. and / or any element thereof carries out an operation, process, algorithm, function, etc. and / or any portion thereof, it is to be understood that any embodiments described and / or claimed herein assume that any apparatus, system, device, etc. and / or any element thereof is configured to carry out any operation, process, algorithm, function, etc. and / or any portion thereof.Communications Networks and Devices

[0025] The methods, apparatuses and systems provided herein are well-suited for communications involving both wired and wireless networks. An overview of various types of wireless devices and infrastructure is provided with respect to FIGs. 1A-1 D, where various elements of the network may utilize, perform, be arranged in accordance with and / or be adapted and / or configured for the methods, apparatuses and systems provided herein.

[0026] FIG. 1A is a system diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), zero-tail (ZT) unique-word (UW) discreet Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0027] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (ON) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a "station" and / or a "STA", may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station,a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fl device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0028] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, e.g., to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the networks 112. By way of example, the base stations 114a, 114b may be any of a base transceiver station (BTS), a Node-B (NB), an eNode-B (eNB), a Home Node-B (HNB), a Home eNode-B (HeNB), a gNode-B (gNB), a NR Node-B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0029] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in an embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0030] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0031] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and / or High-Speed Uplink Packet Access (HSUPA).

[0032] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0033] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0034] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0035] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0036] The base station 114b in FIG. 1A may be a wireless router, Home Node-B, Home eNode-B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN).In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish any of a small cell, picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0037] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d . The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing an NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing any of a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technology.

[0038] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 114 or a different RAT.

[0039] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0040] FIG. 1 B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, aspeaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138, among others. It will be appreciated that the WTRU 102 may include any subcombination of the foregoing elements while remaining consistent with an embodiment.

[0041] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1 B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, e.g., in an electronic package or chip.

[0042] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0043] Although the transmit / receive element 122 is depicted in FIG. 1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116

[0044] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11 , for example.

[0045] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display(LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0046] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0047] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable locationdetermination method while remaining consistent with an embodiment.

[0048] The processor 118 may further be coupled to other elements / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality and / or wired or wireless connectivity. For example, the elements / peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (e.g., for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, and the like. The elements / peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0049] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the uplink (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the uplink (e.g., for transmission) or the downlink (e.g., for reception)).

[0050] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0051] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0052] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the uplink (UL) and / or downlink (DL), and the like. As shown in FIG. 1 C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0053] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any one of these elements may be owned and / or operated by an entity other than the CN operator.

[0054] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0055] The SGW 164 may be connected to each of the eNode-Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter- eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0056] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0057] The ON 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0058] Although the WTRU is described in FIGs. 1A-1 D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0059] In representative embodiments, the other network 112 may be a WLAN.

[0060] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a distribution system (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to- peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an "ad- hoc" mode of communication.

[0061] When using the 802.11 ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be afixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier sense multiple access with collision avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0062] High throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0063] Very high throughput (VHT) STAs may support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse fast fourier transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above-described operation for the 80+80 configuration may be reversed, and the combined data may be sent to a medium access control (MAC) layer, entity, etc.

[0064] Sub 1 GHz modes of operation are supported by 802.11 af and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.11 af and 802.11 ah relative to those used in 802.11n, and 802.11ac. 802.11 af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV white space (TVWS) spectrum, and 802.11 ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11 ah may support meter type control / machine- type communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0065] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11 n, 802.11ac, 802.11 af, and 802.11 ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode.In the example of 802.11 ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0066] In the United States, the available frequency bands, which may be used by 802.11 ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11 ah is 6 MHz to 26 MHz depending on the country code.

[0067] FIG. 1 D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0068] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0069] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., including a varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0070] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non-standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0071] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, and the like. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0072] The CN 115 shown in FIG. 1 D 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 are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0073] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b, e.g., to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and / or the like. The AMF 162 may provide a controlplane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as Wi-Fi.

[0074] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernetbased, and the like.

[0075] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, e.g., to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0076] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0077] In view of FIGs. 1 A-1 D, and the corresponding description of FIGs. 1 A-1 D, one or more, or all, of the functions described herein with regard to any of: WTRUs 102a-d, base stations 114a-b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other element(s) / device(s) described herein, may be performed by one or more emulation elements / devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0078] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within thecommunication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0079] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0080] Artificial intelligence may be broadly defined as the behavior exhibited by machines. Such behavior may, for example, mimic cognitive functions to sense, reason, adapt and / or act.

[0081] Machine learning may refer to type of algorithms that solve a problem based on learning through experience (“data”), without explicitly being programmed (“configuring set of rules”). Machine learning can be considered as a subset of Al. Different machine learning paradigms may be envisioned based on the nature of data or feedback available to the learning algorithm. For example, a supervised learning approach may involve learning a function that maps input to an output based on labeled training example, wherein each training example may be a pair consisting of input and the corresponding output. For example, unsupervised learning approach may involve detecting patterns in the data with no pre-existing labels. For example, reinforcement learning approach may involve performing sequence of actions in an environment to maximize the cumulative reward. In some embodiments, it is possible to apply machine learning algorithms using a combination or interpolation of the above-mentioned approaches. For example, semisupervised learning approach may use a combination of a small amount of labeled data with a large amount of unlabeled data during training. In this regard semi-supervised learning falls between unsupervised learning (e.g., with no labeled training data) and supervised learning (e.g., with only labeled training data).

[0082] Deep learning refers to a class of machine learning algorithms that employ artificial neural networks (specifically DNNs) which were loosely inspired from biological systems. The Deep Neural Networks (DNNs) are a special class of machine learning models inspired by human brain wherein the input is linearly transformed and pass-through non-linear activation function multiple times. DNNs typically consists of multiple layers where each layer consists of linear transformation and a given non-linear activation functions. The DNNs can be trained using the training data via back-propagation algorithm. Recently, DNNs have shown state-of-the-art performance in variety of domains, e.g., speech, vision,natural language etc. and for various machine learning settings supervised, un-supervised, and semisupervised. The term AI / ML based methods / processing may refer to realization of behaviors and / or conformance to requirements by learning based on data, without explicit configuration of sequence of steps of actions. Such methods may enable learning complex behaviors which might be difficult to specify and / or implement when using legacy methods.

[0083] A WTRU may transmit or receive a physical channel or reference signal according to at least one spatial domain filter. The term “beam" may be used to refer to a spatial domain filter.

[0084] The WTRU may transmit a physical channel or signal using the same spatial domain filter as the spatial domain filter used for receiving an reference signal (RS) (such as channel state information (CSI) RS) or a synchronization signal (SS) block. The WTRU transmission may be referred to as “target”, and the received RS or SS block (SSB) may be referred to as “reference” or “source". In such case, the WTRU may be said to transmit the target physical channel or signal according to a spatial relation with a reference to such RS or SS block.

[0085] The WTRU may transmit a first physical channel or signal according to the same spatial domain filter as the spatial domain filter used for transmitting a second physical channel or signal. The first and second transmissions may be referred to as “target” and “reference" (or “source”), respectively. In such case, the WTRU may be said to transmit the first (target) physical channel or signal according to a spatial relation with a reference to the second (reference) physical channel or signal.

[0086] A spatial relation may be implicit, configured by radio resource control (RRC) or signaled by medium access control - control element (MAC-CE) or downlink control information (DCI). For example, a WTRU may implicitly transmit physical uplink shared channel (RUSCH) and demodulation reference signals (DM-RS) of PUSCH according to the same spatial domain filter as an sounding reference signal (SRS) indicated by an SRS resource indicator (SRI) indicated in DCI or configured by RRC. In another example, a spatial relation may be configured by RRC for a SRI or signaled by MAC-CE for a physical uplink control channel (PUCCH). Such spatial relation may also be referred to as a “beam indication”.

[0087] The WTRU may receive a first (e.g. , target) downlink channel or signal according to the same spatial domain filter or spatial reception parameter as a second (e.g., reference) downlink channel or signal. For example, such association may exist between a physical channel such as physical downlink control channel (PDCCH) or physical downlink shared channel (PDSCH) and its respective DM-RS. At least when the first and second signals are reference signals, such association may exist when the WTRU is configured with a quasi-colocation (QCL) assumption type D between corresponding antenna ports. Such association may be configured as a transmission configuration indicator (TCI) state. A WTRU may be indicated an association between a CSI-RS or SS block and a DM-RS by an index to a set of TCI statesconfigured by RRC and / or signaled by MAC-CE. Such indication may also be referred to as a “beam indication".

[0088] In various embodiments, a transmission and reception point (TRP) may be interchangeably used with one or more of a transmission point (TP), a reception point (RP), a radio remote head (RRH), a distributed antenna (DA), a base station (BS), a sector (of a BS), and / or a cell (e.g., a geographical cell area served by a BS), but still consistent with methods and apparatuses described herein. Multi-TRP may be interchangeably used with one or more of an MTRP, an M-TRP, and / or multiple TRPs, but still consistent with t methods and apparatuses described herein.

[0089] A WTRU may report a subset of channel state information (CSI) components, where CSI components may correspond to at least a CSI-RS resource indicator (CRI), an SSB resource indicator (SSBRI), an indication of a panel used for reception at the WTRU (e.g., a panel identity or a group identity), measurements such as layer 1 - reference signal received power (L1-RSRP), layer 1 - signal-to-noise and interference ratio (L1 -SINR) taken from SSB or CSI-RS (e.g., cri-RSRP, cri-SINR, ssb-lndex-RSRP, ssb- Index-SINR), and other channel state information such as at least rank indicator (Rl), channel quality indicator (CQI), precoding matrix indicator (PM I), Layer Index (LI), and / or the like.

[0090] A WTRU may receive a synchronization signal / physical broadcast channel (SS / PBCH) block. The SS / PBCH block (SSB) may include a primary synchronization signal (PSS), secondary synchronization signal (SSS), and physical broadcast channel (PBCH). The WTRU may monitor, receive, or attempt to decode an SSB during initial access, initial synchronization, radio link monitoring (RLM), cell search, cell switching, and so forth.

[0091] A WTRU may measure and report the channel state information (CSI), wherein the CSI for each connection mode may include or be configured with one or more of following.

[0092] For example, a CSI Report configuration may include an indication of CSI report quantity, such as a channel quality indicator (CQI), a rank indicator (Rl), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), and / or a layer indicator (LI). The CSI Report configuration may include a CSI report type, such as aperiodic, semi persistent, periodic CSI report types. The CSI report configuration may include a CSI report codebook configuration (e.g., Type I, Type II, and / or Type II port selection). The CSI report configuration may include an indication of CSI report frequency.

[0093] In some examples, a CSI-RS Resource set may include one or more of the following. For example, a CSI-RS Resource set may include CSI Resource settings, for instance non-zero power (NZP) CSI-RS Resource for channel measurement, NZP-CSI-RS Resource for interference measurement, and / or CSI interference measurement (IM) Resource for interference measurement.

[0094] NZP CSI-RS Resources may include one or more of the following. For example, NZP CSI-RS Resources may include NZP CSI-RS Resource ID, periodicity and offset, quasi co-location (QCL) Informationand transmission configuration indicator (TCI) state, and / or resource mapping (e.g., number of ports, density, CDM type, etc.).

[0095] For example, a WTRU may indicate, determine, or be configured with one or more reference signals (RSs). The WTRU may monitor, receive, and measure one or more parameters based on the respective reference signals. For example, one or more of the following may apply. The following parameters are non-limiting examples of the parameters that may be included in reference signal(s) measurements. In some examples, one or more of the parameters discussed herein may be included. In some cases, one or more other parameters may be included.

[0096] The WTRU may measure SS reference signal received power (SS-RSRP) based on the synchronization signals (e.g., demodulation reference signal (DM-RS) in PBCH or SSS). SS-RSRP may be defined as the linear average over the power contribution of the resource elements (REs) that carry the respective synchronization signal. In measuring the RSRP, power scaling for the reference signals may be required. In case SS-RSRP is used for L1 -RSRP, the measurement may be accomplished based on CSI reference signals in addition to the synchronization signals.

[0097] The WTRU may measure CSI-RSRP based on the linear average over the power contribution of the resource elements (REs) that carry the respective CSI-RS. The CSI-RSRP measurement may be configured within measurement resources for the configured CSI-RS occasions.

[0098] The WTRU may measure SS signal-to-noise and interference ratio (SS-SINR) based on the synchronization signals (e.g., DM-RS in PBCH or SSS). It may be defined as the linear average over the power contribution of the resource elements (REs) that carry the respective synchronization signal divided by the linear average of the noise and interference power contribution. In case SS-SINR is used for L1- SINR, the noise and interference power measurement may be accomplished based on resources configured by higher layers.

[0099] The WTRU may measure CSI-SINR based on the linear average over the power contribution of the resource elements (REs) that carry the respective CSI-RS divided by the linear average of the noise and interference power contribution. In case CSI-SINR is used for L1-SINR, the noise and interference power measurement may be accomplished based on resources configured by higher layers Otherwise, the noise and interference power may be measured based on the resources that carry the respective CSI-RS.

[0100] The WTRU may measure received signal strength indicator (RSSI) may be measured based on the average of the total power contribution in configured OFDM symbols and bandwidth. The power contribution may be received from different resources (e.g., co-channel serving and non-serving cells, adjacent channel interference, thermal noise, and so forth).

[0101] The WTRU may measure cross-Layer interference received signal strength indicator (CLI-RSSI) may be measured based on the average of the total power contribution in configured OFDM symbols of theconfigured time and frequency resources. The power contribution may be received from different resources (e.g., cross-layer interference, co-channel serving and non-serving cells, adjacent channel interference, thermal noise, and so forth).

[0102] The WTRU may measure sounding reference signals RSRP (SRS-RSRP) may be measured based on the linear average over the power contribution of the resource elements (REs) that carry the respective SRS.

[0103] A CSI report configuration (e.g., CSI-ReportConfigs) may be associated with a single bandwidth part (BWP) (e.g., indicated by BWP-ld). A CSI report configuration may configure one or more of the following parameters The CSI report configuration may configure CSI-RS resources and / or CSI-RS resource sets for channel and interference measurement. The CSI report configuration may configure a CSI-RS report configuration type, such as the periodic, semi-persistent, and / or aperiodic. The CSI report configuration may configure a CSI-RS transmission periodicity for periodic and semi-persistent CSI reports. The CSI report configuration may configure a CSI-RS transmission slot offset for periodic, semi-persistent and / or aperiodic CSI reports. The CSI report configuration may configure a CSI-RS transmission slot offset list for semi-persistent and / or aperiodic CSI reports. The CSI report configuration may configure time restrictions for channel and / or interference measurements. The CSI report configuration may configure a report frequency band configuration (e.g., wideband / subband CQI, PMI, and / or so forth). The CSI report configuration may configure thresholds and / or modes of calculations for the reporting quantities (e.g., CQI, RSRP, SINR, LI, Rl, etc.). The CSI report configuration may configure a codebook configuration. The CSI report configuration may configure group based beam reporting. The CSI report configuration may configure a CQI table. The CSI report configuration may configure a subband size. The CSI report configuration may configure a non-PMI port indication. The CSI report configuration may configure a Port Index.

[0104] In CSI-RS resource configuration, a CSI-RS resource set (e.g., NZP-CSI-RS-Resourceset) may include one or more of CSI-RS resources (e.g., NZP-CSI-RS-Resource and CSI-ResourceConfig), where a WTRU may be configured with one or more of the following in a CSI-RS Resource. For example, a WTRU may be configured with CSI-RS periodicity and slot offset for periodic and semi-persistent CSI-RS Resources. A WTRU may be configured with CSI-RS resource mapping to define the number of CSI-RS ports, density, CDM-type, OFDM symbol, and / or subcarrier occupancy. A WTRU may be configured with the bandwidth part to which the configured CSI-RS is allocated. A WTRU may be configured with the reference to the TCI-State including the QCL source RS(s) and the corresponding QCL type(s).

[0105] In RS resource set configuration, one or more of following configurations may be used for RS resource set. For example, a WTRU may be configured with one or more RS resource sets. The RS resource set configuration may include one or more of following. For instance, the RS resource setconfiguration may include RS resource set ID. The RS resource set configuration may include one or more RS resources for the RS resource set. The RS resource set configuration may include repetition (e.g., on or off). The RS resource set configuration may include aperiodic triggering offset (e.g., one of 0-6 slots). The RS resource set configuration may include tracking reference signal (TRS) information (e.g., true or not).

[0106] In RS resource configuration, one or more of the following configurations may be used for RS resource. A WTRU may be configured with one or more RS resources. The RS resource configuration may include one or more of following. For example, the RS resource configuration may include RS resource ID. The RS resource configuration may include resource mapping (e.g., REs in a physical resource block (PRB)). The RS resource configuration may include power control offset (e.g., one value of -8, ... , 15). The RS resource configuration may include power control offset with SS (e.g., -3 dB, 0 dB, 3 dB, 6 Db). The RS resource configuration may include scrambling ID. The RS resource configuration may include periodicity and offset. The RS resource configuration may include QCL information (e.g., based on a TCI state).

[0107] The WTRU may receive a grant or assignment. A property of a grant or assignment may include at least one of the following. For example, a property of a grant or assignment may include a frequency allocation. A property of a grant or assignment may include an aspect of time allocation (e.g., such as a duration). A property of a grant or assignment may include a priority. A property of a grant or assignment may include a modulation and coding scheme (MCS). A property of a grant or assignment may include a transport block size. A property of a grant or assignment may include a number of spatial layers. A property of a grant or assignment may include a number of transport blocks. A property of a grant or assignment may include a TCI state, an indication of CRI or SRI. A property of a grant or assignment may include a number of repetitions. A property of a grant or assignment may include an indication of whether the repetition scheme is Type A or Type B. A property of a grant or assignment may include an indication of whether the grant is a configured grant type 1 , type 2 or a dynamic grant. A property of a grant or assignment may include an indication of whether the assignment is a dynamic assignment or a semi- persistent scheduling (e.g., configured) assignment. A property of a grant or assignment may include a configured grant index or a semi-persistent assignment index. A property of a grant or assignment may include a periodicity of a configured grant or assignment. A property of a grant or assignment may include a channel access priority class (CAPC). A property of a grant or assignment may include one or more parameters provided in a DCI, by MAC or by RRC for the scheduling the grant or assignment.

[0108] An indication by DCI may include an explicit indication by a DCI field or by RNTI used to mask or scramble the CRC of the DCI. The indication by DCI may include an implicit indication by a property, for example, such as DCI format, DCI size, control resource set (CORESET) or search space, aggregation Level, and / or first resource element of the received DCI (e.g., index of first control channel clement (CCE)). The mapping between the property and the value may be signaled by RRC or MAC.

[0109] In various embodiments, an RS may be interchangeably used with one or more of an RS resource, an RS resource set, an RS port, and / or an RS port group, but still consistent with the methods and apparatuses described herein.

[0110] In various embodiments, an RS may be interchangeably used with one or more of an SSB, a CSI- RS, an SRS, a DM-RS, a TRS, a PRS, and / or a PTRS, but still consistent with the methods and apparatuses described herein.

[0111] A reference signal (RS) may be interchangeably used with one or more of following. For example, a signal may be interchangeably used with a sounding reference signal (SRS). A signal may be interchangeably used with a channel state information - reference signal (CSI-RS). A signal may be interchangeably used with a demodulation reference signal (DM-RS). A signal may be interchangeably used with a phase tracking reference signal (PT-RS). A signal may be interchangeably used with a synchronization signal block (SSB).

[0112] A channel may be interchangeably used with one or more of following. For example, a channel may be interchangeably used with a physical downlink control channel (PDCCH). A channel may be interchangeably used with a physical downlink shared channel (PDSCH). A channel may be interchangeably used with a physical uplink control channel (PUCCH). A channel may be interchangeably used with a physical uplink shared channel (PUSCH). A channel may be interchangeably used with a physical random access channel (PRACH)..

[0113] A key performance indicator (KPI) may refer to one or more of the following. For example, a key performance indicator may refer to a signal quality (e.g., L1-RSRP, SINR, CQI, RSSI, RSRQ). A key performance indicator may refer to a prediction performance (e.g., percentage of the Top-1 genie-aided (e.g., best) beam is one of the Top-K predicted beams). A key performance indicator may refer to a link quality (e.g., throughput, block error rate (BLER)). A key performance indicator may refer to a data distribution (e.g., mean and / or variance of measured and / or predicted beam measurements). A key performance indicator may refer to a RSRP (e.g., L1-RSRP) difference (i.e., the difference between measured and predicted RSRP of a beam).

[0114] A signal, channel, and message (e.g., as in downlink or uplink signal, channel, and message) may be used interchangeably, but still consistent with the methods and apparatuses described herein.

[0115] A RS resource set may be interchangeably used with an RS resource and a beam group, but still consistent with the methods and apparatuses described herein.

[0116] Beam reporting may be interchangeably used with CSI measurement, CSI reporting and beam measurement, but still consistent with the methods and apparatuses described herein.

[0117] The proposed procedures for beam resources prediction may be used for beam resources belonging to a single or multiple cells as well as single or multiple TRPs, and still consistent with the methods and apparatuses described herein.

[0118] CSI reporting may be interchangeably used with CSI measurement, beam reporting and beam measurement, but still consistent with the methods and apparatuses described herein.

[0119] A RS resource set may be interchangeably used with a beam group, but still consistent with the methods and apparatuses described herein.

[0120] A set B may be interchangeably used with a set of: RS resource sets, beams, beam-pairs, beam RS resources, RS resources, and / or beam pattern(s) A set B may be interchangeably used with measurement RS resources, a measurement RS resource set, measurement beam resources, a measurement beam resource set, a measurement beam pattern, measurement TCI states, and / or a measurement TCI state group, but still consistent with the methods and apparatuses described herein.

[0121] A set A may be interchangeably used with a set of: RS resource sets, beams, beam-pairs, beam RS resources, RS resources, and / or beam pattern(s).

[0122] An active set B may refer to a set B which is currently being used by a WTRU to make predictions and the predicted outputs (e.g., beam IDs, beam RS IDs, RSRPs) are currently reported and / or used by the WTRU. An inactive set B may refer to a set B which is either not used by a WTRU to make any predictions and / or the predictions associated with the aforementioned (e.g., inactive) set B is not currently reported and / or used by the WTRU.

[0123] Beam prediction accuracy may be interchangeably used with prediction accuracy, but still consistent with the methods and apparatuses described herein.

[0124] Local beam prediction accuracy KPIs may be implemented. One or more methods and procedures discussed herein may relate to beam predictions using KPIs and / or parameters / factors. In some examples, based on the type of WTRU prediction (e.g., type of AI / ML model output), the WTRU calculates KPI using one or more of the following procedures. In one example, the WTRU predicts RSRP values, and the best predicted beam is determined based on predicted RSRP values. For instance, if the predicted beam is from set A and not measured from set B or inactive set B, then prediction accuracy is calculated based on the measured RSRP of the predicted beam (e.g., a TCI state) and the predicted RSRP. For instance, if the predicted beam is from set B or measured beam of inactive set B, then prediction accuracy is calculated based on the predicted RSRP and the measured RSRP.

[0125] In another example, the WTRU may predict best beam indexes. For example, the WTRU may determine and / or define beam groups and each beam group is represented by a set B beam and includes multiple set A beams.

[0126] In an example, the WTRU may receive a configuration of number of beam groups, N_BG, the size (number of beams) of a beam group, SIZE_BG and the starting beam ID, STARTJD, of the first beam group. For instance, if a beam group of the predicted best set A beam is same as the beam group of the best set B beam in the measurement, it may assume that the prediction is correct. In some cases, a time duration for the measurement may be supported. In an example, 10 measurements having 7 correct and 3 incorrect indicate 70% accuracy. In an aspect, for calculating beam prediction accuracy, neighboring beam groups are considered. In an example, if beam groups are same, then plus 1 . If the predicted beam is in neighboring beam groups of the best measured beam group, then plus 0.5. For example, beam prediction accuracy may be calculated as: 1 (correct) + 0.5 (neighboring) + 0 (incorrect) + 1 (correct) + 0 (incorrect) / 5 (number of trials) = 2.5 / 5 = 50% accuracy.

[0127] In one embodiment, a WTRU may be configured to predict one or more best beams for transmission and / or reception of one or more signals and / or channels, where the WTRU may measure, calculate, and / or determine one or more KPIs for monitoring the performance and / or the accuracy of the predicted beams and / or the prediction procedure.

[0128] In one embodiment, a WTRU may determine, be configured, or receive one or more configuration information and / or indications (e.g., via RRC, MAC-CE, or DCI) to perform one or more actions for calculating one or more KPIs. The WTRU may determine the actions for calculating the KPIs based on one or more “prediction types” that may be identified in association with the procedure and / or system model that is used for the predictions. In an example, the WTRU may determine one or more prediction types based on the predicted parameters. In another example, in an AI / ML system, the WTRU may determine one or more prediction types based on the output of the AI / ML system. For example, the WTRU may determine, be (pre)configured, and / or receive configurations on the different prediction types. The WTRU may calculate one or more KPIs based on the determined and / or configured prediction types.

[0129] One or more of the following examples of procedures and / or parameters may be used to calculate KPIs. In some examples, the WTRU may predict RSRP. For instance, a WTRU may determine one or more best predicted beams based on one or more predicted parameters. In an example, the WTRU may predict one or more parameters based on measurements, where the predicted parameters may include, e.g., RSRP, RSRQ, SINR, etc. For example, the WTRU may determine one or more best predicted beams based on one or more predicted RSRP values.

[0130] In one embodiment, a WTRU may determine and / or calculate the prediction accuracy for one or more predicted beam resources. In an example, the WTRU may compare one or more predicted parameters with one or more measured parameters. In an example, if the difference between the predicted parameters and the corresponding measured parameters is lower than a determined and / or configured threshold, the WTRU may determine that the prediction accuracy is acceptable (e.g., the prediction isvalid). If the difference between the predicted parameters and the corresponding measured parameters is higher than the determined and / or configured threshold, the WTRU may determine that the prediction accuracy is non-acceptable (e.g., the prediction is invalid). One or more of the following options may be used.

[0131] In some examples, the WTRU may determine that the predicted beam belongs to the determined and / or configured set A (e.g., the WTRU may determine that the predicted beam may not be from one or more active and / or inactive set Bs). The WTRU may measure RSRP based on one or more signals and / or channels that have the same TCI-state with the predicted beam. For example, the WTRU may measure the RSRP of one or more signals and / or channels that have a spatial relation, for example based on QCL Type D, with the predicted beam. In an example, the WTRU may determine the signals and / or channels to be measured based on the spatial domain filter that is used for receiving them. In an example, the WTRU may measure the RSRP based on one or more signals, for example SSB, CSI-RS, phase tracking reference signal (PT-RS), tracking reference signal (TRS), etc. In another example, the WTRU may measure the RSRP based on one or more reference signals associated with one or more channels, for example PDCCH DM-RS, PDSCH DM-RS, PBCH DM-RS, etc. In one embodiment, a WTRU may compare the predicted RSRP with the measured RSRP and determine the prediction accuracy, accordingly.

[0132] In some examples, the WTRU may determine that the predicted beam belongs to one or more of active set B(s) and / or inactive set B(s) The WTRU may compare the predicted RSRP with the measured RSRP and determine the prediction accuracy.

[0133] In some examples, the WTRU may predict beam indexes. For example, a WTRU may determine, be (pre)configured, and / or receive one or more configuration information and / or indications on one or more beam groups. For instance, the WTRU may receive the configuration information and / or indications on the beam groups via RRC, MAC-CE, DCI, etc. In an example, the WTRU may determine that each determined, received, and / or configured beam groups may include at least a beam from a configured and / or determined set B and one or more beams from a configured and / or determined set A (referring to FIG. 2). The configuration information and / or indications may include one or more of the following parameters. For example, the WTRU may determine, be (pre)configured, and / or receive the number of beam groups, for example indicated by N_BG. In an example, the WTRU may be configured with the total number of the beam resources. The WTRU may determine the number of beam groups based on the total number of beams and the size of beam groups.

[0134] For example, the WTRU may determine, be (pre)configured, and / or receive the size of beam groups, for example indicated by SIZE_BG. In an example, the size of the beam groups may indicate the number of beams included in each beam group. In an example, the size of the beam groups may be similar for all beam groups or indicated and / or configured separately for each beam group.

[0135] For example, the WTRU may determine, be (pre)configured, and / or receive the beam IDs corresponding to the beam resources that are included in each beam group. For instance, the WTRU may receive the beam IDs based on one or more of reference signals’ indexes, TCI states, etc. In an example, the WTRU may receive the beam IDs based on one or more of SSB indexes, CSI-RS indexes, and so forth. The WTRU may determine and / or receive the beam IDs based on implicit and / or explicit indications where one or more of the following may apply.

[0136] For example, explicit indication may be implemented. The WTRU may receive the absolute and / or exact value of the beam indexes for each of the beam resources that are included in a beam group. In an example, for a first beam group with a first S IZE_BG, the WTRU may receive up to SIZEJ3G indications and / or configuration information on the beam indexes of the beam resources that are included in the first beam group.

[0137] For example, implicit indication may be implemented. The WTRU may receive the starting beam ID, for example indicated by STARTJD. In an example, the starting beam ID may correspond to the beam resource with the lowest or the highest beam ID value in the beam group, where the other beam IDs in the beam group may be ordered in ascending or descending orders, respectively. In an example, upon reception of the STARTJD, the WTRU may determine the beam IDs corresponding to the other beam resources that are included in the beam group. For example, the WTRU may determine the beam ID of the other beam resources consecutively, starting from the configured and / or determined START-ID up to the configured and / or determined SIZE_BG corresponding to the beam group.

[0138] In some examples, determination of the accuracy may be implemented. In one embodiment, a WTRU may determine and / or be configured to perform one or more measurements based on one or more beam resources in a determined and / or configured time duration. For example, the WTRU may determine and / or be configured to measure one or more parameters based on one or more beam resources, where the beam resources may be from a configured and / or determined set B. In an example, the WTRU may measure RSRP, RSRQ, SINR, etc. In an example, the WTRU may receive the configurations via RRC, MAC-CE, and / or DCI, etc.

[0139] In one embodiment, the WTRU may calculate the accuracy based on one or more predicted beam resources, corresponding beam groups, and / or one or more measurements. For example, the WTRU may restart and / or initiate an accuracy parameter (AC_Param) for calculating the accuracy. In an example, the WTRU may determine the value of the AC_Param to be equal to zero. The WTRU may then increment the value of the AC_Param based on one or more determined and / or (pre)configured values. For example, the configured values may be a first value (e.g., 1), a second value (e.g., 0.5), and so forth.

[0140] In an example, the WTRU may determine that the predicted (e.g., best) beam belongs to a determined and / or configured set A. The WTRU may determine that the predicted (e.g., best) set A beambelongs to and / or is included in a first beam group. In an example, the WTRU may determine that the determined first beam group is the same as the beam group that includes the (e.g., best) measured set B beam, for example with the highest measured RSRP. In an example, the WTRU may determine that the prediction may be correct if the determined first beam group includes both the (e.g., best) predicted set A beam and the (e.g., best) measured set B beam. In an example, in case the WTRU determines that the prediction is correct, the WTRU may determine to increment the value of AC_Param by a (pre)configured value, for example, 1.

[0141] In another example, the WTRU may determine that the predicted (e.g., best) beam belongs to and / or is included in a first beam group, where the determined first beam group is a neighbor to a second beam group that includes the (e.g., best) measured set B beam, for example with the highest measured RSRP. In an example, in case the WTRU determines that the (e.g., best) predicted set A beam is in a beam group that is adjacent and / or neighbor to the (e.g., best) measured set B beam, the WTRU may determine to increment the value of AC_Param by a (pre)configured value, for example 0.5.

[0142] In an example, in case the WTRU determines that the predicted (e.g., best) beam is not included in the same or neighboring beam group as the (e.g., best) measured set B beam, the WTRU may determine the prediction to be incorrect. As such, the WTRU may determine to not increment the value of AC_Param, or just add a value of, for example zero, to the calculated AC_Param.

[0143] In an example, the WTRU may determine and / or be configured with neighbor beam groups based on spatial relations between the beam groups. In an example, the WTRU may receive the configuration on the neighbor beam groups, for example from a gNB (e.g., via RRC, MAC-CE, DCI, etc.). The WTRU may receive the indication on the neighbor beam groups based on one or more of the following. In some examples, for a first beam group, the WTRU may receive explicit indication of the beam groups that are adjacent and / or neighbor to the first beam group. In an example, the WTRU may receive the indexes corresponding to the neighbor and / or adjacent beam groups. In some examples, the WTRU may determine that one or more of the beam resources indicated and / or configured in a first beam group are also included in one or more second beam groups. As such, the WTRU may determine that the first beam group is neighbor and / or adjacent with the determined second beam groups (e.g., implicit indication)

[0144] In an example, the WTRU may perform one or more accuracy measurement occasions to determine the accuracy parameter, AC_Param, in a determined and / or configured time duration. In an example, the WTRU may determine or be configured with the number of times to perform corresponding measurements and / or the number of trials. In another example, the WTRU may be configured with periodicity, start time, time duration, etc. to perform the corresponding measurements. For example, at the end of the time window, the WTRU may divide the calculated AC_Param by the number of times that the measurements were accomplished.

[0145] In an example, a WTRU may perform 10 measurements, where 7 were correct and 3 were incorrect. As such, the WTRU may determine the accuracy to be 70% {e.g., 7 divided by 10 equals 70%).

[0146] In another example, a WTRU may perform 5 measurements, where the first is in the correct beam group, the second is in neighboring beam group, the third is incorrect beam group, the fourth is in correct beam group, and the fifth is incorrect. As such, in an example, the WTRU may determine the accuracy to be 50%, that is for example {1 (correct) plus 0.5 (neighboring) plus 0 (incorrect) plus 1 (correct) plus 0 (incorrect)} divided by 5 (number of trials) equals 2.5 divided by 5 equals 50%.

[0147] Methods to dynamically switch location of AI / ML operations may be implemented. In some examples, a WTRU may receive a configuration of one or more of the following. For example, a WTRU may receive a configuration of one or more RSs for measurement. For example, a set Bs, which may be a first set B associated to a gNB-side AI / ML model, and a second set B associated to a WTRU-side AI / ML model. For instance, RS resource sets where each RS resource set is associated to a set B. For example, a WTRU may receive a configuration of a priority configuration of AI / ML operation location, for example, offset for prediction quality of one of the AI / ML location {e.g., WTRU-side).

[0148] The WTRU may receive an AI / ML operation location flag indicating active location of AI / ML operation {e.g., gNB side by default). The WTRU may measure one or more RSs {e.g., RSs associated to the configured set B(s)) and may determine associated beam / RS measurement values {e.g., RSRP). The WTRU may use determined beam measurement values {e.g., by inputting the measurement values and / or associated beam IDs in the WTRU-sided model) of RSs associated to WTRU-side set B to obtain predicted beam IDs and / or predicted measurement values. The WTRU may determine a prediction quality {e.g., local prediction accuracy) of WTRU-sided model based on one or more of: the predicted beam ID and / or predicted measurement values as discussed in the local prediction accuracy section.

[0149] Based on the AI / ML operation location flag {e.g., if the flag indicates gNB-side active), the WTRU may determine and / or is indicated a prediction quality of gNB-side model in one or more of the following ways. In some examples, the WTRU may be indicated a prediction quality of gNB-side model by the gNB. For example, the WTRU may receive an indication indicating prediction quality of gNB-side model {e.g., gNB-side model prediction accuracy).

[0150] In some examples, the WTRU may determine and / or is indicated a prediction quality of gNB-side model by comparison between measurement values of a gNB-predicted best beam and other beams. For example, the WTRU determines the measurement value of the gNB-predicted best beam in one or more of the following ways. For instance, the WTRU may measure one or more RSs associated to an indicated TCI-state {e.g., determined from a scheduled PDSCH / PDCCH transmission). For instance, the WTRU may receive a separate indication of a gNB-predicted best beam {e.g., through TCI-state, or CRI or SSBRI {e.g., for calculating prediction accuracy)). For example, the WTRU may determine a local gNB-side predictionaccuracy based on the determined measurement value of the g N B-predicted best beam and measurement values of other beams (e.g., beams associated to configured and / or active set B). For example, the WTRU may compare a predicted measurement value (e.g., indicated to WTRU) and a measured measurement value. For instance, the WTRU may determine a prediction quality of gNB-side model (e.g., local prediction accuracy) based on the difference between measured and predicted measurement value of the gNB- predicted best beam.

[0151] The WTRU may determine a preferred location for AI / ML operation based on one or more of prediction quality of gNB-side model, prediction quality of WTRU-side model, an offset and / or a threshold. For example, the WTRU may determine a preferred location for AI / ML operation based on prediction quality of both gNB-side model and WTRU-side model. For instance, if the gNB-side model prediction quality is less than the WTRU-side model prediction quality plus offset (e.g., configured priority offset), the WTRU may determine WTRU-side model as preferred, and otherwise determines the gNB-side model as preferred. For instance, if the prediction quality of both WTRU-side model is less than a threshold, and gNB-side model is less than a threshold, the WTRU may select a default preferred location for AI / ML operation (e.g., the default location indicated to WTRU by the flag). For example, the WTRU may determine a preferred location for AI / ML operation based on prediction quality of WTRU-side only. For instance, if WTRU-side model prediction quality is less than a threshold, the WTRU may determine the gNB-side model as preferred, and otherwise determines WTRU-side model as preferred.

[0152] The WTRU may transmit an indication to the gNB, indicating one or more of the following based on the WTRU's determined preferred location of AI / ML operation. For example, the WTRU may transmit an indication to the gNB, indicating an indication (e.g., flag) of the WTRU’s preferred location of AI / ML operation. The WTRU may transmit an indication to the gNB, indicating one or more WTRU-sided model predicted best beam(s) (e.g., if the WTRU's preferred AI / ML operation location is WTRU-side). The WTRU may transmit an indication to the gNB, indicating beam qualities of one or more RSs associated to gNB- side set B (e.g., if the WTRU’s preferred AI / ML operation location is gNB-side). The WTRU may transmit an indication to the gNB, indicating WTRU-side model prediction quality (e.g., when WTRU-side model is active, or when gNB-side model is active and WTRU-side model prediction quality greater than a threshold). The WTRU may transmit an indication to the gNB, indicating gNB-side model prediction quality (e.g., when gNB-side model active).

[0153] Methods to determine prediction qualities based on measurement may be implemented. In various embodiments, an AI / ML operation location may interchangeably be used with AI / ML location, AI / ML node, AI / ML side, AI / ML equipment / device, and AI / ML entity but still consistent with the methods and / or apparatuses described herein. In various embodiments, a preferred AI / ML operation location may interchangeably be used with preferred (AI / ML) node, preferred (AI / ML) side, preferred (AI / ML)equipment / device, and preferred (Al / M L) entity but still consistent with the methods and / or apparatuses described herein.

[0154] In one embodiment, a WTRU may receive a configuration of one or more of the following (e.g., via RRC, MAC-CE and / or DCI). In some examples, a WTRU may receive a configuration of one or more set Bs. In an example, the WTRU may receive a configuration (e.g., set B size, set B type, set B side e.g., WTRU-side or gNB-side or both) of a first set B, which may be associated with both, a gNB-side Al / M L model and a WTRU-side Al / M L model. In another example, the WTRU may receive a configuration of a first set B associated with a gNB-side AI / ML model and a second set B associated with a WTRU-side Al / M L model.

[0155] In some examples, a WTRU may receive a configuration of one or more RS resource sets. In an example, the WTRU may receive a configuration of one or more RS resource sets wherein each RS resource belonging to an RS resource set may be associated with a set B. For example, the WTRU may receive a configuration of a first RS resource set wherein each RS resource belonging to the RS resource set may be associated to the first configured set B. For example, the WTRU may receive a configuration of a second RS resource set wherein each RS resource belonging to the RS resource set may be associated to the second configured set B. In some examples, a WTRU may receive a configuration of beam and / or RS quality difference threshold (e.g., a RSRP difference threshold).

[0156] In some examples, the WTRU may be indicated and / or determine a default AI / ML operation node (e.g., either gNB or WTRU). For example, the WTRU may receive a flag based indication (e.g., via RRC, MAC-CE and / or DCI) where a first flag value may indicate gNB-side as default AI / ML node, and a second flag value may indicate WTRU-side as default. In an example, the WTRU may determine a default AI / ML side based on the configuration of set Bs. For example, the WTRU may determine WTRU-side as default only if one set B is configured. For example, the WTRU may determine gNB-side as default if more than one set Bs are configured.

[0157] In some examples, the WTRU may measure one or more RSs associated to one or more configured set Bs. For example, the WTRU may measure one or more RSs associated to the set B associated to the WTRU-side AI / ML model. For example, the WTRU may measure one or more RSs associated to the set B associated to the gNB-side AI / ML model. Based on the measurements, the WTRU may determine associated beam and / or RS qualities (e.g., RSRP, SINR, L1-RSRP, CQI). The WTRU may use measured beam and / or RS quality values (e.g., by inputting the quality values and / or associated beam IDs in the WTRU-sided model) of RSs associated to WTRU-side set B to obtain one or more predicted beam IDs and / or RSRP values. The WTRU may determine a first (e.g., of WTRU-sided model) prediction quality (e.g., local prediction accuracy) based on the WTRU-sided predicted beam ID and measured beamqualities of one or more RSs (e.g., RSs associated to WTRU-side set B). Refer to local beam prediction accuracy KPIs for details above and herein for additional details.

[0158] In some examples, the WTRU may be indicated and / or determine a second (e.g., of a gNB-sided model) prediction quality in one or more of the following ways. In an example, the WTRU may be indicated and / or determine the second prediction quality when the default AI / ML operation location and / or node may be g N B-side. In an example, the WTRU may receive an indication of the second prediction quality (e.g., gNB-side local beam prediction accuracy, beam prediction accuracy, average RSRP difference).

[0159] Comparison between qualities of gNB-predicted beam and other beams may be implemented. In some examples, the WTRU may be indicated and / or determine the beam / RS quality of the best gNB- predicted beam in one or more of the following procedures. For example, the WTRU may receive an indication of a TCI-state (e.g., via DCI or MAC-CE) associated with a gNB-selected beam (e.g., gNB- predicted best beam). The WTRU may receive an indication indicating the status (e.g., whether the beam is the best gNB-predicted beam) of the beam associated with the indicated TCI-state. For example, the WTRU may receive a 1-bit indication (e.g., via RRC or MAC-CE / DCI) where a first value may indicate that the beam associated with the indicated TCI-state is the best gNB-predicted beam and the second value may indicate otherwise. For example, a first value (e.g., 0) of one of the TCI-state indication bits (e.g., first, second, or third bit) inside DCI may indicate that the beam associated with the indicated TCI-state is the best gNB-predicted beam and the second value (e.g., 1) may indicate otherwise. The WTRU may measure the beam RS associated with the indicated TCI-state. Based on the measurement, the WTRU may determine the RS / beam quality (e.g., RSRP, CQI, SINR, L1-RSRP) of the gNB-selected (e.g., best gNB- predicted) beam.

[0160] In some examples, the WTRU may measure a DL signal (e.g., PDSCH, PDCCH) associated with a gNB-selected beam. The WTRU may receive an indication indicating the status (e.g., whether the beam is the best gNB-predicted beam) of the beam associated with the measured DL signal. For example, the WTRU may receive a flag-based indication (e.g., via MAC-CE / DCI) where a first value may indicate that the beam associated with the measured DL signal is the best gNB-predicted beam and the second value may indicate otherwise. Based on the measurement, the WTRU may determine the beam quality (e.g., RSRP, CQI, SINR, L1-RSRP) of the gNB-selected (e.g., best gNB-predicted) beam.

[0161] In some examples, the WTRU may receive an indication of the best gNB-predicted beam. For example, the WTRU may be indicated the best gNB-predicted beam via TCI-state (e.g., additional TCI- state), CRI and / or SSBRI. The WTRU may measure the beam RS associated with the indicated TCI-state, CRI and / or SSBRI. Based on the measurement, the WTRU may determine the RS and / or beam quality (e.g., RSRP, CQI, SINR, L1-RSRP) of the best gNB-predicted beam.

[0162] In some examples, the WTRU may determine the second prediction quality (e.g., gNB-side prediction quality) based on the qualities of the gNB-predicted beam and / or other measured beams (e.g., beams / RSs associated with gNB-side set B) in one or more of the following ways. For example, the WTRU may determine the second prediction quality (e.g., local beam prediction accuracy of gNB-side) based on best gNB-predicted beam's measured quality being the highest and / or Nth-highest compared to the qualities of other beams. In an example, the WTRU may assign a first value for prediction quality (e.g., 1) if the measured quality of the best gNB-predicted beam is the highest. In another example, the WTRU may assign a second value for prediction quality (e.g., 0.5) if the measured quality of the best gNB-predicted beam is the second highest. In another example, the WTRU may assign a third value for prediction quality (e.g., 0.33) if the measured quality of the best gNB-predicted beam is the third highest. In another example, the WTRU may assign a fourth value for prediction quality (e.g., 0) if the measured quality of the best gNB-predicted beam is the fourth highest or lower.

[0163] In an example, the WTRU may determine the second prediction quality based on the difference between the best gNB-predicted beam's measured quality and the and another measured beam (e.g., beam with the highest quality other than the best gNB-predicted beam). In an example, the WTRU may assign a first value for prediction quality (e.g., 1) if the measured quality of the best gNB-predicted beam is the highest. In another example, the WTRU may assign a second value for prediction (e.g., 0.5) if the difference between the highest quality measured beam and the best gNB-predicted beam is less than the preconfigured threshold. In another example, the WTRU may assign a third value for prediction (e.g., 0) if the difference between the highest quality measured beam and the best gNB-predicted beam is greater than the preconfigured threshold.

[0164] In an example, the WTRU may receive an indication of the predicted beam and / or RS quality (e.g., predicted RSRP) of the best gNB-predicted beam (e.g., via RRC / MAC-CE / DCI). The WTRU may determine the second prediction quality based on the difference between the predicted quality and measured quality of the best gNB-predicted beam. In an example, the WTRU may assign a first value for prediction (e.g., 1) if the difference between predicted quality and measured quality of the best gNB- predicted beam is less than preconfigured threshold. In an example, the WTRU may assign a second value for prediction (e.g., 0) if the difference between the predicted quality and measured quality of the best gNB- predicted beam is greater than the preconfigured threshold.

[0165] In an example, the WTRU may determine the second prediction quality as the average (e.g., in percentage) of the sum of prediction qualities, determined in the last N (e.g., 10) determination instances, slots, frame, seconds and / or millisecond (msec).

[0166] A representative procedure for switching AI / ML operations locations based on prediction qualities may be implemented. A WTRU may determine a preferred location for AI / ML operation based on one ormore of beam prediction quality at gNB-side, beam prediction quality at WTRU-side, and / or mobility of the WTRU. Once a preferred location for AI / ML operation is determined, the WTRU may indicate its preferred location and assistance information to the gNB. The WTRU may use one or more of the following methods and procedures.

[0167] In some examples, the WTRU may receive configuration for determining preferred location for AI / ML operation. For example, the WTRU may receive one or more of the following configurations from one or more of RRC signaling, MAC-CE indication, and DCI indication. For instance, the WTRU may receive a priority offset. For example, the WTRU may receive an offset on prediction quality to be used when comparing gNB-side prediction quality and the WTRU-side prediction quality. The WTRU may receive a threshold on prediction quality. For example, the WTRU may receive a minimum prediction quality to be maintained by WTRU-side prediction or gNB-side prediction to use AI / ML based beam predictions for beam management. The WTRU may receive a threshold on mobility. For example, the WTRU may receive a threshold on mobility related measures such as speed (e.g., threshold on speed), change in the direction of movement (e.g., threshold on the rate of change of direction).

[0168] In some examples, the WTRU may determine a preferred location for AI / ML operation based on one or more of the following procedures. For example, the WTRU may determine the preferred location for AI / ML operation based on prediction quality of both gNB-side and WTRU-side. For instance, if the WTRU determines that gNB-side prediction quality is less than the WTRU-side prediction quality plus offset (e.g., configured priority offset), the WTRU may determine the WTRU-side as the preferred location for AI / ML operation. If the gNB-side prediction quality is greater than or equal to WTRU-side prediction quality plus offset (e.g., configured priority offset), the WTRU may determine the gNB-side as the preferred location for AI / ML operation. For example, the WTRU may consider local prediction accuracy of WTRU-side model and gNB-side models as the WTRU-side predication quality and gNB-side prediction quality, respectively. For instance, if the WTRU determines that prediction quality of WTRU-side is less than the preconfigured threshold on prediction quality and prediction quality of gNB-side is less than the preconfigured threshold on prediction quality, the WTRU may select a default preferred location for AI / ML operation (e.g., the default location indicated to WTRU by a flag).

[0169] In some examples, the WTRU may determine the preferred location for AI / ML operation only based on prediction quality of WTRU-side. For example, if the WTRU determines that WTRU-side model prediction quality is less than or equal to the preconfigured threshold on prediction quality, the WTRU may determine the gNB-side as the preferred location for AI / ML operation. If the WTRU determines that WTRU- side model prediction quality greater than the preconfigured threshold on prediction quality, the WTRU may determine the WTRU-side as the preferred location for AI / ML operation.

[0170] In some examples, the WTRU may determine the preferred location for AI / ML operation based on mobility and / or movement of the WTRU. For example, the WTRU may use the speed of the WTRU, rate of change of direction (e.g., number of times the WTRU changes its direction in a preconfigured time window, where the time window for determining rate of change of direction may be preconfigured via one or more of RRC signaling, MAC-CE indication, DCI indication).

[0171] For instance, if the WTRU determines that the speed of the WTRU is greater than the threshold on speed, the WTRU may determine WTRU-side as the preferred location for AI / ML operation. If the WTRU determines that the speed of the WTRU is less than or equal to the threshold on speed, the WTRU may determine gN B-side as the preferred location for AI / ML operation. For instance, if the WTRU determines that the rate of change of direction is greater than the threshold on rate of change of direction, the WTRU may determine WTRU-side as the preferred location for AI / ML operation. If the WTRU determines that the rate of change of direction is less than or equal to the threshold on rate of change of direction, the WTRU may determine g N B-side as the preferred location for AI / ML operation.

[0172] In some examples, the WTRU may report the determined preferred location for AI / ML operation and / or assistance information (e.g., additional measurements or predicted parameters) to the gNB (e.g., reported via a preconfigured PUSCH, PUCCH or MAC-CE indication). The WTRU report may include one or more of the following. For example, the WTRU report may include WTRU’s determined preferred location of AI / ML operation. For instance, the WTRU may report the preferred location of AI / ML operation as a flag where the WTRU may send a first flag value to indicate that the preferred location for AI / ML operation is the gNB-side. The WTRU may send a second flag value to indicate that the preferred location for AI / ML operation is the WTRU-side. For example, the WTRU report may include One or more WTRU- sided predicted beams (e.g., best beams). For instance, the WTRU may report beam IDs (e.g., CRI, SSBRI, CSI-RS resource ID) of one or more WTRU-sided predicted beams (e.g., best beams) if the WTRU’s determined preferred location for AI / ML operation is the WTRU-side. The WTRU report may include Beam qualities of one or more RSs associated to set B of the gNB-side AI / ML model. For instance, the WTRU may report beam qualities (e.g., L1-RSRP) and / or beam IDs (e.g., CRI, SSBRI) of one or more RSs associated to gNB-side set B when the WTRU’s determined preferred location for AI / ML operation is the gNB-side. The WTRU report may include WTRU-side prediction quality. For instance, the WTRU may report WTRU-side prediction quality when WTRU-side is active. For instance, the WTRU may report WTRU-side prediction quality when gNB-side is active and / or WTRU-side prediction quality is greater than the preconfigured threshold on prediction quality. The WTRU report may include gNB-side prediction quality. For instance, the WTRU may report the gNB-side prediction quality when gNB-side AI / ML model is active.

[0173] Methods determining and indicating location(s) for AI / ML operations based on gNB proxy may be implemented. In some examples, the WTRU may receive configuration information indicating one or more of the following. For example, the WTRU may receive configuration information indicating one or more RSs for measurement. For instance, one or more RSs for measurement may be set Bs (e.g., a first set B associated to a gNB-side AI / ML model, and a second set B associated to a WTRU-side AI / ML model). For instance, one or more RSs for measurement may be RS resource sets where each RS resource set is associated to a set B. For example, the WTRU may receive configuration information indicating one or more parameters for a proxy gNB AI / ML model (e.g., model ID, number of inputs, type of input, number of model layers, number of outputs and / or type of outputs).

[0174] In some examples, the WTRU may receive an AI / ML operation location flag indicating active location of AI / ML operation (e.g., gNB side by default). The WTRU may measure one or more RSs (e.g., RSs associated to the configured set B(s))and determines associated beam / RS measurement values (e.g., RSRP). The WTRU may use the determined beam measurement values (e.g., by inputting the measurement values and / or associated beam IDs in the WTRU-sided model) of RSs associated to WTRU- side set B to obtain predicted beam IDs and / or predicted measurement values. For instance, the WTRU may determine a prediction quality (e.g., local prediction accuracy) of WTRU-sided model based on one or more of: the predicted beam ID and predicted measurement values (i.e., see local prediction accuracy section).

[0175] In some examples, the WTRU may be indicated and / or may select (e.g., pre-configured, e.g., selects one of indicated) a proxy gNB-side model based on one or more of a gNB-side set B, model ID, number of inputs, type of input, number of layers, number of outputs and / or type of outputs.

[0176] In some examples, the WTRU may receive one or more of the following types of assistance information (e.g., to assist WTRU in making a correct estimate of prediction quality of gNB-side model). For example, The WTRU may receive a probability distribution function (e.g., a mean, variance and / or distribution shape indicator) and / or a Cumulative Distribution Function (e.g., function ID). The WTRU may receive offsets to predicted output of indicated or selected proxy gNB-side model (e.g., corresponding to different line of sight (LOS) probability and / or WTRU mobility).

[0177] In some examples, the WTRU may determine a prediction quality (e.g., an estimate of gNB-side prediction accuracy) of gNB-side model based on one or more of the following. For example, the WTRU may determine a prediction quality based on determined beam measurement values (e.g., by inputting the quality values and / or associated beam IDs in the indicated or selected proxy gNB-side model) of RSs associated to gNB-side set B. The WTRU may determine a prediction quality based on assistance information. For instance, the assistance information may include or generated by inputting the output ofproxy gNB-side model into CDF, and / or offsetting proxy gNB-side model output based on PDF parameters and / or LOS probability / mobility.

[0178] In some examples, the WTRU may determine a preferred location of AI / ML operation based on the determined prediction qualities of gNB-side model and WTRU-side model. For example, the WTRU determines WTRU-side model as preferred if gNB-side model prediction quality plus offset (e.g., preconfigured offset) is less than the WTRU-side model prediction quality, and / or otherwise determines gNB- side model as preferred.

[0179] In some examples, the WTRU may send an indication (e.g., periodic, or when location preference changes) indicating its preference for the model location via one or more of the following. For example, the WTRU may send an indication indicating its preference for the model location via explicit (e.g., flag based) indication, indicating WTRU preference after every determination instance. The WTRU may send an indication indicating its preference for the model location via explicit (e.g., flag based) indication, indicating WTRU preference after every N (e.g., preconfigured) number of determination instances. The WTRU may send an indication indicating its preference for the model location via indication of location preference score (e.g., after every M number of determination instances).

[0180] In some examples, based on the WTRU report, the WTRU may receive an updated flag indicating change in active location of AI / ML operation (e.g., from gNB-side to WTRU-side).

[0181] Methods to determine and estimate prediction qualities based on proxy models may be implemented. In some examples, an AI / ML operation location may interchangeably be used with AI / ML location, AI / ML node, AI / ML side, AI / ML equipment / device, and / or AI / ML entity, but still consistent with the methods and apparatuses described herein.

[0182] In some examples, a preferred AI / ML operation location may interchangeably be used with preferred (AI / ML) node, preferred (AI / ML) side, preferred (AI / ML) equipment / device, and preferred (AI / ML) entity, but still consistent with the methods and apparatuses described herein.

[0183] In some examples, a WTRU may receive a configuration of one or more of the following (e.g., via RRC, MAC-CE and / or DCI). For example, a WTRU may receive a configuration of one or more set Bs. For instance, the WTRU may receive a configuration (e.g., set B size, set B type, set B side, WTRU-side, gNB- side and / or both) of a first set B, which may be associated with both, a gNB-side AI / ML model and a WTRU-side AI / ML model. For instance, the WTRU may receive a configuration of a first set B associated with a gNB-side AI / ML model and a second set B associated with a WTRU-side AI / ML model. A WTRU may receive a configuration of one or more RS resource sets. For instance, the WTRU may receive a configuration of one or more RS resource sets wherein each RS resource belonging to an RS resource set may be associated with a set B. For instance, the WTRU may receive a configuration of a first RS resource set wherein each RS resource belonging to the RS resource set may be associated to the first configuredset B. For instance, the WTRU may receive a configuration of a second RS resource set wherein each RS resource belonging to the RS resource set may be associated to the second configured set B. the WTRU may receive a configuration of gNB-side AI / ML proxy model. For instance, a gNB-side AI / ML proxy model may refer to an AI / ML model (e.g., the model may exist at WTRU-side) simulating a gNB-side AI / ML model. Additionally and / or alternatively, a gNB-side AI / ML proxy model may refer to an AI / ML model (e.g., the model may exist at WTRU-side) that may predict and / or assist in predicting the performance (e.g., prediction accuracy KPIs) of a gNB-side AI / ML model. In some examples, a gNB-side AI / ML proxy model may interchangeably be used with gNB-proxy model and proxy model but still consistent with the methods and apparatuses described herein. In an example, a WTRU may receive a configuration of one or more of the following parameters associated to a gNB-proxy model. For instance, a WTRU may receive a model ID, number of inputs, number of outputs, and / or number of layers (e.g., neural network layers).

[0184] In some examples, the WTRU may be indicated and / or determine a default AI / ML operation node (i.e., either gNB or WTRU). For example, the WTRU may receive a flag-based indication (e.g., via RRC, MAC-CE and or DCI) where a first flag value may indicate gNB-side as default AI / ML node, and a second flag value may indicate WTRU-side as default. In an example, the WTRU may determine a default AI / ML side based on the configuration of set Bs. For example, the WTRU may determine WTRU-side as default if only one set B is configured. For example, the WTRU may determine gNB-side as default if more than one set Bs are configured.

[0185] In some examples, the WTRU may measure one or more RSs associated to one or more configured set Bs. For example, the WTRU may measure one or more RSs associated to the set B associated to the WTRU-side AI / ML model. For example, the WTRU may measure one or more RSs associated to the set B associated to the gNB-side AI / ML model. Based on the measurements, the WTRU may determine associated beam / RS qualities (e.g., RSRP, SINR, L1-RSRP, CQI). The WTRU may use measured beam / RS quality values (e.g., by inputting the quality values and / or associated beam IDs in the WTRU-sided model) of RSs associated to WTRU-side set B to obtain one or more predicted beam IDs and / or RSRP values. The WTRU may determine a first (e.g., of WTRU-sided model) prediction quality (e.g., local prediction accuracy) based on the WTRU-sided predicted beam ID and measured beam qualities of one or more RSs (e.g., RSs associated to WTRU-side set B). Refer to local beam prediction accuracy KPIs section and herein for details.

[0186] In some examples, the WTRU may select and / or receive / be transferred a gNB-proxy model using and / or based on one or more of the following. For example, the WTRU may select and / or receive / be transferred a gNB-proxy model using and / or based on model selection. The WTRU may select one of its pre-implemented / stored AI / ML model based on one or more of gNB-side set B, configured gNB-side model ID, number of inputs, type of input, number of neural network layers, number of outputs and / or type ofoutputs. For example, the WTRU may select and / or receive / be transferred a gNB-proxy model using and / or based on model transfer. The WTRU may be transferred (e.g., via PDSCH) one or more proxy AI / ML models from gNB. The WTRU may select a transferred model to use based on the gNB-side set B (i.e., model associated with gNB-side set B), configured model ID, and / or other configured model parameters (e.g., number of inputs, outputs, type of output).

[0187] In some examples, the WTRU may receive one or more of the following types of assistance information (e.g., via RRC / MAC-CE, DCI). For example, the WTRU may receive a cumulative distribution function (CDF). For instance, the WTRU may be indicated (e.g., an index for a pre-implemented CDF) and / or transferred a CDF (e.g., via PDSCH / PDCCH). For example, the WTRU may receive a probability distribution function (PDF). For instance, the WTRU may receive an indication of a PDF. For instance, the WTRU may receive an indication of a type of PDF (e.g., gaussian, skewed gaussian distribution) and / or associated parameters (e.g., mean, mode, median, variance, standard deviation and / or skewness of the indicated PDF). For example, the WTRU may receive one or more offsets. For instance, the WTRU may receive one or more prediction quality offsets associated with LOS probability. For instance, the WTRU may receive a first KPI offset associated with a first LOS probability and a second KPI offset associated with a second LOS probability (e.g., where the first offset is greater than the second offset and the first LOS probability is greater than the second LOS probability). For instance, the WTRU may receive one or more prediction quality offsets associated with WTRU mobility / speed. For instance, the WTRU may receive a first KPI offset associated with a first WTRU speed v and a second KPI offset associated with a second WTRU speed (e.g., where the first offset is greater than the second offset and the first WTRU speed is less than WTRU speed).

[0188] In some examples, the WTRU may determine a second (e.g., of gNB-side) prediction quality (e.g., estimate of prediction accuracy e.g., gNB-side local prediction accuracy) based on one or more of the following. For example, the WTRU may determine a second prediction quality based on measured and / or determined beam and / or RS qualities. For instance, the WTRU may predict and / or estimate a second prediction quality based on the measured beam and / or RS qualities of RSs associated with the gNB-side set B. For instance, the WTRU may input RS quality values to the gNB-proxy AI / ML model and determine the second prediction quality, intermediate prediction quality (e.g., sub-optimal estimate of gNB-side prediction accuracy) and / or an intermediate output (e.g., output other than prediction quality to be used as an input for a CDF). For example, the WTRU may determine a second prediction quality based on assistance information. For instance, the WTRU may adjust and / or offset and / or determine the second prediction quality based on the received assistance information in one or more of the following ways. In one embodiment, the WTRU may adjust and / or offset and / or determine the second prediction quality based on using CDF. For instance, the WTRU may determine the second prediction quality by inputting the output(e.g., intermediate output) of the gNB-proxy model to the indicated / transferred CDF. In one embodiment, the WTRU may adjust and / or offset and / or determine the second prediction quality based on using PDF. For instance, the WTRU may determine the second prediction quality based on the output of gNB-proxy model (e.g., intermediate prediction quality), the indicated PDF and associated PDF parameters. In an example, the WTRU may determine the second prediction quality by offsetting the intermediate prediction quality with one or more, or a combination of indicated PDF’s mean, mode, median, standard deviation, variance. In an example, the WTRU may determine the second prediction quality as the expectation (e.g., mean) of a conditional PDF (e.g., a conditional PDF created as: The indicated PDF given intermediate prediction quality). In one embodiment, the WTRU may adjust and / or offset and / or determine the second prediction quality based on using LOS probability / Mobility offsets. For instance, the WTRU may determine a LOS probability based on the measured RS(s). In one embodiment, the WTRU may determine the second prediction quality by offsetting the output (e.g., intermediate prediction quality) based on determined LOS probability. For example, the WTRU may offset the intermediate prediction quality with a first offset if the determined LOS probability is greater than the first threshold. For example, the WTRU may offset the intermediate prediction quality with a second offset (e.g., where second offset is less than the first offset) if the first threshold is greater than the determined LOS probability is greater than the second threshold (e.g., where second threshold is less than the first threshold). In one embodiment, the WTRU may estimate and / or predict its mobility and / or speed based on the measured RS(s). In one embodiment, the WTRU may determine the second prediction quality by offsetting the output (e.g., intermediate prediction quality) based on determined WTRU's mobility and / or speed. For example, the WTRU may offset the intermediate prediction quality with a first offset if the determined WTRU speed is greater than the first threshold. For example, the WTRU may offset the intermediate prediction quality with a second offset (e.g., where second offset is less than the first offset) if the determined WTRU speed is greater than the second threshold (e.g., where second threshold is greater than the first threshold).

[0189] Methods to determine and indicate AI / ML operations location based on prediction qualities may be implemented. In some examples, a WTRU may determine and / or select a preferred side, location, entity, and / or node for performing and / or applying one or more processing, prediction, estimation, evaluation, and / or calculation models. For example, the WTRU may select the preferred node based on a determined and / or configured first or second node. In an example, the first node may be associated with a gNB-sided model and the second node may be associated with a WTRU-sided model. In an example, an AI / ML model may be used for the processing, prediction, estimation, evaluation, and / or calculation model.

[0190] In some examples, the WTRU may determine and / or select the preferred node for performing the AI / ML model based on one or more measured, calculated, and / or determined quality parameters. In an example, a quality parameter may be based on prediction quality, for example for beam prediction, asdescribed herein and in KPI section. For example, the WTRU may use one or more quality parameters based on the node where the AI / ML model may be applied. In an example, the WTRU may use a first quality parameter based on g N B-sided prediction quality parameters. For example, the WTRU may use a second quality parameter based on WTRU-sided prediction quality parameters, etc.

[0191] In an example, the WTRU may determine and / or select the preferred node for performing the AI / ML model by comparing the first and the second quality parameters. For example, if the difference between the first and the second quality parameters is higher than a determined and / or configured threshold, the WTRU may select and / or determine the first node as the preferred node for AI / ML operation. Otherwise, if the difference between the first and the second quality parameters is lower than the threshold, the WTRU may select and / or determine the second node as the preferred node for AI / ML operation. For example, if the gNB-prediction quality in addition to a determined and / or (pre)configured offset value is lower than the WTRU-prediction quality, the WTRU may determine the WTRU-sided model as the preferred model. Otherwise, if the gNB-prediction quality in addition to the offset value is higher than the WTRU- prediction quality, the WTRU may determine the gNB-sided model as the preferred model. In an example, the WTRU may receive one or more threshold and / or offset values via RRC, MAC-CE, DOI, etc.

[0192] In some examples, a WTRU may be configured, determine, and / or receive indications, triggers, and / or configuration information to perform the procedure to determine the preferred node. For example, the WTRU may receive the configuration information from a gNB, for example via RRC, MAC-CE, DCI, etc In an example, the WTRU may determine and / or be configured with one or more of the following. For instance, the WTRU may determine and / or be configured with procedure duration. For example, the WTRU may determine and / or be configured with the time span to perform the procedure. That is, the WTRU may determine and / or be configured with the starting time, the time duration, and or the end time to perform the procedure. In an example, the WTRU may determine and / or be configured with the time duration based on the prediction instances. In an example, the WTRU may determine and / or be configured to perform the procedure per prediction instance. In another example, the WTRU may determine and / or be configured to perform the procedure for a configured and / or determined number prediction instances, for example N prediction instances. In another example, the WTRU may determine and / or be configured to perform the procedure every (e.g., N) prediction instances. In another example, the WTRU may determine and / or be configured to perform the procedure for a time duration based on determined and / or configured time instances, for example number of symbols, slots, frames, subframes, etc. In another example, the WTRU may determine and / or be configured to perform the procedure for a time duration based on time units, for example millisecond, microsecond, etc.

[0193] For instance, the WTRU may determine and / or be configured with periodicity. For example, the WTRU may determine and / or be configured to perform the procedure semi-persistently, periodically, oraperiodically. In an example, the WTRU may determine or be configured with the periodicity for performing the procedure based on prediction quality parameters. For instance, the WTRU may determine and / or be configured with the type of indication. For example, the WTRU may determine and / or be configured to indicate the selected preferred node based on one or more of the following. In one embodiment, the WTRU may determine and / or be configured to indicate the selected preferred node based on flag indication. For example, the WTRU may set a determined and / or configured flag indication each time the WTRU performs the procedure to determine the preferred node. For example, the WTRU may determine the time instances and / or occasions to perform the procedure based on the determined and / or configured time duration and / or periodicity Then, the WTRU may set the flag indication per each time instances and / or occasions that the WTRU performs the procedure. In an example, the WTRU may use a first value (e.g., zero) to indicate a first preferred node, where for example the first node may be gNB-sided model. In another example, the WTRU may use a second value (e.g., one) to indicate a second preferred node, where for example the second node may be WTRU-sided model. In one embodiment, the WTRU may determine and / or be configured to indicate the selected preferred node based on score indication. For example, the WTRU may initiate a counter and / or a score indicator and increment the counter and / or the score indicator by a first or a second value based on the selected preferred node, each time the WTRU performs the procedure. For example, the WTRU may determine the time instances and / or occasions to perform the procedure based on the determined and / or configured time duration and / or periodicity. Then, the WTRU may increment the counter and / or score indicator per each time instances and / or occasions that the WTRU performs the procedure. In an example, the WTRU may increment the counter and / or score indicator with a first value (e.g., zero) if a first preferred node is selected, where for example the first node may be gNB-sided model. In another example, the WTRU may increment the counter and / or score indicator with a second value (e.g., one) if a second preferred node is selected, where for example the second node may be WTRU-sided model. In an example, the WTRU may perform the counting and / or keeping the score for a determined and / or (pre)configured number of prediction instances, for example M instances. In another example, the WTRU may perform the counting and / or keeping the score until the counter and / or score reaches a determined and / or (pre)configured limit, maximum value, and / or threshold. For example, if the number of instances when WTRU-side model is determined as preferred is six, for example in the past ten prediction instances, frames, slots, milliseconds, etc., the WTRU may calculate a counter and / or a score of six.

[0194] In some examples, a WTRU may determine, receive, and / or be configured with one or more report configuration information, based on which the WTRU may transmit one or more requests, reports, and / or indications to indicate the determined and / or selected preferred node. For example, the report configuration information may include the time and frequency resources to send the report and corresponding indications. In an example, the WTRU may indicate the determined and / or selectedpreferred node for AI / ML operation, for example to a gNB. In an example, the WTRU may send the report and / or indications via UCI, MAC-CE, and / or RRC signaling. The indication and / or report may include one or more of the following. For instance, the indication and / or report may include selected and / or preferred node. For example, the WTRU may indicate the determined and / or selected preferred node. The WTRU may use one or more types of above-mentioned indications. One or more of the following may apply. In one embodiment, the WTRU may use flag-based indication. For example, the WTRU may report the determined flag indication after each determination occasion. In an example, the WTRU may report the determined flag indication after each prediction instance. In another example, the WTRU may report the determined flag after a determined and / or (pre)configured number of prediction instances. In one embodiment, the WTRU may use score-based indication. For example, the WTRU may report the determined score after a determined and / or (pre)configured number of prediction instances, for example M instances. In an example, the WTRU may report a first preferred node if the determined score is higher than a configured and / or determined threshold. In another example, the WTRU may report a second preferred node if the determined score is lower than the threshold. The WTRU may send a flag indication for indicating the determined preferred node based on the determined score value. For example, the WTRU may transmit a flag indication based on a first value (e.g., zero) to indicate WTRU-side as the preferred node if the preference score (e.g., 6 out of 10) for the WTRU-sided model is higher than the threshold (e.g., 4). Otherwise, the WTRU may transmit the flag indication based on a second value (e.g., one) to indicate gNB-side as the preferred node, if the preference score (e.g., 4 out of 10) for the gNB-sided model is lower than or equal to the threshold. In another example, the WTRU may report the actual value of the determined score value.

[0195] For instance, the indication and / or report may include time duration. For example, the WTRU may indicate the time span, during which the WTRU may apply the determined preferred node. In an example, the WTRU may indicate the starting time, the time duration, and or the end time. For example, the WTRU may indicate the time duration based on time instances, for example number of symbols, slots, frames, subframes, etc. In another example, the WTRU may indicate the time duration based on time units, for example milliseconds, microseconds, etc. In another example, the WTRU may indicate the time duration based on the number of prediction instances, for example N prediction instances. That is, the WTRU may indicate that the WTRU may apply the determined preferred node for the indicated number of configured and / or scheduled prediction instances, for example N prediction instances. For instance, the indication and / or report may include periodicity. For example, the WTRU may indicate if applying the determined preferred node may take place semi-persistently, periodically, or aperiodically. For example, the WTRU may determine the periodicity for applying the determined preferred node based on the detected, triggered, and / or determined conditions, for example based on determined score, as described herein.

[0196] In some examples, the WTRU may send the report and / or indication based on one or more events, conditions, and / or detected and / or received triggers. In an example, the WTRU may send the report and / or indications if the preferred node changes from a first node to a second node. In another example, the WTRU whose preferred node is gN B-side may determine and / or select the WTRU-sided as its preferred node. As such, the WTRU may send a report and / or indication to indicate the change, for example to a gNB. The WTRU may send the report based on one or more of the following. For instance, the WTRU may send the report based on UCI, MAC-CE, RRC (e.g., the WTRU may send the report and / or indication via UCI, MAC-CE, and / or RRC). The WTRU may send the report based on CSI report (e.g. , the WTRU may send the indication as part of a (pre)configured CSI report). The WTRU may send the report based on a scheduling request (SR). For example, the WTRU may send the indication as part of a (special) SR, for example via (pre)configured PUCCH resources. As such, the WTRU may transmit the determined preferred node and corresponding information as part of the transmitted SR. For instance, the WTRU may send the report based on hybrid automatic repeat request (HARQ) acknowledgement (ACK). In an example, the WTRU may transmit the indication as part of a HARQ-ACK transmission. In an example, the WTRU may transmit an enhanced HARQ-ACK codebook, where the codebook may include a flag indication to indicate the selected preferred node. In an example, the flag indication with a first value (e.g., zero) may indicate gNB-side and the flag indication with a second value (e.g., one) may indicate WTRU- sided.

[0197] In some examples, a WTRU may receive one or more indications and / or configuration information to enable, allow, and / or confirm or disable, not allow, and / or reject changes in the nodes for AI / ML operation. In an example, the WTRU that may be operating based on a first node for AI / ML operation (e.g., gN B-sided) may send a request to change the node for AI / ML operation to a second node (e.g., WTRU- sided), where the WTRU may receive an indication to confirm or reject the change. For example, the WTRU may receive indications from a gNB, for example via DCI, MAC-CE, RRC, etc. The indication may include one or more of the following. For instance, the indication may include a confirmation or rejection. For example, the received indication may confirm or reject the change in the node for AI / ML operation that was requested by WTRU In an example, a WTRU with a first node for AI / ML operation (e.g., gNB-sided) may receive a confirmation or rejection on whether the WTRU may change the node for AI / ML operation to a second node (e.g., WTRU-sided). In an example, the WTRU may receive a flag indication where a first value (e.g., one) may indicate confirmation of the change and a second value (e.g., zero) may indicate rejection of the change. In an example wherein the WTRU receives a confirmation, the WTRU may consider the changes to be applied after a determined and / or (pre)configured time window (e.g., Tappiication). In an example wherein the WTRU receives a rejection, the WTRU may use the first node for AI / ML operation. The WTRU may send a new request to change the node for AI / ML operation (if required) after adetermined and / or (pre)configured time window (e.g., Tdefer_request). In an example, the WTRU may determine that one or more of the quality parameters (e.g., beam prediction quality) based on the first node for AI / ML operation are not acceptable. The WTRU may determine to fallback to non-AI / ML operation. The WTRU may send an indication, for example to the gNB, to indicate the fallback.

[0198] For instance, the indication may include an active node for AI / ML operation. For example, the WTRU may receive indications that may indicate the node to be used as active node for AI / ML operation. The indication may be based on a flag indication, where a first value (e.g., value zero) may indicate a first node for AI / ML operation (e.g., gNB-sided) and a second value (e.g., value one) may indicate a second node for AI / ML operation (e.g., WTRU-sided).

[0199] For instance, the indication may include a time duration. For example, the WTRU may receive the starting time instance, time duration, and / or end time instance to apply the changes. In an example, a WTRU with a first node for AI / ML operation (e.g., gNB-sided) may receive an indication to change the node for AI / ML operation to a second node (e.g., WTRU-sided) starting from the indicated time instance, for the indicated time duration, and / or until the end time instance. In an example, the time instance may be based on the number of prediction occasions, time instances (e.g., symbol, slot, subframe, etc.), and / or time units (e.g., millisecond, microsecond, etc.). In an example, the WTRU may determine and / or be (pre)configured to switch back to the first node for AI / ML operation after the time duration has elapsed, or after the end time instance.

[0200] For instance, the indication may include a time offset until the changes apply (e.g., Tappiication). For example, the WTRU may receive a time window and / or offset after which the changes in the active node for AI / ML operation may be applied. As such, the WTRU may consider the changes to be applied after the indicated time offset. In an example, the time offset may be based on the number of prediction occasions, time instances (e.g., symbol, slot, subframe, etc.), and / or time units (e.g., milliseconds, microseconds, etc.).

[0201] For instance, the indication may include a time window before another change could be requested (e.g., Tdeferj-equest). For example, the WTRU may receive a time window before which the WTRU cannot send another request to change the node for AI / ML operation. In an example, the WTRU may determine that changes to the node for AI / ML operation may be required before the indicated time window has elapsed, for example due to non-acceptable prediction quality parameters. As such, the WTRU determine to fallback to non-AI / ML operation until the time limit to send a new request has elapsed.

[0202] For instance, the indication may include a fallback to non-AI / ML operation. For example, the WTRU may receive an indication to stop operating based on AI / ML operation and to fallback to non-AI / ML operation. This may be due to gNB realizing that change of the node for AI / ML operation may not be possible or that change may not be beneficial, based on reports received from the WTRU.

[0203] Although features and elements are provided above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. The present disclosure is not to be limited in terms of the particular embodiments described in this application, which are intended as illustrations of various aspects. Many modifications and variations may be made without departing from its spirit and scope, as will be apparent to those skilled in the art. No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly provided as such. Functionally equivalent methods and apparatuses within the scope of the disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing descriptions. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is to be understood that this disclosure is not limited to particular methods or systems.

[0204] The foregoing embodiments are discussed, for simplicity, with regard to the terminology and structure of infrared capable devices, i.e., infrared emitters and receivers. However, the embodiments discussed are not limited to these systems but may be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves such as acoustic waves.

[0205] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting. As used herein, the term "video" or the term "imagery" may mean any of a snapshot, single image and / or multiple images displayed over a time basis. As another example, when referred to herein, the terms "user equipment" and its abbreviation "UE", the term "remote" and / or the terms "head mounted display" or its abbreviation "HMD" may mean or include (I) a wireless transmit and / or receive unit (WTRU); (ii) any of a number of embodiments of a WTRU; (iii) a wireless-capable and / or wired-capable (e.g., tetherable) device configured with, inter alia, some or all structures and functionality of a WTRU; (iii) a wireless-capable and / or wired-capable device configured with less than all structures and functionality of a WTRU; or (iv) the like. Details of an example WTRU, which may be representative of any WTRU recited herein, are provided herein with respect to FIGs. 1 A-1 D. As another example, various disclosed embodiments herein supra and infra are described as utilizing a head mounted display. Those skilled in the art will recognize that a device other than the head mounted display may be utilized and some or all of the disclosure and various disclosed embodiments can be modified accordingly without undue experimentation. Examples of such other device may include a drone or other device configured to stream information for providing the adapted reality experience.

[0206] In addition, the methods provided herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wirelessconnections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0207] Variations of the method, apparatus and system provided above are possible without departing from the scope of the invention. In view of the wide variety of embodiments that can be applied, it should be understood that the illustrated embodiments are examples only, and should not be taken as limiting the scope of the following claims. For instance, the embodiments provided herein include handheld devices, which may include or be utilized with any appropriate voltage source, such as a battery and the like, providing any appropriate voltage.

[0208] Moreover, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices that include processors are noted. These devices may include at least one Central Processing Unit ("CPU") and memory. In accordance with the practices of persons skilled in the art of computer programming, reference to acts and symbolic representations of operations or instructions may be performed by the various CPUs and memories. Such acts and operations or instructions may be referred to as being "executed," "computer executed" or "CPU executed."

[0209] One of ordinary skill in the art will appreciate that the acts and symbolically represented operations or instructions include the manipulation of electrical signals by the CPU. An electrical system represents data bits that can cause a resulting transformation or reduction of the electrical signals and the maintenance of data bits at memory locations in a memory system to thereby reconfigure or otherwise alter the CPU's operation, as well as other processing of signals. The memory locations where data bits are maintained are physical locations that have particular electrical, magnetic, optical, or organic properties corresponding to or representative of the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs and that other platforms and CPUs may support the provided methods.

[0210] The data bits may also be maintained on a computer readable medium including magnetic disks, optical disks, and any other volatile (e.g., Random Access Memory (RAM)) or non-volatile (e.g., Read-Only Memory (ROM)) mass storage system readable by the CPU. The computer readable medium may include cooperating or interconnected computer readable medium, which exist exclusively on the processing system or are distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above- mentioned memories and that other platforms and memories may support the provided methods.

[0211] In an illustrative embodiment, any of the operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer- readable instructions may be executed by a processor of a mobile unit, a network element, and / or any other computing device.

[0212] There is little distinction left between hardware and software implementations of aspects of systems. The use of hardware or software is generally (but not always, in that in certain contexts the choice between hardware and software may become significant) a design choice representing cost versus efficiency tradeoffs. There may be various vehicles by which processes and / or systems and / or other technologies described herein may be affected (e.g., hardware, software, and / or firmware), and the preferred vehicle may vary with the context in which the processes and / or systems and / or other technologies are deployed. For example, if an implementer determines that speed and accuracy are paramount, the implementer may opt for a mainly hardware and / or firmware vehicle. If flexibility is paramount, the implementer may opt for a mainly software implementation. Alternatively, the implementer may opt for some combination of hardware, software, and / or firmware.

[0213] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of block diagrams, flowcharts, and / or examples. Insofar as such block diagrams, flowcharts, and / or examples include one or more functions and / or operations, it will be understood by those within the art that each function and / or operation within such block diagrams, flowcharts, or examples may be implemented, individually and / or collectively, by a wide range of hardware, software, firmware, or virtually any combination thereof. In an embodiment, several portions of the subject matter described herein may be implemented via Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), digital signal processors (DSPs), and / or other integrated formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein, in whole or in part, may be equivalently implemented in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and / or writing the code for the software and or firmware would be well within the skill of one of skill in the art in light of this disclosure. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein may be distributed as a program product in a variety of forms, and that an illustrative embodiment of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually carry out the distribution. Examples of a signal bearing medium include, but are not limited to, the following: a recordable type medium such as a floppy disk, a hard disk drive, a CD, a DVD, a digital tape, a computer memory, etc., and a transmission type medium such as adigital and / or an analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).

[0214] Those skilled in the art will recognize that it is common within the art to describe devices and / or processes in the fashion set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least a portion of the devices and / or processes described herein may be integrated into a data processing system via a reasonable amount of experimentation. Those having skill in the art will recognize that a typical data processing system may generally include one or more of a system unit housing, a video display device, a memory such as volatile and non-volatile memory, processors such as microprocessors and digital signal processors, computational entities such as operating systems, drivers, graphical user interfaces, and applications programs, one or more interaction devices, such as a touch pad or screen, and / or control systems including feedback loops and control motors (e.g., feedback for sensing position and / or velocity, control motors for moving and / or adjusting components and / or quantities). A typical data processing system may be implemented utilizing any suitable commercially available components, such as those typically found in data computing / communication and / or network computing / communication systems.

[0215] The herein described subject matter sometimes illustrates different components included within, or connected with, different other components. It is to be understood that such depicted architectures are merely examples, and that in fact many other architectures may be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively "associated" such that the desired functionality may be achieved. Hence, any two components herein combined to achieve a particular functionality may be seen as "associated with" each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated may also be viewed as being "operably connected", or "operably coupled", to each other to achieve the desired functionality, and any two components capable of being so associated may also be viewed as being "operably couplable" to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and / or physically interacting components and / or wirelessly interactable and / or wirelessly interacting components and / or logically interacting and / or logically interactable components.

[0216] With respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.

[0217] It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as "open" terms (e.g.,the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as “having at least," the term "includes" should be interpreted as "includes but is not limited to," etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, where only one item is intended, the term “single" or similar language may be used. As an aid to understanding, the following appended claims and / or the descriptions herein may include usage of the introductory phrases "at least one" and “one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim including such introduced claim recitation to embodiments including only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an" (e.g., "a" and / or “an" should be interpreted to mean "at least one" or "one or more"). The same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number [e.g., the bare recitation of "two recitations," without other modifiers, means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). In those instances where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase “A or B" will be understood to include the possibilities of "A" or "B" or “A and B." Further, the terms “any of" followed by a listing of a plurality of items and / or a plurality of categories of items, as used herein, are intended to include "any of," "any combination of," "any multiple of," and / or "any combination of multiples of" the items and / or the categories of items, individually or in conjunction with other items and / or other categories of items. Moreover, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, theterm "number" is intended to include any number, including zero. And the term "multiple", as used herein, is intended to be synonymous with "a plurality".

[0218] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0219] As will be understood by one skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily recognized as sufficiently describing and enabling the same range being broken down into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed herein may be readily broken down into a lower third, middle third and upper third, etc. As will also be understood by one skilled in the art all language such as "up to," "at least," "greater than,” "less than," and the like includes the number recited and refers to ranges which can be subsequently broken down into subranges as discussed above. Finally, as will be understood by one skilled in the art, a range includes each individual member. Thus, for example, a group having 1-3 cells refers to groups having 1, 2, or 3 cells. Similarly, a group having 1-5 cells refers to groups having 1 , 2, 3, 4, or 5 cells, and so forth.

[0220] Moreover, the claims should not be read as limited to the provided order or elements unless stated to that effect. In addition, use of the terms "means for" in any claim is intended to invoke 35 U S C §112, U 6 or means-plus-function claim format, and any claim without the terms "means for" is not so intended.

Claims

CLAIMS:1 . A wireless transmit / receive unit (WTRU), comprising: a processor configured to: receive, from a network device, configuration information indicating one or more reference signals (RSs) for measurement and a priority configuration of an artificial intelligence (Al) / machine learning (ML) (AI / ML) operation location at which an AI / ML operation is to be performed, wherein the AI / ML operation location is at the WTRU or at the network device; determine a WTRU prediction quality based on measurement values associated with the one or more RSs, wherein the WTRU prediction quality indicates a prediction quality associated with beam selection using the AI / ML operation location at the WTRU; determine a network prediction quality, wherein the network prediction quality indicates a prediction quality associated with the beam selection using the AI / ML operation location at the network device; determine a preferred AI / ML location based on the WTRU prediction quality, the network prediction quality, and the priority configuration, wherein the preferred AI / ML location is at the WTRU or at the network device; and send an indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation.

2. The WTRU of claim 1 , wherein the priority configuration of the AI / ML operation location comprises an offset.

3. The WTRU of claim 1 , wherein the processor is further configured to: determine predicted beam IDs or predicted measurement values based on measurement values associated with the one or more RSs; and determine the WTRU prediction quality based on the predicted beam IDs or predicted measurement values.

4. The WTRU of claim 1 , wherein the processor is further configured to: receive an indication of the network prediction quality from the network device; and determine the network prediction quality based on the indication of the network prediction quality received from the network device.

5. The WTRU of claim 1 , wherein the processor is further configured to:determine a measurement value of a network device-predicted best beam, wherein the measurement value of the network device-predicted best beam is determined by the WTRU measuring one or more RSs associated with an indicated transmission configuration indicator (TCI) state; determine a network prediction accuracy based on the determined measurement value of the network device-predicted best beam; compare a predicted measurement value indicated by the WTRU and the determined measurement value of the network device-predicted best beam; and determine the network prediction quality based on the difference between the predicted measurement value and the determined measurement value of the network device-predicted best beam.

6. The WTRU of claim 1 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises the network prediction quality.

7. The WTRU of claim 1 , wherein the processor is further configured to: determine the preferred AI / ML location to be at the WTRU based on the WTRU prediction quality being less than a combination of the network prediction quality and an offset indicated by the priority configuration.

8. The WTRU of claim 1 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises a flag indicating that the WTRU's preferred location of AI / ML operation is at the WTRU or at the network device.

9. The WTRU of claim 1 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises an indication of one or more WTRU predicted beams.

10. The WTRU of claim 1 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises an indication of the WTRU prediction quality.11 . A method implemented by a wireless transmit / receive unit (WTRU), the method comprising: receiving, from a network device, configuration information indicating one or more reference signals (RSs) for measurement and a priority configuration of an artificial intelligence (Al) I machinelearning (ML) (AI / ML) operation location at which an AI / ML operation is to be performed, wherein the AI / ML operation location is at the WTRU or at the network device; determining a WTRU prediction quality based on measurement values associated with the one or more RSs, wherein the WTRU prediction quality indicates a prediction quality associated with beam selection using the AI / ML operation location at the WTRU; determining a network prediction quality, wherein the network prediction quality indicates a prediction quality associated with the beam selection using the AI / ML operation location at the network device; determining a preferred AI / ML location based on the WTRU prediction quality, the network prediction quality, and the priority configuration, wherein the preferred AI / ML location is at the WTRU or at the network device; and sending an indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation.

12. The method of claim 11 , wherein the priority configuration of the AI / ML operation location comprises an offset.

13. The method of claim 11 , further comprising: determining predicted beam IDs or predicted measurement values based on measurement values associated with the one or more RSs; and determining the WTRU prediction quality based on the predicted beam IDs or predicted measurement values.

14. The method of claim 11 , further comprising: receiving an indication of the network prediction quality from the network device; and determining the network prediction quality based on the indication of the network prediction quality received from the network device.

15. The method of claim 11 , further comprising: determining a measurement value of a network device-predicted best beam, wherein the measurement value of the network device-predicted best beam is determined by the WTRU measuring one or more RSs associated with an indicated transmission configuration indicator (TCI) state; determining a network prediction accuracy based on the determined measurement value of the network device-predicted best beam;comparing a predicted measurement value indicated by the WTRU and the determined measurement value of the network device-predicted best beam; and determining the network prediction quality based on the difference between the predicted measurement value and the determined measurement value of the network device-predicted best beam.

16. The method of claim 11 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises the network prediction quality.

17. The method of claim 11 , further comprising: determining the preferred AI / ML location to be at the WTRU based on the WTRU prediction quality being less than a combination of the network prediction quality and an offset indicated by the priority configuration.

18. The method of claim 11 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises a flag indicating that the WTRU's preferred location of AI / ML operation is at the WTRU or at the network device.

19. The method of claim 11 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises an indication of one or more WTRU predicted beams.

20. The method of claim 11 , wherein the indication of the preferred AI / ML location to the network device for performing the beam selection using the AI / ML operation comprises an indication of the WTRU prediction quality.

Images