Verification of artificial intelligence (AI) / machine learning (ML) in beam management and hierarchical beam prediction

Abstract

A wireless transmit / receive unit (WTRU) may perform measurements on a first set of beam resources. The WTRU may then predict a beam resource in a second set of beam resources based on the measurement of the first set of beam resources. In addition, the WTRU may report the predicted beam resources. In addition, the WTRU may receive one or more first signals using the first beam. In one example, the first beam may use beam resources in the second set of beam resources. In addition, the WTRU may perform measurements on one or more accuracy parameters of the received one or more first signals. Further, the WTRU may transmit one or more second signals using the first beam under conditions that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 395,587, filed on August 5, 2022, the contents of which are incorporated herein by reference. Background Art

[0003] Beam management is a targeted use case for artificial intelligence (AI) / machine learning (ML) for air interfaces in wireless communications. This technology provides a solid foundation for improving the performance and complexity of conventional beam management, including beam prediction in the time and / or spatial domain to reduce overhead and latency, and improve beam selection accuracy.

[0004] In wireless communications, conventional beam selection is based on beam sweeping at the gNode B (gNB) side or base station side and the wireless transmit / receive unit (WTRU) side or handset side. In frequency range 2 (FR2), conventional beam management may result in beam sweeping and measurements of a large number of antennas at the gNB side and the WTRU side. When selecting the best beam, the WTRU may report up to four beams during the beam management process. In one example, the WTRU may report beams based on reference signal received power (RSRP).

[0005] Using AI / ML models, FR2 beam selection / prediction can be performed based on frequency range 1 (FR1) channel state information (CSI) measurements. However, in scenarios with hierarchical spatial relationships and associations between beam resources in different frequency ranges, the implementation of such a framework is subject to addressing key challenges in the measurement and reporting of beams and the training and verification of AI / ML models. In addition, the use of AI / ML model-based beam prediction may not always be beneficial. As an example, in the case of non-line of sight (NLOS) communications, AI / ML-based beam prediction may be inaccurate and traditional beam management processes will be beneficial. Summary of the invention

[0006] A wireless transmit / receive unit (WTRU) may determine one or more beam resources based on measurements of other beam resources. The measured beam resources may be frequency range 1 (FR1) beam resources, and the determined beam resources may be frequency range 2 (FR2) beam resources. The determination may be based on an artificial intelligence (AI) / machine learning (ML) model. The WTRU may receive a signal using one or more determined FR2 beam resources. In addition, the WTRU may perform a calibration procedure based on one or more accuracy parameters.

[0007] In one example, the WTRU may perform measurements on a first set of beam resources. The WTRU may then predict beam resources in a second set of beam resources based on the measurements of the first set of beam resources. In addition, the WTRU may report the predicted beam resources. In addition, the WTRU may receive one or more first signals using the first beam. In one example, the first beam may use beam resources in the second set of beam resources. In addition, the WTRU may perform measurements on one or more accuracy parameters of the received one or more first signals. In addition, the WTRU may send one or more second signals using the first beam, provided that the measured one or more accuracy parameters of the received one or more first signals are acceptable. In one example, these accuracy parameters may be acceptable when the measured LOS is above a LOS threshold and the CQI is above a CQI threshold.

[0008] In another example, the WTRU may receive one or more third signals using the first beam under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

[0009] In one example, the one or more first signals received may be a physical downlink control channel (PDCCH) signal. In another example, the one or more first signals received may be a channel state information-reference signal (CSI-RS).

[0010] Furthermore, in one example, using the first beam may include activating the first beam. In another example, using the first beam may include continuing to use the first beam.

[0011] In another example, the one or more accuracy parameters may include one or more of a line of sight (LOS) parameter, a channel parameter, or a channel quality indicator (CQI) parameter. In an additional example, the WTRU may also activate the AI / ML model to predict the one or more second beams. In an example, the one or more second beams may use beam resources from the second set of beam resources. In an additional or alternative example, the WTRU may continue to use the AI / ML model to predict the one or more second beams.

[0012] In an additional example, under the condition that one or more accuracy parameters measured of the received one or more first signals are unacceptable, the WTRU may send a request to select and report a third beam. In one example, the measured LOS may be below a LOS threshold and the measured CQI may be below a CQI threshold.

[0013] As another example, the WTRU may send a request under the condition that one or more accuracy parameters measured for the received one or more first signals are unacceptable. In one example, the measured LOS may be above a LOS threshold and the measured CQI may be below a CQI threshold. The request sent may include a request to update the AI / ML model. The request sent may include a request to retrain the AI / ML model. In addition, the request sent may include a request to use the AI / ML model to predict and report a fourth beam.

[0014] In addition, under the condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, the WTRU may fall back to the non-AI / ML beam management process to select and report the fifth beam. In one example, the measured CQI may be below the CQI threshold and a plurality of time instances may have passed since the first signal was received using the first beam.

[0015] In another example, the WTRU may receive the one or more fourth signals using the one or more sixth beams and may measure the one or more accuracy parameters of the received one or more fourth signals under the condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable. In one example, the measured LOS may be below a LOS threshold, the measured CQI may be below a CQI threshold, and a number of time instances may not have elapsed since the first signal was received using the first beam. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] A more detailed understanding may be obtained from the following description given by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate like elements, and in which:

[0017] Figure 1A is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented;

[0018] Figure 1B is an example of an embodiment in which Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within an illustrated communication system;

[0019] Figure 1C is an example of an embodiment in which Figure 1A A system diagram of an example Radio Access Network (RAN) and an example Core Network (CN) used within the illustrated communication system;

[0020] Figure 1D is an example of an embodiment in which Figure 1AA system diagram of another example RAN and another example CN used within the illustrated communication system;

[0021] Figure 2 is a system diagram illustrating an example of performing beam prediction in a second set of beam resources based on beam resource reports in a first set of beam resources;

[0022] Figure 3 is a flow chart illustrating an example of a verification process for beam prediction based on hierarchical spatial relationships; and

[0023] Figure 4 is a flow chart illustrating an example of predicted beam management. DETAILED DESCRIPTION

[0024] Figure 1A 1 is a diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, broadcast, etc. to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content through sharing of system resources (including wireless bandwidth). For example, the communication system 100 may employ one or more channel access methods such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single carrier FDMA (SC-FDMA), zero tail unique word discrete Fourier transform spread OFDM (ZT-UW-DFT-S-OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, and filter bank multi-carrier (FBMC), etc.

[0025] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104, a core network (CN) 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, but it should be understood 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 one of which may be referred to as a station (STA)) may be configured to transmit and / or receive wireless signals and may include user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, a personal digital assistant (PDA), a smart phone, a laptop computer, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, a medical device and application (e.g., remote surgery), an industrial device and application (e.g., a robot and / or other wireless devices operating in an industrial and / or automated processing chain environment), a consumer electronic device, and a device operating on a commercial and / or industrial wireless network, etc. Any one of the WTRUs 102a, 102b, 102c, and 102d may be interchangeably referred to as a UE.

[0026] The communication system 100 may further include base stations 114a and / or base stations 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks such as the CN 106, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be transceiver base stations (BTSs), Node Bs, evolved Node Bs (eNBs), home Node Bs, home evolved Node Bs, next-generation Node Bs (such as gNode Bs (gNBs)), new radio (NR) Node Bs, site controllers, access points (APs), and wireless routers, etc. Although the base stations 114a, 114b are each depicted as a single element, it should be understood that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0027] The base station 114a may be part of the RAN 104, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), and a relay node. The base station 114a and / or the base station 114b may be configured to send 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 a licensed spectrum, an unlicensed spectrum, or a combination of an unlicensed spectrum and an unlicensed spectrum. A cell may provide coverage of wireless services to a specific geographic area, which may be relatively fixed or may change over time. The cell may be further divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Therefore, in one embodiment, the base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In one embodiment, the base station 114a may employ multiple-input multiple-output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming can be used to send and / or receive signals in a desired spatial direction.

[0028] 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).

[0029] More specifically, as noted above, the communication system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, and SC-FDMA, among others. For example, the base station 114a in the RAN 104 and the WTRUs 102a, 102b, 102c may implement a radio technology, such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), that may use Wideband CDMA (WCDMA) to establish the air interface 116. WCDMA may include communication protocols, such as High Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High Speed ​​Uplink (UL) Packet Access (HSUPA).

[0030] 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) that may establish the air interface 116 using Long Term Evolution (LTE) and / or Advanced LTE (LTE-A) and / or Advanced LTE Pro (LTE-A Pro).

[0031] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology (such as NR radio access) that may establish the air interface 116 using NR.

[0032] In one 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 together implement LTE radio access and NR radio access, for example using the dual connectivity (DC) principle. Thus, the air interface utilized by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions transmitted to / from multiple types of base stations (e.g., eNBs and gNBs).

[0033] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi)), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), and GSM EDGE (GERAN).

[0034] Figure 1AThe base station 114b in may be, for example, a wireless router, a Home NodeB, a Home eNodeB, or an access point, and may utilize any suitable RAT to facilitate wireless connectivity in local areas such as commercial venues, homes, vehicles, campuses, industrial facilities, sky corridors (e.g., for use by drones), and roads. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology (such as IEEE 802.11) to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology (such as IEEE 802.15) to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish a picocell or a femtocell. As Figure 1A As shown, the base station 114 b may have a direct connection to the Internet 110. Therefore, the base station 114 b may not need to access the Internet 110 via the CN 106.

[0035] The RAN 104 may be in communication with the CN 106, which may be any type of network configured to provide voice, data, applications, and / or Voice over Internet Protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 may provide call control, billing services, mobile location-based services, prepaid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not described in detail in the specification, the CN 106 may be 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. Figure 1A Although not shown in the figure, it will be appreciated that the RAN 104 and / or the CN 106 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 or a different RAT. For example, in addition to being connected to the RAN 104, which may utilize NR radio technology, the CN 106 may also be in communication with another RAN (not shown) that employs GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0036] The CN 106 may also act 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 a circuit-switched telephone network that provides 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), the User Datagram Protocol (UDP), and / or the Internet Protocol (IP) in the TCP / IP Internet protocol suite. The networks 112 may include wired communication networks and / or wireless communication networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 or a different RAT.

[0037] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communication 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 via different wireless links). Figure 1A The illustrated WTRU 102c 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.

[0038] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B As shown, the WTRU 102 may include, among other things, a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0039] 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 associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), any other type of integrated circuit (IC), state machine, etc. The processor 118 may perform signal decoding, 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. Although Figure 1B The processor 118 and the transceiver 120 are depicted as separate components, but it is understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0040] The send / receive element 122 may be configured to send a signal to a base station (e.g., base station 114a) or receive a signal from a base station via an air interface 116. For example, in one embodiment, the send / receive element 122 may be an antenna configured to send and / or receive an RF signal. In an embodiment, the send / receive element 122 may be a transmitter / detector configured to send and / or receive, for example, an IR, UV, or visible light signal. In another embodiment, the send / receive element 122 may be configured to send and / or receive both an RF signal and an optical signal. It should be understood that the send / receive element 122 may be configured to send and / or receive any combination of wireless signals.

[0041] Although the transmit / receive element 122 Figure 1B Although depicted as a single element in the figure, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0042] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and to demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. For example, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11.

[0043] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an 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 a non-removable memory 130 and / or a removable memory 132. The non-removable memory 130 may include a random access memory (RAM), a 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, and a secure digital (SD) memory card, among others. In other embodiments, the processor 118 may access information from and store data in a memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0044] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control 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, etc.

[0045] 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 from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by any suitable location-determination method while remaining consistent with an embodiment.

[0046] The processor 118 may also be coupled to other peripherals 138, which may include one or more software modules and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, Modules, frequency modulation (FM) radio units, digital music players, media players, video game player modules, Internet browsers, virtual reality and / or augmented reality (VR / AR) devices and activity trackers, etc. The peripheral device 138 may include one or more sensors. The sensor may be one or more of the following: a gyroscope, an accelerometer, a Hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geographic location sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and a humidity sensor, etc.

[0047] 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 specific subframes for both UL (e.g., for transmission) and DL (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit for reducing and / or substantially eliminating self-interference via signal processing performed by hardware (e.g., a choke) or via a processor (e.g., a separate processor (not shown) or via the 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 specific subframes for both UL (e.g., for transmission) or DL ​​(e.g., for reception)) may be concurrent and / or simultaneous.

[0048] Figure 1C 1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0049] The RAN 104 may include evolved Node-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of evolved Node-Bs while remaining consistent with an embodiment. The evolved Node-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the evolved Node-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the evolved Node-B 160a, for example, may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0050] Each of the evolved Node Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, and scheduling of users in the UL and / or DL, among other things. Figure 1C As shown, the eNode-Bs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0051] Figure 1C The illustrated CN 106 may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. Although the foregoing elements are depicted as part of the CN 106, it should be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0052] The MME 162 may be connected to each of the evolved Node-Bs 162a, 162b, 162c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, and selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c. 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.

[0053] The SGW 164 may be connected to each of the evolved Node-Bs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during an inter-evolved Node-B handover, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0054] 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.

[0055] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may be in communication with, an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts 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 other networks 112, which may include other wired networks and / or wireless networks owned and / or operated by other service providers.

[0056] Although the WTRU Figures 1A to 1D Although described as wireless terminals, it is contemplated that in certain representative embodiments, such terminals may (eg, temporarily or permanently) use a wired communications interface with a communications network.

[0057] In a representative embodiment, the other network 112 may be a WLAN.

[0058] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for a BSS and one or more stations (STAs) associated with the AP. The AP may have access or an interface to a distribution system (DS) or another type of wired / wireless network that carries traffic to and / or carries traffic away from the BSS. Traffic originating from outside the BSS and destined for the STA may be reached by the AP and may be delivered to the STA. Traffic originating from the STA and destined for a target outside the BSS may be transmitted to the AP to be delivered to the corresponding target. Traffic between STAs within the BSS may be transmitted by the AP, for example, wherein the source STA may transmit traffic to the AP, and the AP may deliver traffic to the target STA. Traffic between STAs within the BSS may be considered and / or referred to as point-to-point traffic. Point-to-point traffic may be transmitted between the source STA and the target STA (e.g., directly between them) using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunnel DLS (TDLS). A WLAN using an independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (eg, all STAs in the STA) may communicate directly with each other. The IBSS communication mode may sometimes be referred to herein as an "ad hoc" communication mode.

[0059] When using the 802.11ac infrastructure operating mode or a similar operating mode, the AP may send beacons on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., a 20 MHz wide bandwidth) or a dynamically set width. The primary channel may be an operating channel of the BSS and may be used by the STA to establish a connection with the AP. In certain representative embodiments, carrier sense multiple access / collision avoidance (CSMA / CA) may be implemented, for example, in an 802.11 system. For CSMA / CA, a STA (e.g., each 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.

[0060] High throughput (HT) STAs may communicate using a 40 MHz wide channel (eg, via a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels) to form a 40 MHz wide channel.

[0061] Very high throughput (VHT) STA can support 20MHz, 40MHz, 80MHz and / or 160MHz wide channels. 40MHz channels and / or 80MHz channels can be formed by combining continuous 20MHz channels. 160MHz channels can be formed by combining 8 continuous 20MHz channels, or by combining two non-continuous 80MHz channels (this can be called 80+80 configuration). For 80+80 configuration, after channel coding, the data can pass through a segment parser that can divide the data into two streams. Each stream can be processed by inverse fast Fourier transform (IFFT) and time domain processing separately. These streams can be mapped to two 80MHz channels, and the data can be sent by sending STA. At the receiver of the receiving STA, the above-mentioned operation for 80+80 configuration can be reversed, and the combined data can be transmitted to the medium access control (MAC).

[0062] 802.11af and 802.11ah support operating modes below 1GHz. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah relative to those used in 802.11n and 802.11ac. 802.11af supports 5MHz, 10MHz, and 20MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1MHz, 2MHz, 4MHz, 8MHz, and 16MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support meter type control / machine type communication (MTC), such as MTC devices in macro coverage areas. MTC devices may have certain capabilities, such as limited capabilities, including support for (e.g., only support for) certain bandwidths and / or limited bandwidths. MTC devices may include batteries with battery life above a threshold (e.g., to maintain very long battery life).

[0063] WLAN systems that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) include channels that can be designated as primary channels. The primary channel may have a bandwidth equal to the maximum 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 (which supports the minimum bandwidth operating mode) from all STAs operating in the BSS. In the example of 802.11ah, for STAs (e.g., MTC-type devices) that support (e.g., only support) a 1MHz mode, the primary channel may be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the state of the primary channel. If the primary channel is busy, for example, because a STA (which only supports a 1MHz operating mode) is transmitting to the AP, all available bands may be considered busy even if most of the available bands remain idle.

[0064] In the United States, the available frequency band for 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz, depending on the country code.

[0065] Figure 1D1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As noted above, the RAN 104 may employ NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0066] The RAN 104 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 104 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to send signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a may, for example, use multiple antennas to send 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, gNB 180a may transmit multiple component carriers to 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, 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).

[0067] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with 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 the gNBs 180a, 180b, 180c using subframes or Transmission Time Intervals (TTIs) of varying or scalable lengths (e.g., containing a varying number of OFDM symbols and / or lasting a varying length of absolute time) .

[0068] gNBs 180a, 180b, 180c can be configured to communicate with WTRUs 102a, 102b, 102c in stand-alone configuration and / or non-stand-alone configuration. In stand-alone configuration, WTRUs 102a, 102b, 102c can communicate with gNBs 180a, 180b, 180c without also accessing another RAN (e.g., such as evolved Node Bs 160a, 160b, 160c). In stand-alone configuration, WTRUs 102a, 102b, 102c can utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In stand-alone configuration, WTRUs 102a, 102b, 102c can communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In non-stand-alone configuration, WTRUs 102a, 102b, 102c can communicate / connect with gNBs 180a, 180b, 180c while also communicating / connecting with another RAN such as evolved Node Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c can implement the DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more evolved Node Bs 160a, 160b, 160c substantially simultaneously. In non-stand-alone configuration, evolved Node Bs 160a, 160b, 160c can act as a mobility anchor for WTRUs 102a, 102b, 102c, and gNBs 180a, 180b, 180c can provide additional coverage and / or throughput to serve WTRUs 102a, 102b, 102c.

[0069] Each of gNBs 180a, 180b, 180c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, scheduling of users in UL and / or DL, support for network slicing, DC, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, and routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, etc. As Figure 1D shown, gNBs 180a, 180b, 180c can communicate with each other via the Xn interface.

[0070] Figure 1DThe illustrated CN 106 may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and possible data networks (DNs) 185a, 185b. Although the aforementioned elements are depicted as part of the CN 106, it should be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0071] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via the N2 interface and may act as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRU 102a, 102b, 102c, support of network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a specific SMF 183a, 183b, management of registration areas, termination of non-access stratum (NAS) signaling, and mobility management, etc. The AMF 182a, 182b may use network slicing to customize CN support for the WTRU 102a, 102b, 102c based on the type of service utilized by the WTRU 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, etc. The AMF 182a, 182b may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0072] The SMF 183a, 183b may be connected to the AMF 182a, 182b in the CN 106 via the N11 interface. The SMF 183a, 183b may also be connected to the UPF 184a, 184b in the CN 106 via the N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b, and configure traffic routing through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy implementation and QoS, and providing DL data notifications. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0073] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via the N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering DL packets, and providing mobility anchoring, etc.

[0074] The CN 106 may facilitate communications with other networks. For example, the CN 106 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts 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 other networks 112, which may include other wired networks and / or wireless networks owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to the DNs 185a, 185b via the UPFs 184a, 184b via the N3 interfaces to the UPFs 184a, 184b and the N6 interfaces between the UPFs 184a, 184b and the local DNs 185a, 185b.

[0075] Given that Figures 1A to 1D as well as Figures 1A to 1D Corresponding to the description of the present invention, one or more or all of the functions described herein with reference to one or more of the following items may be performed by one or more simulation devices (not shown): WTRU102a-d, base station 114a-114b, evolved Node B 160a-160c, MME 162, SGW 164, PGW 166, gNB 180a-180c, AMF 182a-182b, UPF 184a-184b, SMF 183a-183b, DN 185a-185b and / or any other device described herein. The simulation device may be one or more devices configured to simulate one or more or all of the functions described herein. For example, the simulation device can be used to test other devices and / or simulate network and / or WTRU functions.

[0076] The simulation device can be designed to implement one or more tests of other devices in a laboratory environment and / or in an operator network environment. For example, one or more simulation devices can perform one or more functions or all functions while being fully or partially implemented and / or deployed as part of a wired communication network and / or a wireless communication network to test other devices within the communication network. One or more simulation devices can perform one or more functions or all functions while being temporarily implemented / deployed as part of a wired communication network and / or a wireless communication network. The simulation device can be directly coupled to another device for testing and / or perform testing using over-the-air wireless communications.

[0077] One or more simulation devices can perform one or more (including all) functions without being implemented / deployed as part of a wired communication network and / or a wireless communication network. For example, the simulation device can be utilized in a test scenario in a test lab and / or a non-deployed (e.g., testing) wired communication network and / or wireless communication network to implement testing of one or more components. One or more simulation devices can be test equipment. Direct RF coupling and / or wireless communication via RF circuits (e.g., which can include one or more antennas) can be used by the simulation device to send and / or receive data.

[0078] In frequency range 2 (FR2), conventional beam management may result in beam sweeping and measurements of a large number of antennas at the gNB side and the WTRU side. When selecting the best beam, the WTRU may report up to four beams during the beam management process (e.g., based on reference signal received power (RSRP)).

[0079] Using artificial intelligence (AI) / machine learning (ML) models, FR2 beam selection / prediction can be performed based on frequency range 1 (FR1) channel state information (CSI) measurements. However, in scenarios with hierarchical spatial relationships and associations between beam resources in different frequency ranges, the implementation of such a framework is subject to addressing key challenges in the measurement and reporting of beams and the training and verification of AI / ML models. In addition, the use of AI / ML model-based beam prediction may not always be beneficial. As an example instance, in the case of non-line of sight (NLOS) communications, AI / ML-based beam prediction may be inaccurate and traditional beam management processes will be beneficial.

[0080] This results in different WTRU behaviors in determining the association, measurement and reporting of beam resources and the training, verification, activation and / or deactivation of AI / ML models. Therefore, further research is needed on hierarchical beam prediction in NR AI / ML beam management.

[0081] The embodiments and examples herein explain how to efficiently / dynamically activate / deactivate AI / ML model-based beam prediction. Thus, the beam management process can be modified advantageously.

[0082] In the embodiments and examples of this document, methods are provided for activating or deactivating an AI / ML model in beam prediction based on beam measurements of different beam resources in an AI / ML framework. In an example, different beam resources may include resources with different beam widths, different frequency ranges, etc. This document proposes to determine the accuracy of the AI / ML model considering different use cases and conditions, wherein different options for selecting in the activation or deactivation of the AI / ML model are provided. Consider iterative retraining / updating of the AI / ML model based on the AI / ML output and the predicted beam, wherein in particular, this document provides conditions for retraining the AI / ML model due to changes in the activation / deactivation set of the transmit configuration indicator (TCI) state. Finally, this document presents an AI / ML model verification for beam prediction and based on reciprocity.

[0083] Hereinafter, "a", "an" and similar terms and phrases may be interpreted as "one or more" and "at least one". Similarly, any term or phrase ending with the suffix "(s)" may be interpreted as "one or more" and "at least one". For example, the term "may" may be interpreted as "can".

[0084] As used in the embodiments and examples herein, AI can be broadly defined as behavior exhibited by a machine. Such behavior can, for example, mimic the cognitive functions of sensing, inference, adaptation, and action.

[0085] As used in the embodiments and examples herein, ML may refer to an algorithm type that solves problems based on learning through experience ("data") without explicit programming ("configuration rule set"). ML may be considered a subset of AI. Based on the nature or feedback of the data available for learning the algorithm, different machine learning paradigms may be envisioned. For example, supervised learning methods may involve learning a function that maps inputs to outputs based on labeled training examples, where each training example may be a pair consisting of an input and a corresponding output. For example, unsupervised learning methods may involve detecting patterns in data without pre-existing labels. For example, reinforcement learning methods may involve performing a series of actions in an environment to maximize cumulative rewards. In some solutions, it is possible to use a combination of the above-mentioned methods or interpolation to apply machine learning algorithms. For example, a semi-supervised learning method may use a combination of a small amount of labeled data and a large amount of unlabeled data during training. In this regard, semi-supervised learning falls between unsupervised learning (no labeled training data) and supervised learning (only labeled training data).

[0086] As used in the embodiments and examples herein, deep learning (DL) may refer to a class of machine learning algorithms that employ artificial neural networks (such as deep neural networks (DNNs)) that are loosely inspired by biological systems. DNNs are a special class of machine learning models inspired by the human brain, in which inputs are linearly transformed and passed through nonlinear activation functions multiple times. DNNs are typically composed of multiple layers, each of which consists of a linear transformation and a given nonlinear activation function. DNNs can be trained using training data via a back propagation algorithm. Recently, DNNs have demonstrated prior art performance in various fields (e.g., speech, vision, natural language, etc.) and for various machine learning settings for supervision, unsupervised, and semi-supervised. The term "method / processing based on AI / ML (AIML)" may refer to implementing behaviors and / or meeting requirements based on data learning without explicit configuration of a sequence of action steps. Such methods may enable learning of complex behaviors that may be difficult to specify, difficult to implement, or both when using old-style methods.

[0087] The WTRU may transmit or receive a physical channel or a reference signal (RS) according to at least one spatial domain filter.As used in embodiments and examples herein, the term "beam" can be used to refer to a spatial domain filter.

[0088] The WTRU may transmit a physical channel or signal using the same spatial domain filters used to receive RS (such as channel state information reference signal (CSI-RS)) or synchronization signal (SS) blocks. The RS or SS blocks transmitted by the WTRU may be referred to as "target" and the RS or SS blocks received may be referred to as "reference" or "source". In such cases, the WTRU may be said to transmit the target physical channel or signal based on the spatial relationship of the reference to such RS or SS blocks.

[0089] The WTRU may transmit a first physical channel or signal according to the same spatial domain filter as used to transmit a second physical channel or signal. The first transmission and the second transmission may be referred to as "target" and "reference" (or "source"), respectively. In such a case, the WTRU may be said to transmit the first (target) physical channel or signal according to a spatial relationship with reference to the second (reference) physical channel or signal.

[0090] The spatial relationship may be implicit, configured by radio resource control (RRC) signaling or signaled by a MAC control element (CE) or downlink control information (DCI). For example, a WTRU may implicitly send a physical uplink shared channel (PUSCH) transmission and a demodulation reference signal (DM-RS) for the PUSCH according to the same spatial domain filter as a sounding reference signal (SRS), which is indicated by an SRS resource indicator (SRI) indicated in the DCI or configured by RRC signaling. For another example, the spatial relationship may be configured by RRC signaling for SRI or signaled by a MAC CE for a physical uplink control channel (PUCCH). Such a spatial relationship may also be referred to as a "beam indication".

[0091] The WTRU may receive a first (target) downlink channel or signal based on the same spatial domain filters or spatial reception parameters as a second (reference) downlink channel or signal. For example, such an association may exist between a physical channel (such as a physical downlink control channel (PDCCH) or a physical downlink shared channel (PDSCH)) and its corresponding DM-RS. Such an association may exist at least when the first signal and the second signal are reference signals and when the WTRU is configured with a quasi co-location (QCL) assumption type D between corresponding antenna ports. Such an association may be configured as a TCI state. The WTRU may indicate the association between a CSI-RS or SS block and a DM-RS by an index to a set of TCI states (configured by RRC signaling and / or signaled by a MAC CE). Such an indication may also be referred to as a "beam indication".

[0092] As used herein, a transmit and receive point (TRP) may be used interchangeably with one or more of a transmit point (TP), a receive point (RP), a radio remote head (RRH), a distributed antenna (DA), a base station (BS), a sector (sector of a BS), and a cell, but still consistent with the embodiments and examples provided herein. In one example, a cell may be a geographic cell area served by a BS. In addition, as used herein, a multi-TRP may be used interchangeably with one or more of an MTRP, an M-TRP, and a plurality of TRPs, but still consistent with the embodiments and examples provided herein.

[0093] The WTRU may report a subset of CSI components, where the CSI components may correspond to at least a CSI-RS resource indicator (CRI), a synchronization signal block (SSB) resource indicator (SSBRI), an indication of a panel for reception at the WTRU (such as a panel identifier or a group identifier), measurement results such as L1-RSRP, L1-SINR obtained from SSB or CSI-RS (e.g., cri-RSRP, cri-SINR, ssb-Index-RSRP, ssb-Index-SINR), and at least other channel state information such as a rank indicator (RI), a channel quality indicator (CQI), a precoding matrix indicator (PMI) and / or a layer indicator (LI).

[0094] Embodiments herein include activating / deactivating beam prediction based on AI / ML modeling. Specifically, embodiments herein include AI / ML model activation / retraining / deactivation / fallback options. Furthermore, embodiments herein include determining the accuracy of the AI / ML model. Furthermore, embodiments herein include use cases and conditions for which the AI / ML model may be used.

[0095] Embodiments herein include dynamic retraining / updating of AI / ML models. Specifically, embodiments herein include iterative retraining / updating of AI / ML models based on AI / ML. Furthermore, embodiments herein include dynamic retraining / updating of AI / ML models based on changes in activation / deactivation sets of TCI states. Furthermore, embodiments herein include reciprocity-based AI / ML model beam prediction verification.

[0096] Embodiments and examples herein include activating / deactivating FR2 beam prediction based on AI / ML modeling. In the examples provided herein, the WTRU is configured with one or more CSI-RS resources in FR1 for channel measurement. The WTRU derives one or more FR1 CSI parameters. One or more of the following may be applied. The WTRU may determine one or more FR2 beam resources, may predict one or more FR2 beam resources, or may perform both. In one example, the WTRU may determine, predict, or both based on an AI / ML model. In one example, a beam resource may consist of a TCI state for a downlink, a CSI-RS or SSB, an SRS resource, or a TCI state for an uplink. In addition, the WTRU may report one or more FR1 CSI parameters (e.g., multiple CRIs), and the base station or gNB may perform FR2 beam prediction accordingly. In one example, beam prediction may be performed based on an AI / ML model.

[0097] In addition, the WTRU may receive one or more FR2 beam resources, which may be predicted FR2 resources. In addition, the WTRU may receive one or more thresholds for accuracy level during the verification process. For example, the WTRU may receive thresholds for LOS probability, CQI, block error rate (BLER), Doppler shift, etc. In addition, the WTRU may perform a verification process on, for example, the received FR2 beam resources based on one or more accuracy parameters.

[0098] Embodiments herein include AI / ML model activation / retraining / deactivation / fallback options. In one example, based on the measured / determined accuracy parameters, the WTRU may determine to use one or more of the following options. In the case where the accuracy parameters are acceptable, the first option may be to use / activate the AI / ML model in beam prediction.

[0099] In case the accuracy parameter is not acceptable, in the second option, the WTRU may select from other candidate beam resources based on the AI / ML prediction. In addition, the WTRU may transmit one or more FR2 candidate beam resources, for example, indicated by the base station or gNB, or determined by the WTRU based on the AI / ML model. The WTRU may start the corresponding timer / counter. In addition, the WTRU may monitor / measure the candidate beams. In case the accuracy metric is acceptable for the beam resource, the WTRU may indicate the corresponding beam via the physical random access channel (PRACH) or PUCCH. In case the counter / timer has exceeded the corresponding maximum count / time, the WTRU may switch to the fourth option, which will be further explained below.

[0100] The third option may update / retrain the parameters / models. The WTRU may transmit a request to update / retrain, for example, the AI / ML parameters / models. The WTRU may start a corresponding timer / counter. The WTRU may use the updated / retrained parameters / models for beam prediction in FR2. In case the accuracy metric is acceptable for the predicted FR2 beam resources, the WTRU may indicate the corresponding beam via PRACH or PUCCH. In case the counter / timer has exceeded the corresponding maximum count / time, the WTRU may switch to the fourth option, which is explained below.

[0101] A fourth option may include fallback. The WTRU may transmit a request to deactivate the AI / ML model and / or fall back to a conventional beam management mechanism.

[0102] Embodiments herein include determining the accuracy of the AI / ML model. The WTRU may determine accuracy parameters for a predicted FR2 beam based on a verification process and a corresponding threshold. For example, for a predicted beam resource in FR2, if the measured CSI parameters and / or the assumed (Hyp.) PDCCH BLER are higher and / or lower than corresponding thresholds, respectively, the WTRU may determine that, for example, the accuracy parameters for the AI / ML model are acceptable. In an example, the measured CSI parameters may include one or more of RSRP, signal to interference plus noise ratio (SINR), CQI, etc.

[0103] In addition, embodiments and examples herein include that the WTRU may determine accuracy based on an association of one or more parameters. In an example, the one or more parameters may include one or more of CQI, hypothesis, PDCCH BLER, RSRP, SINR, LOS probability, Doppler shift, Doppler spread, average delay, delay spread, etc. For example, for the predicted beam resources in FR2, the LOS probability is higher than a first threshold (e.g., LOS_th); however, the derived CQI is lower than the corresponding threshold (e.g., CQI_th). In this way, the WTRU may determine to perform the third option. For another example, for the predicted beam resources in FR2, the LOS probability is lower than a first threshold (e.g., LOS_th) and the derived CQI is lower than the corresponding threshold (e.g., CQI_th). In this way, the WTRU may determine to perform the second option or the fourth option, for example, based on the determined LOS probability.

[0104] Additionally or alternatively, the WTRU may be configured with one or more of the use cases, such as a subset of one or more use cases, and / or conditions for which the AI / ML model may be used, such as LOS, antenna panel configuration, etc. The WTRU may determine and transmit a request to the base station or gNB to fall back to FR2 beam management and deactivate AI / ML beam prediction, for example, based on the configured use cases.

[0105] Thus, one or more of the following may apply. An indication of LOS, a probability of LOS, or both may apply. Specifically, the WTRU may request a fallback in the event that the probability of LOS is below a corresponding threshold for any of the CSI-RS resources. For example, the base station or gNB may configure multiple FR1 beams to find the one FR1 beam with the best probability of LOS to be used in the AI / ML FR2 beam prediction.

[0106] Additionally, antenna panel configuration may be applied. In one example, in the absence of the same QCL type D assumption between the FR1 antenna port and the FR2 antenna port and / or panel at the WTRU side, the WTRU may determine to transmit a request to the base station to fall back to FR2 beam management and deactivate AI / ML beam prediction.

[0107] In addition, the WTRU may use other conditions to activate / deactivate AI / ML. For example, the other conditions may include the number of FR1 beams and FR2 beams supported. In addition, other conditions may include the boresight of the antenna array at the WTRU side, at the base station or gNB side, or at both sides, the beam direction of the antenna, or the antenna array configuration for FR1 and FR2. In addition, other conditions may include WTRU capabilities.

[0108] Embodiments and examples herein include iterative training / updating of AI / ML models based on AI / ML output prediction beams. In one example, a WTRU receives one or more sets of FR1 beam resources and FR2 beam resources and derives beam resource parameters. The beam resources may consist of one or more of a TCI state for downlink, a CSI-RS or SSB, an SRS resource for uplink, or a TCI state for uplink.

[0109] In initial training, the WTRU may use the measured CSI parameters and TCI states in beam prediction AI / ML model training. In one example, the measured CSI parameters may include one or more of CQI, PMI, CRI, etc. The WTRU may determine one or more best FR2 beams, for example based on RSRP. The WTRU may then report the predicted FR2 beams to the base station or gNB. The WTRU may receive one or more of the FR2 beams, for example based on the reported FR2 beams. The WTRU may determine whether the accuracy of the AI / ML and prediction is acceptable.

[0110] Retraining may be optionally used. If the accuracy is not within an acceptable range, the WTRU may use the received FR2 beams to retrain and / or update the corresponding AI / ML model parameters. For example, the WTRU may determine the amount of additional information, such as the number of FR2 beams to use for retraining.

[0111] The WTRU may use the measured CSI parameters in the retrained / updated beam prediction AI / ML model and accordingly determine one or more optimal FR2 beams, for example based on RSRP. In one example, the measured CSI parameters may include one or more of CQI, PMI, CIR, etc. The WTRU may determine whether the retraining and updating of the model has resulted in a different output from the previous model, such as a different predicted FR2 beam.

[0112] If the retraining of the model has resulted in a new / different output, such as a different predicted FR2 beam, the WTRU may report the predicted FR2 beam to the base station or gNB. Otherwise, the WTRU may perform the retraining step one or more times, for example based on a timer or counter, and if unsuccessful, the WTRU determines to follow one or more of the activation / deactivation / fallback options.

[0113] Embodiments and examples herein include retraining of an AI / ML model due to a change in an activated / deactivated set of TCI states. The WTRU receives a set of activated / deactivated TCI states. In one example, the WTRU may receive the set in a MAC-CE. If the WTRU further receives a second (e.g., updated / changed) set of activated / deactivated TCI states (e.g., in a MAC-CE), one or more of the following may apply. The WTRU may determine whether retraining of the AI / ML model is required. The WTRU may determine whether the second set of activated / deactivated TCI states partially overlaps with the first set. If the overlap is greater than a threshold, the WTRU may determine that retraining is not required. Otherwise, if the overlap is less than a threshold, the WTRU may determine that retraining of the AI / ML is required.

[0114] Embodiments herein include beam prediction AI / ML model verification based on reciprocity. In an example, the WTRU determines / predicts one or more FR2 beams based on FR1 beam / CSI measurements. The WTRU performs a transmission to a base station or gNB based on the FR2 beams that the WTRU has predicted. In an example, the transmission may include one or more of an SRS, a hybrid automatic repeat request (HARQ) acknowledgment (Ack), or a CSI-RS report. The base station or gNB may measure the channel, such as RSRP, based on the received FR2 signal. The base station or gNB may then change or verify the WTRU side beam selection. The WTRU may receive one or more FR2 CSI-RS measurement and reporting configurations, which may be based on the selected beam at the base station or gNB. In an example, the measurement and reporting configuration may include one or more of CSI RS resources, QCL information, TCI status, etc. The WTRU may measure the FR2 CSI and use the measured parameters to update / retrain the AI / ML model. The WTRU may select and report the best beam and corresponding CSI quantities, such as CSI-RSRP, CIR, etc.

[0115] The WTRU may use channel and / or interference measurements. For example, the WTRU may receive a synchronization signal / physical broadcast channel (SS / PBCH) block. The SS / PBCH block (SSB) may include a primary synchronization signal (PSS), a secondary synchronization signal (SSS), and / or a physical broadcast channel (PBCH). The WTRU may monitor, receive, or attempt to decode SSBs during initial access, initial synchronization, radio link monitoring (RLM), cell search, cell handover, etc.

[0116] In addition, the WTRU may measure and report CSI, where the CSI for each connection mode may include or be configured with one or more of the following: CSI reporting configuration, CSI-RS resource set, or non-zero power (NZP) CSI-RS resources. The CSI reporting configuration may include one or more of the following: CSI reporting amount, such as CQI, RI, PMI, CRI, LI, etc.; CSI reporting type, such as aperiodic, semi-persistent, or periodic; CSI reporting codebook configuration, such as Type I, Type II, Type II port selection, etc.; or CSI reporting frequency. The CSI-RS resource set may include one or more of the following CSI resource settings: NZP-CSI-RS resources for channel measurement; NZP CSI-RS resources for interference measurement; or CSI-IM resources for interference measurement. The NZP CSI-RS resource may include one or more of the following: NZP CSI-RS resource identification (ID); periodicity and offset; QCL information and TCI-state; or resource mapping, such as number of ports, density, code division multiplexing (CDM) type, etc.

[0117] The WTRU may indicate, determine, or be configured with one or more reference signals. The WTRU may monitor, receive, and measure one or more parameters based on the corresponding reference signals. For example, one or more of the following may apply. The following parameters are non-limiting examples of parameters that may be included in the reference signal measurement. One or more of these parameters may be included. Other parameters may be included.

[0118] SS reference signal received power (SS-RSRP) can be measured based on synchronization signals (e.g., demodulation reference signal (DMRS) or SSS in PBCH). SS-RSRP can be defined as the linear average of the power contribution of resource elements (REs) carrying the corresponding synchronization signal. When measuring RSRP, power scaling of the reference signal may be required. In the case where SS-RSRP is used for L1-RSRP, the measurement can be done based on CSI reference signals in addition to synchronization signals.

[0119] The CSI-RSRP may be measured based on a linear average of the power contributions of the REs carrying the corresponding CSI-RS.The CSI-RSRP measurement may be configured within the measurement resources of the configured CSI-RS opportunity.

[0120] The SS-SINR may be measured based on a synchronization signal (e.g., DMRS or SSS in PBCH). The SS-SINR may be defined as the linear average of the power contribution to the REs carrying the corresponding synchronization signal divided by the linear average of the noise and interference power contributions. In the case where the SS-SINR is used for the L1-SINR, the noise and interference power measurement may be done based on resources configured by higher layers.

[0121] The CSI-SINR may be measured based on the linear average of the power contribution to the REs carrying the corresponding CSI-RS divided by the linear average of the noise and interference power contributions. In the case where the CSI-SINR is used for L1-SINR, the noise and interference power measurement may be done based on the resources configured by the higher layers. Otherwise, the noise and interference power may be measured based on the resources carrying the corresponding CSI-RS.

[0122] The received signal strength indicator (RSSI) may be measured based on an average of the total power contribution in the configured OFDM symbol and bandwidth.Power contributions may be received from different resources (eg, co-channel serving and non-serving cells, adjacent channel interference, thermal noise, etc.).

[0123] A cross-layer interference received signal strength indicator (CLI-RSSI) may be measured based on the average of the total power contribution in the configured OFDM symbols of the configured time and frequency resources. Power contributions may be received from different resources (e.g., cross-layer interference, co-channel serving and non-serving cells, adjacent channel interference, thermal noise, etc.).

[0124] Sounding Reference Signal RSRP (SRS-RSRP) may be measured based on a linear average of the power contributions of REs carrying the corresponding SRS.

[0125] CSI report configurations (e.g., CSI-ReportConfigs, beam / CSI report configurations, etc.) can be associated with a single bandwidth part (BWP), indicated, for example, by a BWP-Id, in which one or more of the following parameters are configured: CSI-RS resources and / or CSI-RS resource sets for channel and interference measurements; CSI-RS report configuration types, including periodic, semi-persistent, and aperiodic; CSI-RS transmission periodicity for periodic and semi-persistent CSI reporting; CSI-RS transmission time slot offsets for periodic, semi-persistent, and aperiodic CSI reporting; CSI-RS transmission time slot offset lists for semi-persistent and aperiodic CSI reporting; time restrictions for channel and interference measurements; reporting band configuration (wideband / sub-band CQI, PMI, etc.); thresholds and calculation modes for reporting quantities (CQI, RSRP, SINR, LI, RI, etc.); codebook configuration; group-based beam reporting; CQI table; subband size; non-PMI port indication; port index; etc.

[0126] Examples provided herein may include CSI-RS resource configuration. A CSI-RS resource set (e.g., NZP-CSI-RS-ResourceSet) may include one or more CSI-RS resources in a CSI-RS resource (e.g., NZP-CSI-RS-Resource and CSI-ResourceConfig), wherein the WTRU may be configured with one or more of the following in the CSI-RS resource: CSI-RS periodicity and slot offset for periodic and semi-persistent CSI-RS resources; CSI-RS resource mapping for defining the number, density, CDM type, OFDM symbol and subcarrier occupancy of CSI-RS ports; bandwidth portion to which the configured CSI-RS is allocated; or an indexing of a TCI state including a QCL source RS and a corresponding QCL type.

[0127] The examples provided herein may include RS resource set configurations. One or more of the following configurations may be used for RS resource sets. Specifically, the WTRU may be configured with one or more RS resource sets. In addition, the RS resource set configuration may include one or more of the following: RS resource set ID; one or more RS resources for the RS resource set; repetition (i.e., on or off); non-periodic trigger offset (e.g., one time slot in 0 to 6 time slots); or tracking reference signal (TRS) information (e.g., true or not true).

[0128] The examples provided herein may include RS resource configurations. One or more of the following configurations may be used for RS resources. For example, the WTRU may be configured with one or more RS resources. In addition, the RS resource configuration may include one or more of the following: RS resource ID; resource mapping, such as REs in a physical resource block (PRB); power control offset (e.g., a value in -8, ..., 15); power control offset with SS (e.g., -3dB, 0dB, 3dB, 6db); scrambling code ID; periodicity and offset; or QCL information (e.g., based on TCI state).

[0129] In the following, the attributes of a grant or assignment may consist of at least one of the following: frequency allocation; aspects of time allocation, such as duration; priority; modulation and coding scheme; transport block size; number of spatial layers; number of transport blocks; TCI state, CRI or SRI; number of repetitions; whether the repetition scheme is type A or type B; whether the grant is a configured grant type 1, type 2 or a dynamic grant; whether the assignment is a dynamic assignment or a semi-persistent scheduled (configured) assignment; configuring a grant index or a semi-persistent assignment index; configuring the periodicity of the grant or assignment; channel access priority class (CAPC); or any parameter provided by the MAC or by the RRC in the DCI for scheduling grants or assignments.

[0130] In the following, the indication by the DCI may consist of at least one of the following: an explicit indication by a DCI field or by the RNTI used to mask the cyclic redundancy check (CRC) of the PDCCH; or an implicit indication by attributes such as the DCI format, DCI size, Coreset or search space, aggregation level, the first resource element of the received DCI (for example, the index of the first control channel element), where the mapping between the attributes and the values ​​may be signaled by RRC or MAC.

[0131] Examples provided herein may include beam quality monitoring, radio link monitoring, or both. For example, the WTRU may use / receive / or be configured with one or more sets of reference signals for each BWP for monitoring and detecting beam failure detection. For example, the term q0 may be used for a beam failure detection set. In another example, the term q0,0 or q0,1 may be used as a beam failure detection set. A beam failure detection set (e.g., set q0, q0,0 or q0,1) may include one or more reference signals, where the reference signal may be a CSI-RS resource configuration index and / or an SSB index. The reference signals included in the beam failure detection RS set may be the same as the reference signals configured / used / received for RLM.

[0132] If the WTRU is not provided / configured with a beam failure detection RS set for BWP (e.g., set q0, q0,0, or q0,1), the WTRU may determine the corresponding RS set. For example, the WTRU may determine the RS signals to be included in the beam failure detection RS set for BWP based on the periodic CSI-RS resource configuration index that the WTRU uses to monitor the PDCCH in the corresponding CORESET as indicated by the TCI state.

[0133] The WTRU may measure the reference signals included in the beam failure detection RS set and estimate the radio link quality accordingly. The WTRU may use one or more thresholds / ranges to monitor and estimate the radio link quality. For example, an out-of-sync threshold (e.g., Q_out), an in-sync threshold (e.g., Q_in), or both may be used, where the thresholds Q_out, Q_in, or both may be used to estimate the quality of the radio link and / or the corresponding beam. The terms Q_out and Q_in can be used to represent one or more attributes or parameters, and the corresponding values ​​of the attributes or parameters.

[0134] The threshold Q_out can be used to determine a radio link and / or beam quality at which signal transmissions may not be reliably received, corresponding to an out-of-sync block error rate (BLER_out). Additionally or alternatively, the threshold Q_in can be used to determine a radio link and / or beam quality at which signal transmissions can be reliably received, corresponding to an in-sync block error rate (BLER_in). BLER_out, BLER_in, or both can be explicitly determined by the base station or gNB.

[0135] In the case where the base station or gNB does not explicitly determine BLER_out and / or BLER_in, they may be estimated based on one or more parameters. For example, the WTRU may use, receive, or be configured with PDCCH transmission parameters to perform out-of-sync assessment, in-sync assessment, or both assessments. In one example, the number of OFDM symbols, aggregation level, ratio of assumed PDCCH RE energy to average SSS RE energy, ratio of assumed PDCCH DMRS energy to average SSS RE energy, BWP in number of PRBs, subcarrier spacing, etc. may be used to determine the BLER_out threshold, the BLER_in threshold, or both thresholds.

[0136] Examples of PDCCH transmission parameters that may be included when evaluating the Q_out and Q_in thresholds are shown in Tables 1 and 2, respectively. These tables are non-limiting examples of parameters that may be included in evaluating the out-of-sync threshold and the in-sync threshold. One or more of these parameters may be included. The values, number of PRBs, and selections for each parameter are examples. Other values, number of PRBs, or selections may be included.

[0137]

[0138]

[0139] Table 1: PDCCH transmission parameters for out-of-sync assessment

[0140] property Value of BLER configuration #0 DCI payload size 1-0 Controlling the number of OFDM symbols 2 Aggregation Level (CCE) 4 Ratio of assumed PDCCH RE energy to average SSS RE energy 0dB Ratio of assumed PDCCH DMRS energy to average SSS RE energy 0dB Bandwidth (PRB) 24 Subcarrier spacing (kHz) SCS of active DL BWP DMRS pre-decoder granularity REG Bundle Size REG Bundle Size 6 CP length normal Mapping from REG to CCE distributed

[0141] Table 2: PDCCH transmission parameters for synchronization assessment

[0142] Hereinafter, the term "RS" may be used interchangeably with one or more of an RS resource, an RS resource set, an RS port, and an RS port group, but is still consistent with the embodiments and examples provided herein. In addition, the term "RS" may be used interchangeably with one or more of SSB, CSI-RS, SRS, DM-RS, TRS, PRS, and a phase tracking reference signal (PTRS), but is still consistent with the embodiments and examples provided herein.

[0143] Hereinafter, the phrase "reference signal" may be used interchangeably with one or more of the following, while still being consistent with the embodiments and examples provided herein: SRS, CSI-RS, DM-RS, PT-RS, and / or SSB.

[0144] Hereinafter, the term "channel" may be used interchangeably with one or more of the following, but still consistent with the embodiments and examples provided herein: PDCCH, PDSCH, PUCCH, PUSCH, PRACH, etc. Hereinafter, the phrase "RS resource set" may be used interchangeably with one or more of RS resources and beam groups, but still consistent with the embodiments and examples provided herein.

[0145] In the following, the phrase "beam report" may be used interchangeably with one or more of CSI measurement, CSI report and beam measurement, but still consistent with the embodiments and examples provided herein. In the following, the proposed solution for beam resource prediction can be used for beam resources belonging to a single or multiple cells and a single or multiple TRPs, and still consistent with the embodiments and examples provided herein.

[0146] Hereinafter, the phrase "CSI report" may be used interchangeably with one or more of CSI measurement, beam report, and beam measurement, but still consistent with the embodiments and examples provided herein. Hereinafter, the term "quality" or the phrase "measurement quality" may be used interchangeably with one or more of RSRP, reference signal received quality (RSRQ), SINR, CQI, modulation and coding scheme (MCS), assumed PDCCH BLER, PDSCH BLER, LOS probability, etc., but still consistent with the embodiments and examples provided herein.

[0147] This document provides implementation schemes and examples for activating / deactivating beam prediction based on AI / ML modeling. In one example, the WTRU may receive one or more CSI report configurations. For example, the WTRU may receive a CSI-ReportConfig. In one example, the WTRU may receive one or more CSI report configurations from a base station. The CSI report configuration may include a CSI report amount, which may indicate a CSI parameter that may need to be measured / estimated / derived and reported. In one example, the CSI report amount may be one or more of CQI, RI, PMI, CRI, LI, SINR, RSRP, etc.

[0148] The CSI reporting configuration may be associated with one or more CSI resource settings (e.g., CSI-ResourceConfig) for channel / interference measurements. A resource setting may include a list of CSI resource sets, where the list may include references to one or more CSI-RS resource sets, SSB sets, or both types of sets.

[0149] Figure 2is a system diagram illustrating an example of performing beam prediction in a second set of beam resources based on beam resources reported in a first set of beam resources. Figure 2 The illustrated example presents a WTRU configured with a first set of beam resources. For example, the first set of beam resources may be CSI-RS resources, TCI states, etc. Additionally, the first set of beam resources may be in a first frequency range (e.g., FR1) and / or a first beam width (e.g., a wide beam width for wide beams), which are illustrated as CSI-RS resources. 1,1 , C 1,2 and C 1,3 .

[0150] In addition, the WTRU is configured with a second set of beam resources. For example, the second set of beam resources may be CSI-RS resources, TCI states, etc. In addition, the second set of beam resources may be in a second frequency range (e.g., FR2) and / or a second beam width (e.g., a narrow beam width for narrow beams) that are located ... Figure 2 In example B 21 , B 22 ,……,B 29 .

[0151] The WTRU may perform measurements on one or more CSI-RS resources and derive one or more CSI parameters. In one example, the WTRU may determine that the best beam resource in the first set of beam resources may be Figure 2 C 1,2 For example, the WTRU may determine beam C 1,2 is the best beam because it is the beam with the highest RSRP or LOS. For example, the WTRU may determine the best PMI in the first set of CSI-RS resources, which is shown by the directional arrows pointing from the base station 214 to the WTRU 202 and the obstacle 203. In the example shown in the system diagram 200, the obstacle 203 reflects the signal received from the base station 214 to the WTRU 202.

[0152] The WTRU may select a corresponding beam resource, such as C 1,2 Determined parameters are reported in a first set of CSI-RS resources, such as CSI parameters, e.g., RSRP, RI, LI, SINR, PMI, CQI, etc. At a base station 214, which may be a gNB in ​​one example, the reported CSI parameters can be used to predict one or more of the best beam resources in a second frequency range (e.g., FR2), e.g., based on an AI / ML model.

[0153] Additionally or alternatively, the WTRU may determine one or more best beam resources in the second set, for example based on an AI / ML model. For example, the WTRU may select / determine / predict the best beam resources in the second set, for example based on the best PMI. Figure 2 Beam B 2,4 and B 2,6 . In this way, the WTRU may report the determined / selected beam resources (e.g., beam index or CRI) and the corresponding predicted RSRP / SINR for up to a maximum number of beams (e.g., up to four beams). In one example, the corresponding predicted RSRP / SINR may include L1-RSRP, L1-SINR, etc. In other words, the optimal beam resources in the second frequency range may be determined based on the AI / ML model without excessive beam sweeping at the base station 214 (which may be a gNB) or at the WTRU 202.

[0154] In a framework based on beam prediction for a second frequency range and based on measurements in a first frequency range (e.g., based on an AI / ML model), the beam prediction may not be so accurate and may require further verification and validation. A person of ordinary skill in the art will appreciate that one or more problems are solved by the embodiments and examples provided herein. For example, how is the beam prediction verified (e.g., based on AI / ML)? How can one distinguish whether a low quality of prediction (e.g., a predicted beam with low RSRP) is due to a bad behavior of the AI / ML model or whether it has other reasons? How to resolve situations with low prediction quality, e.g., a predicted beam with low RSRP / CQI?

[0155] In one example, the WTRU may activate the AI / ML model in beam prediction based on one or more accuracy parameters for candidate beam resources. The WTRU may select other candidate beam resources based on the AI / ML beam prediction. In addition, the WTRU may determine the accuracy parameters for the beam predicted by the AI / ML model. In addition, the WTRU may deactivate the AI / ML beam prediction based on one or more of an indication of line of sight (LOS), a probability of LOS, an antenna panel configuration, a supported number of beams, an antenna array, or WTRU capabilities. In addition, the WTRU may use the measured CSI parameters and TCI status in beam prediction for initial training of the AI / ML model.

[0156] In an example solution, the WTRU may determine or be configured to perform a check on the AI / ML output. For example, the AI / ML model may be used to predict beam resources in a second frequency range based on measurements (such as CSI measurements) in a first frequency range. For example, the AI / ML model may be executed at the WTRU and / or the gNB. The beam resources may consist of TCI states for downlink, CSI-RS or SSB, SRS resources, or TCI states for uplink.

[0157] The WTRU may determine, instruct, or be configured to receive and measure one or more of the CSI / beam resources in order to verify the validity and / or accuracy of the AI / ML output. In one example, the WTRU may suggest, report, or request the base station or gNB to send one or more channels / signals corresponding to the predicted beam resources, such as the same QCL, the same spatial relationship, or the same two. In one example, the one or more channels / signals may be PDCCH, CSI-RS signals, etc. As another example, the WTRU may be configured to receive and measure one or more channels / signals (e.g., PDCCH, CSI-RS signals, etc.) corresponding to the predicted beam resources (e.g., the same QCL, the same spatial relationship, or the same two). As an example, the requested / configured beam resources may be in a second frequency range, such as in FR2.

[0158] The WTRU may determine or be configured to derive measurements of one or more parameters regarding the configured / determined beam resources. For example, the WTRU may be configured to derive CSI parameters such as LOS probability, PMI, CQI, RSRP, SINR, Doppler drift, etc. based on the configured / received CSI-RS signal. For another example, the WTRU may be configured to derive parameters corresponding to the received channel, such as the PDCCH assumed BLER. In addition, the WTRU may determine or be configured with one or more thresholds associated with the parameters determined / configured to be measured. In addition, the WTRU may determine or be configured with one or more limits / maximum / minimum values ​​associated with the timer / counter used in the verification process.

[0159] The WTRU may determine / report the validity of the AI / ML model, and the WTRU may determine / report that the AI / ML is "valid" (the measured accuracy is acceptable) or "invalid" (the measured accuracy is not acceptable). Thus, in the case where the measured parameters or associations / combinations of measured parameters are within an acceptable range, the WTRU may determine that the AI / ML model is "valid" and has "acceptable accuracy". In the opposite case, in the case where the measured parameters or associations / combinations of measured parameters are not within an acceptable range, the WTRU may determine that the AI / ML model is "invalid" and the model "does not have acceptable accuracy".

[0160] In an example solution, the WTRU may be configured with one or more options to select under different conditions based on measurements, thresholds, and verification scenarios. Therefore, one or more of the following examples may apply.

[0161] Under option 1, the WTRU may use the AI / ML model in beam prediction, activate the AI / ML model in beam prediction, or perform both. For example, the WTRU may determine that the corresponding AI / ML model is valid and its accuracy is acceptable. Thus, the WTRU may determine to use / activate the corresponding AI / ML model, for example, for beam prediction.

[0162] Under option 2, the WTRU may select from other candidate beam resources based on the AI / ML prediction. For example, the WTRU may determine or be configured with one or more candidate (predicted) beams, for example based on the AI / ML model. In this way, in the event that the WTRU detects / determines that the best (predicted) beam is not showing acceptable accuracy, the WTRU may determine to monitor one or more candidate (predicted) beams among the candidate (predicted) beams. In the example, not shown, acceptable accuracy may be shown by a CQI less than a threshold, an RSRP less than a threshold, or both, or by a PDCCH hypothesized BLER above a threshold.

[0163] Under option 3, the parameters, the model, or both may be updated, retrained, or both. For example, the WTRU may determine that the reason that the predicted beam based on, for example, AI / ML, does not have acceptable accuracy is due to the AI / ML model. Thus, the WTRU may determine, suggest, or transmit a request to update the AI / ML model, retrain the AI / ML model, or perform both.

[0164] Under option 4, the WTRU may fall back to legacy procedures, deactivate the AI / ML model, or both. For example, the WTRU may determine that the quality, accuracy, or both of the (predicted) beam is below one or more thresholds, where the WTRU may determine that the AI / ML model is invalid. Therefore, the WTRU may determine to deactivate the AI / ML model, fall back to legacy, or do both. In one example, falling back to legacy may include using a non-AI / ML model based procedure.

[0165] In an example solution, the WTRU may determine to change the selected option based on a measured accuracy parameter, one or more timers / counters, and the like. In one example, the WTRU may determine to operate in option 2, where the WTRU may start a timer or counter, for example, for the number of candidate beams monitored. In the event that the timer (counter) times out (reaches a maximum value) before the WTRU is able to find another candidate beam with acceptable accuracy, the WTRU may determine to select another option. For example, the WTRU may determine to select option 3 or option 4. Additionally or alternatively, if the WTRU determines that one or more of the candidate beams have an acceptable accuracy, such as before the timer (counter) times out (reaches a maximum), the WTRU may report the determined beams and the WTRU may determine to select an option to use / activate the AI / ML model, for example, as in option 1.

[0166] As another example, the WTRU may determine to operate in option 3, where the WTRU may start a timer, a counter, or both. In the event that the update / retraining of the model results in the WTRU determining one or more beams with acceptable accuracy before the timer (counter) expires (reaches its maximum), the WTRU may determine the option to use, activate, or both (the retrained / updated) AI / ML model, for example, as in option 1. In the opposite case, if the timer expires (and / or the counter reaches its maximum limit) and the WTRU determines that the update / retraining of the AI / ML model has not resulted in acceptable accuracy, the WTRU may determine the option to roll back or deactivate the AI / ML model, for example, as in option 4.

[0167] In an example solution, the WTRU may determine and / or establish accuracy parameters and verification procedures based on an association / combination of one or more CSI, beam, channel, environment, and / or mobility parameters. For example, the WTRU may determine to establish an association based on one or more of the following parameters.

[0168] The WTRU may determine to establish an association based on beam resource parameters. For example, the WTRU may determine parameters corresponding to beam resources and CSI metrics, such as RSRP, SINR, CQI, PMI, RI, LI, assumed PDCCH BLER, etc. and corresponding thresholds.

[0169] The WTRU may determine to establish an association based on channel, mobility, and environmental parameters. For example, the WTRU may determine parameters corresponding to channels, environment, and mobility, such as LOS probability, Doppler drift, Doppler spread, average delay, delay spread, etc. and corresponding thresholds.

[0170] For example, the WTRU may determine an accuracy parameter based on the association / combination of CSI and / or beam parameters and environmental, mobility, and channel parameters for (predicted) beam resources relative to corresponding thresholds. For example, the WTRU may determine one or more accuracy levels based on the association of CQI, the combination of CQI, or both and the LOS probability. For example, if the measured LOS probability and the measured received power and / or channel quality (e.g., CQI, RSRP, SINR, etc.) are higher than the corresponding thresholds, the WTRU may determine that the AI / ML model performance is acceptable, and thus the WTRU may determine to verify the AI / ML model and use / activate the corresponding AI / ML model, e.g., as in Option 1.

[0171] For example, the measured LOS probability may be higher than the corresponding threshold, while the measured received power and / or channel quality (e.g., CQI, RSRP, SINR, etc.) are lower than the corresponding thresholds. In this case, the WTRU may determine that the accuracy of the AI / ML is unacceptable. Thus, the WTRU may determine to update the AI / ML model, e.g., as in Option 3. For example, if the measured LOS probability and the measured received power and / or channel quality (e.g., CQI, RSRP, SINR, etc.) are lower than the corresponding thresholds, the WTRU may determine to monitor / measure one or more candidate (predicted) beams, e.g., as in Option 2.

[0172] In an example solution, the WTRU may suggest, request, or report the verification results and the determined options, such as activating / deactivating the AI / ML model, to the base station or gNB. In one example, the WTRU may suggest, request, or report the results and options via uplink control information (UCI) in the PUSCH as part of a CSI report, as a flag in HARQ-ACK, as a parameter in the PUCCH, as a parameter in the PRACH, etc.

[0173] In another example solution, the WTRU may determine or be configured with one or more use cases (or a subset of use cases) for which the WTRU determines to use, activate, or deactivate the AI / ML model. For example, the WTRU may determine to activate the AI / ML model, deactivate the AI / ML model, or both based on one or more of the following: an indication of LOS, a probability of LOS, or both; antenna panel configuration; other conditions; or all of these.

[0174] For example, using the indication of LOS, the probability of LOS, or both, the WTRU may deactivate the AI / ML model in a case where the probability of LOS is below a corresponding threshold for any of the configured / determined beam resources, such as in a first frequency range, e.g., in FR1. For example, the WTRU may be configured to determine, report, or determine and report the beam with the best probability of LOS, the highest probability of LOS, or both among a plurality of beams in a first frequency range (e.g., in FR1). In this way, the determined / reported beam may be used at the base station or gNB and / or the WTRU for AI / ML beam prediction, for example, in a second frequency range (e.g., in FR2).

[0175] In the example using an antenna panel configuration, the WTRU may deactivate the AI / ML model in the event that the same QCL Type D assumption does not exist between the antenna ports, the panel, or both (at the WTRU side) for the first frequency range and the second frequency range (e.g., for FR1 and FR2).

[0176] The WTRU may use other conditions to activate / deactivate AI / ML, such as: supported number of beams, beam attributes, WTRU capabilities, or all of these. For example, using the supported number of beams, the WTRU may determine or be configured to use / activate the AI / ML model only for a set of beams in the first frequency range and the second frequency range (e.g., in FR1 and FR2).

[0177] For example, using beam attributes, the WTRU may determine or be configured to activate the AI / ML model if one or more determined or configured parameters are within an acceptable range, such as the boresight of the antenna array, the beam direction of the antenna, or the antenna array configuration for the first frequency range and the second frequency range, such as at the WTRU, at the gNB or base station, or at both the WTRU and the gNB or base station. Otherwise, the WTRU may determine to deactivate the AI / ML model.

[0178] For example, using WTRU capabilities, the WTRU may determine or be configured to activate the AI / ML model if one or more WTRU capabilities (e.g., processing time, antenna switching time, BWP switching time, etc.) are met. Otherwise, the WTRU may determine to deactivate the AI / ML model.

[0179] This document provides AI / ML model activation / retraining / deactivation / fallback options. One or more of the following configurations may be used for CSI / beam reporting configurations. The WTRU may be configured with one or more CSI reporting configurations. In addition, the WTRU may be configured with one or more beam reporting configurations. The CSI reporting configuration may include one or more of the following: reporting configuration type (e.g., periodic, semi-persistent on PUCCH, semi-persistent on PUSCH, or aperiodic); reporting quantity (e.g., CRI-RI-PMI-CQI, CRI-RI-i1, CRI-RI-i1-CQI, CRI-RSRP, SSB-Index-RSRP, CRI-RI-LI-PMI-CQI, CRI-SINR, SSB-Index-SINR); reporting frequency configuration; CQI format indicator, such as wideband CQI or subband CQI; PMI format indicator, such as wideband PMI or subband PMI; CSI reporting band; time limit for channel measurement; time limit for interference measurement; codebook configuration; group-based beam reporting; CQI table; subband size; non-PMI port indication; reporting time slot configuration / offset list; CSI reporting period and offset; one or more PUCCH resources for CSI reporting; port index; or any or all of these combinations.

[0180] One or more of the following configurations may be used for measurement configurations for CSI / beam reporting. The WTRU may be configured with one or more CSI measurement configurations. In addition, the WTRU may be configured with one or more beam measurement configurations. The CSI measurement configuration may include one or more of the following: RS for channel measurement; RS for interference measurement (zero power or non-zero power); report trigger size; non-periodic trigger state list; semi-persistent trigger state list on PUSCH; associated CSI resource configuration; associated CSI report configuration; or a combination of any of these. Similar parameters may be included in the beam measurement configuration.

[0181] One or more of the following configurations may be used for CSI resource configuration. A WTRU may be configured with one or more CSI resource configurations. A CSI resource configuration may include one or more of the following: a CSI resource configuration ID; one or more RS resource sets for channel measurement; one or more RS resource sets for interference measurement; bandwidth portion ID; or resource type, such as aperiodic, semi-persistent, or periodic.

[0182] In an example solution, the WTRU may activate / apply the AI / ML model, deactivate the AI / ML model, update / retrain the AI / ML model, or trigger a process for selecting one or more new beams. The activation of the AI / ML model may include one or more of the following: activation of one or more RS resources / resource sets associated with the AI / ML model; activation of one or more CSI reporting configurations associated with the AI / ML model; activation of one or more measurement configurations associated with the AI / ML model; activation of one or more CSI resource configurations associated with the AI / ML model; resetting / starting one or more counters associated with the AI / ML model; resetting / starting one or more timers associated with the AI / ML model.

[0183] Deactivation of the AI / ML model may include one or more of the following: deactivation of one or more RS resources / resource sets associated with the AI / ML model; deactivation of one or more CSI reporting configurations associated with the AI / ML model; deactivation of one or more measurement configurations associated with the AI / ML model; deactivation of one or more CSI resource configurations associated with the AI / ML model; resetting one or more counters associated with the AI / ML model; resetting one or more timers associated with the AI / ML model.

[0184] The process for updating / retraining the AI / ML model or associated parameters / weights may include one or more of the following: transmitting a request / indication to update the AI / ML model or associated parameters / weights; resetting / starting one or more counters associated with the process; resetting / starting one or more timers associated with the process; updating the AI / ML model and associated parameters / weights; applying / using the updated AI / ML model and associated parameters / weights; or selecting one or more RS / beams based on the updated AI / ML model and associated parameters / weights. The WTRU may select one or more RS / beams based on quality. For example, the WTRU or base station or gNB may select one or more RS / beams with the best quality.

[0185] The process for updating / retraining the AI / ML model or associated parameters / weights may also include one or more of the following: measuring one or more selected RS / beams based on the updated AI / ML model and associated parameters / weights; indicating one or more selected RS / beams; or if the process is unsuccessful, indicating deactivation of the AI / ML model and / or falling back to a conventional beam management mechanism. In an example solution for indicating one or more selected RS / beams, the WTRU or base station or gNB may indicate one or more selected beams RS / beams. For example, if the measured quality of one or more selected RS / beams is greater than or equal to (≥) a threshold, the WTRU and / or base station or gNB may indicate one or more selected RS / beams.

[0186] Example solutions include: if the process is unsuccessful, indicating deactivation of the AI / ML model and / or fallback to the conventional beam management mechanism. For example, the WTRU may determine that the process is unsuccessful if one or more of the following conditions are met: timer (if the timer associated with the process expires, the WTRU may determine that the process is unsuccessful); counter (when the WTRU measures the candidate RS and / or the measured quality of the candidate RS is less than one or more first thresholds, the WTRU may increase the counter; if the counter is greater than a second threshold, the WTRU may determine that the process is unsuccessful); or measured quality (if the measured quality of one or more candidate beams < threshold, the WTRU may determine that the process is unsuccessful).

[0187] The process for selecting one or more new beams may include one or more of the following: triggering / requesting one or more candidate beam resources; resetting / starting one or more counters associated with the process; resetting / starting one or more timers associated with the process; monitoring / measuring candidate beams / RS; selecting one or more RS / beams; indicating one or more selected beams; or if the process is unsuccessful, indicating deactivation of the AI / ML model and / or fallback to conventional beam management mechanisms. In the example of selecting one or more RS / beams, the WTRU may select one or more beams based on quality. For example, the WTRU or base station or gNB may select one or more RS / beams with the best quality.

[0188] In an example regarding indicating one or more selected beams, the WTRU may indicate the one or more selected beams to the base station or gNB. In addition, the WTRU may indicate the one or more beams by sending one or more UL resources. The one or more UL resources may be one or more of: PRACH (e.g., the WTRU may send one or more PRACHs (e.g., in PRACH resources associated with the one or more selected beams)); PUCCH (e.g., the WTRU may indicate one or more RS indices and / or beam indices (e.g., as part of CSI) by using one or more PUCCHs (e.g., in PUCCH resources associated with the process or one or more selected beams); or PUSCH (e.g., the WTRU may indicate one or more RS indices and / or beam indices (e.g., as part of CSI) by using one or more PUSCHs). In addition, the WTRU may receive an acknowledgment from the base station or gNB. For example, the WTRU may receive one or more PDCCHs in, for example, one or more CORESETs / search spaces associated with the process.

[0189] In another example regarding indicating one or more selected beams, the base station or gNB may indicate the one or more selected beams to the WTRU, for example, via one or more of RRC, MAC CE, and DCI. In addition, the WTRU may receive an indication based on one or more of: a TCI state; or a beam index. In the example of receiving a TCI state, the WTRU may receive an indication of one or more TCI states associated with the selected beam. In the example of receiving a beam index, the WTRU may receive an indication of one or more beam indexes associated with the selected beam.

[0190] In the example of indicating that the AI / ML model is deactivated and / or falls back to the conventional beam management mechanism if the process is unsuccessful, the WTRU may determine that the process is unsuccessful if one or more of the following conditions are met: timer, counter, or measured quality. For example, if a timer associated with the process times out, the WTRU may determine that the process is unsuccessful. In the counter example, when the WTRU measures a candidate RS and / or the measured quality of the candidate RS is less than one or more first thresholds, the WTRU may increase the counter. If the counter is greater than a second threshold, the WTRU may determine that the process is unsuccessful. In the measured quality example, if the measured quality of one or more candidate beams is less than (<) a threshold, the WTRU may determine that the process is unsuccessful.

[0191] Activation of AI / ML models, deactivation of AI / ML models, update / retraining of AI / ML models and associated parameters / weights, and triggering of a new beam selection process may be based on one or more of the following: base station or gNB indication, or WTRU indication. In an example solution, the WTRU may receive an indication from a base station or gNB to activate / deactivate one or more AI / ML models, update one or more AI / ML models and associated parameters, or trigger a new beam selection process, such as one or more of RRC signaling, MAC CE, or DCI. The indication may be based on one or more of the following: a display indication; or an indication based on one or more configurations associated with one or more AI / ML models.

[0192] In an example of an explicit indication, the WTRU may receive an indication to activate / deactivate or trigger an update process for one or more AI / ML models or trigger a beam selection process. The explicit indication may include one or more of the following.

[0193] For example, the WTRU may receive an indication of a procedure type. For example, the WTRU may receive one or more of activation, deactivation, update, or new beam selection.

[0194] The indication may include an indication of triggering an update process of the AI / ML model. For example, a bit may indicate triggering an update process of the AI / ML model. For example, if the bit is "1", the update process may be triggered. If the bit is "0", the update process may not be triggered.

[0195] The indication may include an indication of triggering a new beam selection process. For example, one bit may indicate triggering a new beam selection process. For example, if the bit is "1", the new beam selection process may be triggered. If the bit is "0", the new beam selection process may not be triggered.

[0196] The indication may include an AI / ML model ID. For example, the WTRU may receive one or more AI / ML model IDs to be activated / deactivated / updated. If new beam selection is triggered, the explicit indication may not include an AI / ML model ID.

[0197] The indication may include a bitmap of AI / ML models. For example, each bit of the bitmap may be associated with each AI / ML model. For example, if the bit is "1", the AI / ML model associated with the bit may be activated. If the bit is "0", the AI / ML model associated with the bit may be deactivated. If new beam selection is triggered, the explicit indication may not include a bitmap of AI / ML models.

[0198] In an example, the indication may be based on an indication of one or more configurations associated with one or more AI / ML models. For example, the WTRU may receive an indication of activation / deactivation / update for one or more configurations. For example, if the WTRU receives an indication of activation for a first set of configurations, the WTRU may activate the first set of AI / ML models associated with the first set of configurations. If the WTRU receives an indication of deactivation for a second set of configurations, the WTRU may deactivate the second set of AI / ML models associated with the second set of configurations. If the WTRU receives an indication of an update for a third set of configurations, the WTRU may update the third set of AI / ML models associated with the third set of configurations. If the WTRU receives an indication of new beam selection for a fourth set of configurations, the WTRU may select one or more new beams for the third set of AI / ML models associated with the third set of configurations. The one or more configurations may be one or more of: CSI reporting configuration; measurement configuration; CSI resource configuration; RS resource configuration; and / or RS resource set configuration.

[0199] The following includes examples of activation of AI / ML models, deactivation of AI / ML models, update / retraining of AI / ML models and associated parameters / weights, and triggering of new beam selection procedures based on WTRU indication. In an example solution, the WTRU may indicate a preferred mode, such as one or more of activation, deactivation, update, and new beam selection, to the base station or gNB. The indication may be based on one or more of: explicit indication for all AI / ML models, indication per AI / ML model, indication per configuration, or quality measurement.

[0200] The WTRU may explicitly indicate a preferred mode for all AI / ML models. For example, one information bit may be used to indicate activation / deactivation. For example, 1 may indicate activation of all AI / ML models or activation of an AI / ML mode, and 0 may indicate deactivation of all AI / ML models or deactivation of an AI / ML mode. For example, one bit of information may be used to indicate an update. For example, 1 may indicate an update of all AI / ML models, and 0 may indicate that no AI / ML models have been updated. For example, one information bit may be used to trigger a new beam selection process. For example, 1 may indicate selection of one or more new beams, new RSs, or both for all AI / ML models, and 0 may indicate that one or more new beams / RSs are not selected.

[0201] The WTRU may indicate a preferred mode for each AI / ML model or for each AI / ML model. For example, 1 may indicate activation of the AI / ML model associated with the indication, and 0 may indicate deactivation of the AI / ML model associated with the indication. For example, 1 may indicate an update of the AI / ML model associated with the indication, and 0 may indicate that the AI / ML model associated with the indication has not been updated. For example, 1 may indicate selection of one or more new beams, new RSs, or both for the AI / ML model associated with the indication, and 0 may indicate not selecting one or more new beams, new RSs, or both for the AI / ML model associated with the indication.

[0202] The WTRU may indicate each configuration or a preferred mode for each configuration. For example, 1 may indicate activation of the AI / ML model associated with the configuration, and 0 may indicate deactivation of the AI / ML model associated with the configuration. For example, 1 may indicate an update of the AI / ML model associated with the configuration, and 0 may indicate that the AI / ML model associated with the configuration has not been updated. For example, 1 may indicate selection of one or more new beams, new RSs, or both for the AI / ML model associated with the indication, and 0 may indicate that one or more new beams, new RSs, or both are not selected for the AI / ML model associated with the configuration. The configuration may be one or more of the following: CSI report configuration; measurement configuration; CSI resource configuration; RS resource configuration; or RS resource set configuration.

[0203] In an example solution, the WTRU may activate / deactivate / update one or more AI / ML models or trigger a new beam selection process based on one or more measured qualities. In an example solution, the process may be based on a threshold and quality measurement for each process, such as the quality reported to the base station or gNB. For example, if the measured quality is greater than or equal to (≥) the threshold, the WTRU may indicate, determine, or both indicate and determine the activation of the AI / ML model. If the measured quality is less than (<) the threshold, the WTRU may indicate, determine, or both indicate and determine the deactivation of the AI / ML model.

[0204] For example, if the measured quality is greater than or equal to (≥) a threshold, the WTRU may indicate, determine, or both indicate and determine that the AI / ML model has not been updated. If the measured quality is less than (<) a threshold, the WTRU may indicate, determine, or both indicate and determine an update of the AI / ML model. For another example, if the measured quality is greater than or equal to (≥) a threshold, the WTRU may indicate / determine that there is no new beam selection for the AI / ML model. If the measured quality is less than (<) a threshold, the WTRU may indicate / determine a new beam selection for the AI / ML model.

[0205] In an example solution, the process may be based on two or more thresholds and a quality measurement. For example, if the measured quality is greater than or equal to (≥) a first threshold, the WTRU may indicate, may determine, or may both indicate and determine the activation of the AI / ML model. If a second threshold is less than (<) the measured quality, which may be less than (<) the first threshold, the WTRU may trigger / indicate / determine a new beam selection process. If the measured quality is less than (<) the second threshold, the WTRU may indicate, may determine, or may both indicate and determine the deactivation of the AI / ML model.

[0206] For example, if the measured quality is greater than or equal to (≥) a first threshold, the WTRU may indicate, may determine, or both indicate and determine activation of the AI / ML model. If a second threshold is less than (<) the measured quality, which may be less than (<) the first threshold, the WTRU may trigger / indicate / determine an AI / ML update procedure. If the measured quality is less than (<) the second threshold, the WTRU may indicate, may determine, or both indicate and determine deactivation of the AI / ML model.

[0207] In an example solution, the process may be based on two or more quality measurements and two or more thresholds. For example, if the first measured quality (e.g., RSRP, RSRQ, SINR, MCS, or CQI) is greater than or equal to (≥) a first threshold and the second measured quality (e.g., LOS probability) is greater than or equal to (≥) a second threshold, the WTRU may indicate, determine, or both indicate and determine the activation of the AI / ML model. If the first measured quality (e.g., RSRP, RSRQ, SINR, MCS, or CQI) is less than (<) the first threshold and the second measured quality (e.g., LOS probability) is greater than or equal to (≥) the second threshold, the WTRU may indicate, determine, or both indicate and determine the update of the AI / ML model. If the first measured quality (e.g., RSRP, RSRQ, SINR, MCS, or CQI) is less than (<) a first threshold and the second measured quality (e.g., LOS probability) is less than (<) a second threshold, the WTRU may indicate, may determine, or may both indicate and determine deactivation of the AI / ML model, triggering a new beam selection process, or both.

[0208] If the WTRU reports two or more measured qualities, the WTRU may indicate activation / deactivation / triggering of a new beam selection process based on one or more of the following: an indication of each measured quality, an indication of all measured qualities, or both. The WTRU may indicate activation / deactivation / triggering of a new beam selection process based on the measured quality. The WTRU may indicate activation / deactivation / triggering of a new beam selection process based on all measured qualities. The WTRU may determine activation / deactivation / triggering of a new beam selection process based on one or more of the following. For example, the WTRU may determine activation / deactivation / triggering of a new beam selection process based on an average value. In addition, in an example where the WTRU may average all measured qualities, the WTRU may determine activation / deactivation / triggering of a new beam selection process, and if the average quality is greater than (≥) a threshold, the WTRU may indicate activation. In addition, the WTRU may determine activation / deactivation / triggering of a new beam selection process based on multiple measured qualities greater than (≥) a threshold. Additionally, the WTRU may determine to activate / deactivate / trigger a new beam selection process, where if the number of measured qualities is greater than or equal to (≥) a threshold, the WTRU may indicate activation.

[0209] In an example solution, the WTRU may receive a confirmation of the WTRU indication / determination. For example, the WTRU may receive a PDCCH in one or more CORESETs / search spaces associated with the WTRU indication. For another example, the WTRU may receive a confirmation message via one or more of RRC signaling, MAC CE, or DCI.

[0210] Examples of methods for determining or obtaining the accuracy of an AI / ML model are provided herein. The phrases "accuracy of an AI / ML model" and "effectiveness of an AI / ML model" may be used interchangeably and still be consistent with the examples provided herein. The phrases "frequency region" or "frequency range" may be used interchangeably and still be consistent with the examples provided herein. The terms "ML," "AI / ML," and "AIML" may be used interchangeably and still be consistent with the examples provided herein.

[0211] The WTRU may determine the effectiveness or accuracy of the AI / ML model. The WTRU may be configured with resources on which measurements are performed to determine the effectiveness of the AI / ML model. The resources may be in one or more frequency regions. For example, the AI / ML model may obtain input from a first frequency region to determine behavior in a second frequency region. To determine the effectiveness of the AI / ML model, the WTRU may be configured with measurement resources in the first frequency region or the second frequency region.

[0212] The WTRU may determine whether the second frequency region behavior determined based on the AI / ML model matches the second frequency region behavior determined based on the measurement resources in the second frequency region. In one example, the WTRU may be configured with a periodic or sparse reference signal in the second frequency region to perform a legacy method (e.g., a non-AI / ML based method) and compare it to the output of the AI / ML model, which may be based on the reference signal in the first frequency region.

[0213] The validity or accuracy of the AI / ML model may be determined by at least one of: execution of the associated function, statistical performance of the associated function, transmission performance in a frequency region of the function associated with the AI / ML model, comparison of legacy results with AI / ML results, measurements and / or fault counters. In an example, the validity or accuracy of the AI / ML model may be determined by execution of the associated function.

[0214] For example, the AI / ML model can be used to support or provide feedback or enable functionality. The functionality may include one or more of the following: beam management, CSI reporting, RLM, beam failure detection, persistent listen-before-talk (LBT) failure, mobility, cell (re)selection, random access, or measurement reporting. The WTRU may determine the effectiveness of the AI / ML model based on the execution of the associated functionality. The WTRU may be configured with metrics to determine the execution of the associated functionality. For example, the WTRU may be configured with an AI / ML model that supports beam management. The WTRU may be configured with metrics such as best beam determination. If the AI / ML model determines the best beam, the AI / ML model may be considered valid.

[0215] Effectiveness metrics associated with beam management may include at least one of the following. These metrics may include best beam predictions. For example, the AI / ML model predicts the best beam. These metrics may include predicted beam measurements within a threshold offset from the best beam. In one example, the threshold may be configurable. As another example, the threshold offset can be used to compare RSRP measurements. These metrics may include N predicted best beams that match at least M actual best beams. These metrics may include a rate of beam failure detection.

[0216] In an example, the effectiveness or accuracy of an AI / ML model may be determined by the statistical performance of the associated function. For example, if the WTRU satisfies the metric of the associated function at a certain percentage of times within a time period, the WTRU may be considered an AI / ML model.

[0217] In an example, the effectiveness or accuracy of the AI / ML model may be determined by the execution of the transmission in the frequency region of the function associated with the AI / ML model. For example, the WTRU may determine the effectiveness of the AI / ML model with the associated function in the second frequency region based on the execution of the transmission in the second frequency region. The execution of the transmission may be determined based on at least one of: BLER, assumed PDCCH BLER, HARQ-ACK / negative ACK (NACK) performance or ratio, latency, throughput, spectral efficiency, outage probability, etc.

[0218] In an example, the validity or accuracy of the AI / ML model may be determined by comparing legacy results (e.g., non-AI / ML based results) with the AI / ML results. For example, the WTRU may perform measurements in the frequency region of the associated function to compare with the output of the AI / ML model. The WTRU may determine the validity of the AI / ML model based on the difference between the output of the AI / ML model and the output of the associated function based on the measurements in the applicable frequency region (e.g., using legacy methods).

[0219] In an example, the validity or accuracy of the AI / ML model may be determined by measurements. For example, the WTRU may determine the validity based on measurements performed on the RS. These measurements may include at least one of the following: RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, channel occupancy (CO), LOS probability, Doppler drift, Doppler spread, average delay, or delay spread. The WTRU may compare at least one measurement with one or more thresholds to determine the accuracy or validity of the model.

[0220] In an example, the effectiveness or accuracy of an AI / ML model can be determined by a fault counter. The WTRU can count the number of times the AI / ML model fails. For example, the WTRU can count the number of times the associated functions of the AI / ML model fail. As another example, the WTRU can count the number of prediction deviations that exceed a (possibly configurable) threshold. The counter can be valid for a period of time. At the end of that period, the counter can be reset. The period can be fixed or configurable. When a fault occurs, the WTRU can start or restart the period.

[0221] When N (where N is configurable) outputs of the AI / ML model are considered accurate (e.g., the prediction is within a configurable threshold of the actual value), the WTRU can stop a period or can reset the counter. When a period elapses, the WTRU can determine the accuracy or effectiveness of the AI / ML model based on the counter value. As another example, the WTRU can determine the accuracy or effectiveness of the AI / ML model based on a fault counter reaching a specific value. For example, if the fault counter reaches X, the WTRU can consider the model invalid.

[0222] The WTRU can report the effectiveness of the AI / ML model to the base station or gNB. The WTRU can report one of two states: valid or invalid. As another example, the WTRU can report an accuracy metric of the AI / ML model. The accuracy metric can indicate the effectiveness value of the AI / ML model. The effectiveness value can provide an accuracy parameter of the AI / ML model.

[0223] The effectiveness of the AI / ML model can be reported in a PUCCH resource, a PUSCH resource, a RACH, an RRC message, or a MAC CE. A new message can be used to report the effectiveness of the AI / ML model. As another example, the effectiveness of the AI / ML model can be implicitly reported, for example, by the WTRU indicating a fault in an associated function (e.g., beam failure detection). Such a fault report can include a new element indicating that the cause of the fault is due to the AI / ML model no longer being effective.

[0224] The WTRU can request resources, such as a DL reference signal, to determine the effectiveness of the AI / ML model. The WTRU can indicate to the base station or gNB the type of resource required, the AI / ML model (e.g., the AI / ML model index), and the associated function.

[0225] The WTRU can be configured to determine the accuracy of the AI / ML model. When the WTRU can determine the accuracy of the AI / ML model, the configuration can include a set of periodic time instances. The configuration can also include, for example, reporting resources associated with one or more of the periodic time instances such that the WTRU can report the accuracy of the AI / ML model.

[0226] The WTRU may also be dynamically triggered to determine and possibly report the accuracy of the AI / ML model. The WTRU may receive a trigger in a DL signal such as a DCI, MAC CE, or RRC command. The WTRU may be configured with one or more triggers to determine the accuracy of the AI / ML model.

[0227] The WTRU may be triggered to determine the accuracy of the AI / ML model by at least one of: time, a timer, reception of an RS signal, an indication from a base station or gNB, execution of a function associated with the AI / ML model, execution of transmission in a frequency region associated with the function associated with the AI / ML model, beam failure detection or radio link failure determination, activation or deactivation of a cell, change of BW, change of cell, measurement and / or failure counters.

[0228] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model over time. For example, the WTRU may be triggered to determine the accuracy of the AI / ML model, for example, at a specific time instance (e.g., a time slot, subframe, or symbol).

[0229] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model through a timer. For example, the WTRU may be triggered to determine the accuracy of the AI / ML model when the timer expires or after a set number of time instances or time slots or subframes or symbols. The WTRU may start or restart the timer after determining the accuracy of the AI / ML model. The WTRU may start or restart the timer based on signaling from the base station or gNB. The WTRU may start or restart the timer based on the execution of a function associated with the AI / ML model. For example, if the AI / ML model is used for beam prediction, the WTRU may start or restart the timer if the prediction is determined to be within the required range.

[0230] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model through the reception of the RS signal. For example, the WTRU may be triggered to determine the accuracy of the AI / ML model based on the reception of the RS that is expected to be used for the AI / ML model accuracy determination.

[0231] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by performing a function associated with the AI / ML model. For example, if the AI / ML model is used for beam prediction, if the prediction is determined to be outside of an acceptable range, the WTRU may be triggered to determine the accuracy of the AI / ML model. Other examples of the performance of functions associated with the AI / ML model from the portion of determining the validity or accuracy of the AI / ML model may be applicable here.

[0232] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by performing a transmission in a frequency region with the function associated with the AI / ML model. For example, the WTRU may be triggered to determine the effectiveness or accuracy of the AI / ML model with the associated function in a second frequency region based on the performance of the transmission in a second frequency region. The performance of the transmission may be determined based on at least one of: BLER, assumed PDCCH BLER, HARQ-ACK / NACK performance or ratio, latency, throughput, spectral efficiency, outage probability, etc.

[0233] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by a change of cell. In one example, the change of cell may be from a cell handover (HO). In another example, the change of cell may be from a cell selection. In another example, the change of cell may be from a cell reselection.

[0234] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by measuring. For example, the WTRU may be triggered to perform a determination of the accuracy of the AI / ML model based on measurements of the RS. These measurements may include at least one of: RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, CO, LOS probability, Doppler shift, Doppler spread, average delay, or delay spread.

[0235] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model via a failure counter. The WTRU may count the number of times the AI / ML model fails. For example, the WTRU may count the number of times an associated function of the AI / ML model fails. As another example, the WTRU may count the number of times a prediction deviation exceeds a (possibly configurable) threshold. The counter may be valid for a time period. At the end of the time period, the counter may be reset. The time period may be fixed or configurable. When a failure occurs, the WTRU may start or restart the time period.

[0236] When N (where N is configurable) outputs of the AI / ML model are deemed accurate (e.g., the prediction is within a configurable threshold of the actual value), the WTRU may stop for a time period or may reset the counter. When a time period elapses, the WTRU may be triggered to perform a determination of the accuracy of the AI / ML model based on the counter value. As another example, the WTRU may be triggered to perform a determination of the accuracy or effectiveness of the AI / ML model based on a failure counter reaching a certain value. For example, if the failure counter reaches X, the WTRU may be triggered to perform a determination of the accuracy of the AI / ML model.

[0237] In an example, when determining the accuracy of the AI / ML model, the WTRU may engage in the following behavior. The WTRU may determine appropriate behavior based on the determined accuracy or effectiveness of the AI / ML model. The WTRU behavior may depend on the method used to determine the accuracy or effectiveness of the AI / ML model. The WTRU behavior may be determined based on one or more of the measurements or the measurements compared to a threshold, or a combination thereof. The measurements may be triggered based on the determination of the accuracy or effectiveness of the AI / ML model. The measurements may include at least one of the following: BLER, assumed PDCCH BLER, RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, CO, LOS probability, Doppler drift, Doppler spread, average delay, or delay spread. The WTRU behavior may include at least one of the following: continue to use the AI / ML model, select a secondary output of the AI / ML model, update or train the AI / ML model, and / or stop using the AI / ML model and use or fall back to the old method of the associated functionality.

[0238] Examples herein include situations where the WTRU behavior includes continuing to use the AI / ML model. For example, if the AI / ML model is deemed accurate or valid, the WTRU may continue to use it. If the accuracy of the AI / ML model is greater than a threshold, the WTRU may consider the AI / ML model to be accurate.

[0239] Examples herein include situations where WTRU behavior includes selecting a secondary output of an AI / ML model. For example, if the AI / ML model is deemed accurate on average but incorrect for a particular result, the WTRU may select a secondary output if available.

[0240] For example, if for the predicted beam resources in FR2, the LOS probability is above a first threshold (e.g., LOS_th) and the derived CQI is below a corresponding threshold (e.g., CQI_th), the WTRU may update or retrain the AI / ML model. As another example embodiment, if for the predicted beam resources in FR2, the LOS probability is below a first threshold (e.g., LOS_th) and the derived CQI is below a corresponding threshold (e.g., CQI_th), the WTRU may determine, for example based on the determined LOS probability, to select a secondary output of the AI / ML model or fall back to legacy operation.

[0241] The ML model for beam selection and / or prediction may be at the WTRU and / or the network. In a first exemplary solution where the ML model is at the WTRU, the WTRU may be configured with one or more use cases, which may include, for example, one or more subsets of use cases for which the ML model may be used. The WTRU may also be configured to make and possibly report measurements to determine whether the ML model is suitable for use. The use cases / parameters that determine whether the WTRU may use the ML model may include any one or more of the following: indication / probability of LOS / NLOS, change in indication / probability of LOS / NLOS, signal-to-noise ratio (SNR) / SINR measurement / calculation, additional channel measurements or changes in channel measurements, number of FR1 beams and FR2 beams supported, change in bandwidth part (BWP), WTRU capabilities, network assistance, antenna panel configuration at the WTRU, other antenna parameters, and / or model validity / accuracy.

[0242] Examples provided herein include the WTRU using an indication / probability of LOS / NLOS to determine whether to use an ML model. In one example, a base station or gNB may configure multiple beams in a first frequency range (e.g., FR1) to find the beam with the best LOS probability such that the chance of exceeding a pre-configured LOS probability is higher. In such a scenario, the WTRU may use only the FR1 beam with the best LOS probability (such as above a pre-configured threshold) as input to the ML model.

[0243] In one example, the WTRU may determine that the LOS indication is negative or that the LOS probability is below a pre-configured threshold for any of the CSI-RS resources. The WTRU may determine to deactivate the AI / ML model and resort to legacy beam management procedures. In one example, the WTRU may make this determination based on historical poor performance of the ML model in NLOS scenarios that the WTRU has previously observed.

[0244] Examples provided herein include the WTRU using a change in LOS / NLOS indication / probability to determine whether to use the ML model. In one example, the WTRU may determine to activate / deactivate the ML model based on a change in LOS / NLOS conditions. For example, if the LOS indication changes from "1" to "0" to indicate a loss of LOS, the WTRU may determine to deactivate the ML model and switch back to the legacy beam management process.

[0245] As another example, the WTRU may measure a sudden drop in the LOS / NLOS probability. A drop below a threshold pre-configured by the WTRU or base station or gNB may trigger the WTRU to deactivate the use of the ML model and switch to the legacy beam management process.

[0246] Examples provided herein include the WTRU using SNR / SINR measurements / calculations to determine whether to use the ML model. The WTRU may be configured to make / calculate SNR / SINR measurements, such as SS-SINR, CSI-SINR. The WTRU may determine to deactivate the ML model for FR2 beam selection based on a drop in the SNR / SINR measurement / calculation below a configured or pre-configured threshold. The threshold may also be based on a drop / difference in SNR / SINR values ​​rather than an absolute value, such that a drop / difference exceeding the threshold may be a trigger for the WTRU to switch to a legacy process, which in one example may be a legacy beam management process.

[0247] As another example, the WTRU may be configured with an SNR / SINR range, where the use of a second frequency range (e.g., FR2, ML selection / prediction model) provides the best output for beam prediction based on measured input in a first frequency range (e.g., FR1). Measurement / calculation of SNR / SINR outside of the pre-configured range may trigger the WTRU to deactivate the ML model and revert to a legacy framework, which in one example may be a legacy beam management framework.

[0248] Examples provided herein include the WTRU using additional channel measurements, such as channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc., or changes in channel measurements to determine whether to use the ML model. The WTRU may perform additional channel measurements, such as channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc. The measurements of channel conditions and / or changes in the measurements may constitute a trigger to use or not use the ML model.

[0249] In one example, a WTRU measuring and recording a large channel coherence time (such as exceeding a configured or pre-configured threshold) may indicate a slow fading channel, causing the WTRU to activate an ML model that predicts the best FR2 beam based on the FR1 beam information / measurements. As another example, a channel coherence time below a pre-configured threshold may result in poor performance of the FR2 prediction model due to fast fading conditions. In this case, the WTRU may deactivate the model and resort to conventional methods of FR2 beam selection.

[0250] In one example, the WTRU may measure a sudden change in any of the channel parameters (e.g., channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc.). In one example, a change in the channel coherence time from a large measured value to a smaller value may indicate a sudden degradation in the channel condition, such that the WTRU may determine that the channel condition is no longer valid / stable enough to use the FR2 beam ML predictor, and therefore revert / fall back to the legacy method of FR2 beam selection.

[0251] In one example, the WTRU may be configured with a corresponding range for any one of channel parameters (e.g., channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc.) such that when the channel measurements are within the configured / pre-configured / determined range, the WTRU may determine to activate only the FR2 beam selection / prediction ML model.

[0252] Examples provided herein include the WTRU using a supported number of FR1 beams and FR2 beams to determine whether to use the ML model. The WTRU may activate / deactivate the ML model based on the number of supported beams in the first frequency range and the second frequency range. In one example, a lower number of supported beams in the second frequency range (e.g., FR2) may trigger the WTRU to deactivate the beam ML model predicted for the second frequency range (e.g., FR2) because the WTRU may determine that in the case of a lower number of supported beams, legacy measurement methods select the best FR2 beam. In such a scenario, the minimum number of supported beams in the second frequency range (e.g., FR2) that would trigger the use of the ML model may be determined by the WTRU through historical data (e.g., past verification of the ML model accuracy evaluated relative to the number of supported FR2 beams).

[0253] Examples provided herein include the WTRU using a change in the BWP to determine whether to use the ML model. The WTRU may determine to deactivate the ML model after a change / switch in the BWP. In one example, when the WTRU changes / switches the BWP due to a timer expiration, the WTRU may determine that the model is no longer suitable for the new BWP.

[0254] Examples provided herein include the WTRU using the WTRU capabilities to determine whether to use the ML model. The WTRU may determine to use the ML model based on the WTRU capabilities. In one example, a WTRU with reduced capabilities and / or a WTRU without ML capabilities may not be configured with any ML models and may have to use legacy methods, such as legacy methods of beam selection. As another example, a WTRU with lower capabilities may be able to use the ML model for current beam selection / determination in the second frequency range (e.g., FR2) based on beam measurements in the first frequency range (e.g., FR1), but may not be able to predict future beams based on current measurements because the WTRU makes fewer measurements (e.g., compared to the larger number of measurements that a WTRU with four (4) receive antennas would make). In one example, a WTRU with lower capabilities may be a WTRU with two (2) receive antennas compared to four (4) receive antennas.

[0255] The examples provided herein include a WTRU using network assistance to determine whether to use an ML model. The network may transmit assistance to the WTRU based on an indication of when the WTRU is able to activate its ML model. During registration, the network may transmit a "WTRU Capability Enquiry" to the WTRU to specify which capability the WTRU wants to report. One such capability may be whether the WTRU is ML capable. The indication may be a single bit / flag type indicator where the WTRU will report "1" if the WTRU is configured with an ML model, otherwise the WTRU will report "0", or the WTRU may have additional parameters reported, such as the SNR range for which the ML model is activated at the WTRU. Based on measurements by the base station or gNB (such as based on channel conditions), assistance may be provided to the WTRU regarding when to activate the corresponding ML model.

[0256] The examples provided herein include the WTRU using the antenna panel configuration at the WTRU to determine whether to use the ML model. In one example, the antenna panel configuration between antenna ports in a first frequency range and a second frequency range may be incompatible, such that measurements made in the first frequency range (e.g., FR1) may not result in the selection of the best beam in the second frequency range (e.g., FR2). For example, the same QCL Type D assumptions may not exist between antenna ports and / or panels for different frequency ranges, such as on the WTRU side. The WTRU may determine to deactivate the ML prediction model and revert / fall back to a legacy process, such as a legacy beam selection process.

[0257] Examples provided herein include the WTRU using other antenna parameters to determine whether to use the ML model. The WTRU may determine to activate / deactivate / retrain its ML model based on other antenna parameters, such as one or more of the boresight of the antenna array at the WTRU and / or the base station or gNB, the beam direction of the antenna, or the antenna array configuration for the first frequency range and / or the second frequency range. In one example, a change in the boresight of the antenna array or the beam direction of the antenna may trigger the WTRU to deactivate its ML model, for example, because the model may need to be retrained for the new beam direction.

[0258] The examples provided herein include the WTRU using model validity / accuracy to determine whether to use the ML model. The WTRU may activate / deactivate the ML model based on the model validity / accuracy, which the WTRU may determine by any method as explained elsewhere in the embodiments and examples herein. The activation / deactivation of the ML model may be triggered by any trigger as explained elsewhere in the embodiments and examples herein.

[0259] In any use case involving a determination that one method of beam selection / prediction is no longer valid, resulting in another method of beam selection / prediction (e.g., switching from an ML model to a legacy (beam management) procedure), the WTRU may be configured with a procedure for smooth transition. In one example, before the ML model is deactivated, the interim procedure may involve triggering of a time window after the WTRU determines to transition to the legacy procedure to allow time for measurements to be made / transmitted / reported to the base station or gNB, e.g., SS and / or CSI-RS measurements and / or SRS.

[0260] In an exemplary solution where the ML model is at the base station or gNB, the WTRU may provide feedback / reporting to the base station or gNB, e.g., in UCI, on the accuracy / quality of the beams selected by the base station or gNB. After the feedback from the WTRU, the base station or gNB may determine whether to keep using the ML model for beam selection / prediction, deactivate the ML model, retrain the ML, or revert / fall back to legacy / non-ML methods, such as for beam selection.

[0261] In one example, the WTRU may be configured to perform RSRP measurements on beams selected by the ML model at a base station or gNB in ​​a second frequency range (e.g., FR2), which may be based on input / reported data / information from the WTRU in a first frequency range (e.g., FR1). If the WTRU measures an RSRP value below a threshold, the WTRU may report the measurement to the base station or gNB, which may fall back to the legacy (beam management) process. In one example, the threshold may be one or more of configured, preconfigured, determined, or predetermined by the WTRU or base station or gNB.

[0262] In one example, when the ML model is used at the base station or gNB, the WTRU may be configured to perform additional measurements, particularly at the beginning of a check period, to ensure that the ML model at the base station or gNB is well calibrated. The WTRU may be configured to report all channel measurements, or only report channel measurements by the network when they are above / below a (pre-)configured / determined threshold, or only report changes in channel measurements below / above a (pre-)configured / determined threshold.

[0263] This article provides implementations and examples of dynamic retraining / updating of AI / ML models. In addition, this article provides examples of iterative retraining / updating of AI / ML models based on beam output predicted by AI / ML.

[0264] Examples of AI / ML model configuration aspects are provided herein. The WTRU may be configured with an AI / ML model to perform predictions of beam resources and / or attributes of beam resources associated with a second frequency band (e.g., FR2) based on the beam resources and / or attributes of beam resources in a first frequency band (e.g., FR1). In this document, the beam resources may consist of a TCI state for a downlink, a CSI-RS or SSB, an SRS resource, or a TCI state for an uplink. In this document, the attributes of the beam resources may be any CSI associated with the beam resources, including but not limited to CQI, PMI, RI, RSRP, SNR, SINR, LoS or NLoS information, CIR, or any statistics associated therewith, etc. In an example solution, the WTRU may apply the measured FR1 beam resource attributes as input to the AI / ML model and obtain the best beam resources and / or beam resource attributes associated with FR2 as output. In one example, the first frequency band (e.g., FR1) beam resource attributes may include one or more of RSRP, CSI, PMI, CIR, LoS probability, etc.

[0265] In an example solution, the WTRU may be configured to report the output of the AI / ML model to the base station or gNB. For example, the WTRU may measure the FR1 beam resources, apply as input to the AI / ML model, obtain the predicted RSRP of the FR2 beam resources as output from the AI / ML model, and report the predicted RSRP of the FR2 beam resources to the base station or gNB.

[0266] Examples of monitoring / verifying the accuracy of an AI / ML model are provided herein. The WTRU may be configured to determine the accuracy of the AI / ML model. The mechanism for determining the accuracy of the AI / ML model may depend on the specific functionality that the AI / ML model may support. For example, the functionality may be beam management, CSI feedback generation, beam failure and / or radio link failure determination, mobility, measurement reporting, etc. For example, the WTRU may compare predicted values ​​of FR2 beam resources, e.g., outputs from an AI / ML model, with actual values ​​of FR2 beam resources, e.g., based on measurements of the FR2 beam resources. Some example methods for determining the accuracy of an AI / ML model are described in embodiments and examples elsewhere herein.

[0267] In an example solution, the WTRU may be configured with an accuracy threshold for the operation of the AI / ML model. For example, such an accuracy threshold may be semi-statically configured via RRC configuration. In a possible example, such an accuracy threshold may be signaled as part of the AI / ML model configuration. As another example, the accuracy threshold may be signaled in a MAC control element. Possibly, such an accuracy threshold may be signaled together with the AI / ML model activation command. When the model is active, the WTRU may be configured to monitor the accuracy of the AI / ML model. Possibly, such monitoring may be performed within a pre-configured time period. In an example solution, if the accuracy of the AI / ML model does not meet the pre-configured accuracy threshold, the WTRU may autonomously deactivate the AI / ML model and send a report to the network. Possibly, the WTRU may be configured to fall back to the old method for the functions performed by the AI / ML model. Possibly, the WTRU may initiate retraining of the AI / ML model.

[0268] In an example solution, the WTRU may be configured to periodically perform retraining of the AI / ML model. For example, the WTRU may be configured to start a timer with a preconfigured value. When the timer expires, the WTRU may trigger retraining of the AI / ML model. The WTRU may restart the timer when the retraining process is completed. In another example solution, the WTRU may restart the timer when the AI / ML model retraining is successfully performed due to an event-based trigger. The periodic AI / ML model retraining timer may be configured as part of the AI / ML model configuration or as part of the AI / ML model trigger.

[0269] In another example solution, the WTRU may be configured to perform retraining of the AI / ML model based on a preconfigured trigger. In the example solution, the trigger may be based on AI / ML model accuracy. For example, the WTRU may be configured to determine the accuracy of the AI / ML model based on one or more triggers as outlined in the embodiments and examples provided elsewhere herein. If the determined accuracy is lower than a preconfigured accuracy threshold, the WTRU may trigger retraining of the AI / ML model. In another example solution, the trigger may be based on AI / ML performance. For example, the WTRU may be configured to monitor AI / ML model performance, for example, based on metrics associated with functions enabled by the AI / ML model. For example, the performance metric may include one or more of the reported BLER performance on FR2 beams above or below a threshold, HARQ-ACK or HARQ-NACK ratio, L3 (e.g., RSRP, RSSI, RSRQ, CO) or L1 measurements (e.g., RI, PMI, CQI, LI, CRI, RSRP), etc.

[0270] In another example solution, the trigger can be based on a change in a configuration aspect. For example, the configuration aspect can include RS configuration, bandwidth part configuration, SCell configuration, etc. In yet another example solution, the trigger can be based on a mobility event. For example, the mobility event can include a change in the serving cell / TRP due to HO / conditional handover (CHO) / dual active protocol stack (DAPS) handover, radio link failure (RLF), etc. In an example solution, the trigger condition can be based on a network command. For example, the WTRU can receive an implicit indication or an explicit indication in a deactivation command associated with an AI / ML model, where the deactivation command can indicate that the WTRU should retrain the AI / ML model. In a possible example, the deactivation command can additionally indicate the configuration of the resources applicable to the retraining.

[0271] This document provides examples of an iterative process for training, retraining, or both, of an AI / ML model. When one or more triggers for training, retraining, or both, of the AI / ML model are met, the WTRU can indicate to the network that the retraining process has been triggered, and additionally provide the reason for the retraining. For example, the reason can be expressed as a reason value, and different code points in the reason value can be associated with different trigger conditions. In a possible example, the indication can include an AI / ML performance and / or accuracy value. Possibly, the WTRU can include assistance information to enable the network to configure the resources for the retraining. For example, the assistance information can include one or more of the following: the number of beam resources for retraining, periodicity, density of RS in the frequency domain, etc.

[0272] The WTRU can train, retrain, or both train and retrain the AI / ML model based on configuration parameters received from a base station or gNB. For example, such configuration parameters can include one or more of the following: configuration of FR1 beam resources, configuration of FR1 beam resource attributes, configuration of FR2 beam resources, configuration of FR2 beam resource attributes, configuration including a parameterized loss function, threshold, etc. For example, the loss function can be associated with a metric that indicates the difference between the predicted FR2 beam resources and the actual FR2 beam resources as cross-entropy loss, hinge loss, squared hinge loss, mean squared error, etc.

[0273] In an example solution, the WTRU can determine that the retraining is successful based on preconfigured criteria and indicate to the base station or gNB that the retraining is complete. For example, when the accuracy of the AI / ML model after retraining is higher than a preconfigured threshold, the WTRU can determine that the retraining is complete.

[0274] In an example solution, the WTRU may be configured to iteratively retrain the model until the AI / ML model output is updated. For example, the WTRU may be configured to use the measured CSI parameters (e.g., CQI, PMI, CIR, etc.) in the retrained / updated beam prediction AI / ML model, and may determine one or more optimal FR2 beams, for example based on RSRP. When the retraining of the model has resulted in a different output (e.g., a predicted FR2 beam different from the AI / ML model before retraining), the WTRU may determine that the retraining is complete. The WTRU may be configured to indicate the success of the retraining to the network via a MAC control element, a pre-configured PUCCH resource, or a preamble resource. The WTRU may optionally indicate the accuracy value of the AI / ML model in the retraining success indication.

[0275] In an example solution, the WTRU may determine that retraining is unsuccessful based on preconfigured criteria. For example, if retraining is unsuccessful within a preconfigured time period, the WTRU may declare retraining failure. For example, if the AI / ML model accuracy does not become better than a preconfigured accuracy threshold, the WTRU may declare retraining failure. For example, if the model output before and after retraining results in the same output, such as the same predicted FR2 beam, the WTRU may declare retraining failure. For example, if the beam resources configured for training are no longer available, such as the beam resources may be released / deactivated by the network or due to obstruction or WTRU mobility, and the accuracy of the AI / ML model is still below the preconfigured accuracy threshold, the WTRU may declare retraining failure. In the event of retraining failure, the WTRU may deactivate the AI / ML model (if active) and fall back to the conventional beam management mechanism. The WTRU may be configured to send a retraining failure indication to the network via a MAC control element. In another example solution, the WTRU may send a retraining failure indication via a preconfigured PUCCH or a preconfigured preamble resource.

[0276] Figure 3 is a flow chart illustrating an example of a verification process for beam prediction based on hierarchical spatial relations. In the example shown in flow chart 300, the WTRU may perform measurements on parameters of a first set of beam resources, and the WTRU may then predict beam resources 310 from a second set of beam resources based on the measured parameters of the first set of beam resources. In an example, the base station may transmit to the WTRU using the first set of beam resources. The WTRU may then report the predicted beam resources. In an example, the WTRU may report these predicted beam resources to the base station.

[0277] In another example, the WTRU may receive one or more thresholds for accuracy checking 315. These thresholds may be used when measuring the first set of beam resources. In an example, the thresholds for accuracy checking may include one or more of a CQI threshold, an RSRP threshold, an SINR threshold, a LOS probability threshold, an assumed BLER threshold, etc. In one example, the WTRU may receive the one or more thresholds from a base station.

[0278] In addition, the WTRU may receive one or more signals on one or more channels based on beam resources in the second set of beam resources 320. In addition, the WTRU may measure one or more accuracy parameters of the one or more signals. In one example, the WTRU may receive one or more signals from a base station.

[0279] In example 325, the one or more signals may include one or more PDCCH signals. In addition, the one or more signals may include one or more PDSCH signals. For example, the one or more signals may include one or more CSI-RS. In other examples, similar signals may also be received. In addition, one or more channels may include one or more PDCCHs. In addition, one or more channels may include one or more PDSCHs. In other examples, similar channels may also be used for reception.

[0280] The WTRU may further perform a verification procedure and determine whether one or more of the measured accuracy parameters are within an acceptable range 330. If the one or more of the measured accuracy parameters are within an acceptable range, the WTRU may determine that the AI / ML model is valid 340. Furthermore, upon determining that the AI / ML model is valid, the WTRU may activate use of the AI / ML model to predict the best beam. In an additional or alternative example, upon determining that the AI / ML model is valid, the WTRU may continue use of the AI / ML model to predict the best beam. Furthermore, the WTRU may perform transmission, reception, or both based on the prediction for the determined best beam or beams 390.

[0281] If one or more of the measured accuracy parameters are not within an acceptable range, the WTRU may determine that the predicted beam is invalid 350. Additionally, the WTRU may select one or more other predicted beams from one or more other candidates. Additionally, the WTRU may restart the verification process. In one example, the beam-specific accuracy parameters may not be within an acceptable range because the measured probability of one or more LOS parameters is below a LOS threshold and one or more channel parameters are below a channel parameter threshold 355. In one example, the one or more channel parameters may include one or more CQI parameters.

[0282] If the WTRU restarts the verification process 350, and the timer has not expired 335, the WTRU may again determine whether one or more measured accuracy parameters are within an acceptable range 330. The WTRU may then continue using the verification process. If the timer has expired 375, the WTRU may fall back to legacy beam management 370.

[0283] During the verification process, if one or more measured accuracy parameters are not within an acceptable range, the WTRU may determine that the AI / ML model is invalid 360. Furthermore, the WTRU may then update the AI / ML model, retrain the AI / ML model, or perform both. Furthermore, the WTRU may predict a new beam. Furthermore, the WTRU may restart the verification process. In one example, the beam-specific accuracy parameters may not be within an acceptable range because the measured probability of one or more LOS parameters is above a LOS threshold, while one or more channel parameters are below a channel parameter threshold 365. In one example, the one or more channel parameters may include one or more CQI parameters.

[0284] If the WTRU restarts the verification process 360, and the timer has not expired 335, the WTRU may again determine whether one or more measured accuracy parameters are within an acceptable range 330. The WTRU may then continue using the verification process. If the timer has expired 375, the WTRU may fall back to legacy beam management 370.

[0285] If the WTRU falls back to legacy beam management, the WTRU may deactivate the AI / ML model and subsequently use legacy beam management to determine the best beam 370. In addition, the WTRU may perform transmission, reception, or both 390 based on the prediction for the determined best beam or beams.

[0286] Figure 4 is a flow chart illustrating an example of predicted beam management. In the example shown in flow chart 400, the WTRU may perform measurements 410 on a first set of beam resources. In an example, the base station may use the first set of beam resources to transmit to the WTRU. In an example, the first set of beam resources may be FR1 beam resources. The WTRU may then predict beam resources in a second set of beam resources 420 based on the measurements of the first set of beam resources. In an example, the second set of beam resources may be FR2 beam resources. In addition, the WTRU may report the predicted beam resources 430. In an example, the WTRU may report the predicted beam resources to the base station.

[0287] Additionally, the WTRU may use the first beam to receive one or more first signals 440. In one example, the WTRU may receive the one or more first signals from a base station. In one example, the first beam may use beam resources in the second set of beam resources.

[0288] Additionally, the WTRU may perform measurements of one or more accuracy parameters of the received one or more first signals 450. Additionally, under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable, the WTRU may transmit one or more second signals using the first beam 460. In one example, the accuracy parameters may be acceptable when the measured LOS is above a LOS threshold and the CQI is above a CQI threshold. In one example, the WTRU may send the one or more second signals to the base station.

[0289] In another example, the WTRU may receive one or more third signals using the first beam under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable. In one example, the WTRU may receive the one or more third signals from the base station.

[0290] In one example, the one or more first signals received may be PDCCH signals. In another example, the one or more first signals received may be CSI-RS.

[0291] Furthermore, in one example, using the first beam may include activating the first beam. In another example, using the first beam may include continuing to use the first beam.

[0292] In another example, the one or more accuracy parameters may include one or more line of sight (LOS) parameters. In another example, the one or more accuracy parameters may include one or more channel parameters. In addition, the one or more accuracy parameters may include one or more CQI parameters.

[0293] In an additional example, the WTRU may also activate the AI / ML model to predict one or more second beams. In an example, the one or more second beams may use beam resources in the second set of beam resources. In an additional or alternative example, the WTRU may continue to use the AI / ML model to predict the one or more second beams.

[0294] In an additional example, under a condition that one or more measured accuracy parameters of the received one or more first signals are unacceptable, the WTRU may send a request to select and report a third beam. In one example, the measured LOS may be below a LOS threshold and the measured CQI may be below a CQI threshold. In one example, the WTRU may send the request to the base station. In another example, the base station may respond to the request. Therefore, the WTRU may select the third beam. In addition, the WTRU may report the third beam to the base station.

[0295] As another example, the WTRU may send a request under the condition that one or more accuracy parameters measured for the received one or more first signals are unacceptable. In one example, the measured LOS may be above a LOS threshold and the measured CQI may be below a CQI threshold. The request sent may include a request to update the AI / ML model. The request sent may include a request to retrain the AI / ML model. In addition, the request sent may include a request to use the AI / ML model to predict a fourth beam and report the fourth beam. In one example, the WTRU may send a request to a base station. In addition, in one example, the base station may respond to the request. Therefore, the WTRU may update the AI / ML model. In an additional example or an alternative example, the WTRU may retrain the AI / ML model. In addition, the WTRU may use the AI / ML model to predict the fourth beam. In addition, the WTRU may report the fourth beam. In one example, the WTRU may report the fourth beam to the base station.

[0296] In addition, under the condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, the WTRU may fall back to the non-AI / ML beam management process to select and report the fifth beam. In an example, the measured CQI may be below the CQI threshold and a plurality of time instances may have passed since the first signal was received using the first beam. In an example, the WTRU may then select the sixth beam. In addition, the WTRU may report the sixth beam. In an example, the WTRU may report the sixth beam to the base station.

[0297] In another example, the WTRU may receive one or more fourth signals using one or more sixth beams and may measure one or more accuracy parameters of the received one or more fourth signals under a condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable. In one example, the measured LOS may be below a LOS threshold, the measured CQI may be below a CQI threshold, and a plurality of time instances may not have elapsed since the first signal was received using the first beam. In one example, the WTRU may receive one or more fourth signals from the base station.

[0298] An example of dynamic retraining / updating of an AI / ML model based on a change in the activation / deactivation set of TCI states is provided herein. The TCI state provides the QCL information necessary for the WTRU to receive various reference signals and / or channels. The WTRU may be configured with several TCI states (e.g., via RRC signaling), and a subset of the configured TCI states may be activated via signaling (e.g., MAC-CE signaling). In order to receive reference signals, channels, or both, the WTRU may select at least one TCI state from a set of activated TCI states, e.g., based on a DCI, an indication, or following a (predefined) configuration, such as when the DM-RS of the PDSCH is received using the default QCL assumption when the scheduling offset is less than (<) timeDurationForQCL. Upon receiving new signaling / indication, e.g., via MAC-CE, the WTRU may activate a new set of TCI states.

[0299] For example, a change in the set of activated TCI states may be viewed as an indication that the radio wave propagation environment has changed due to various factors, such as due to rotation, movement, or both of the WTRU, or changes in other objects in the surrounding environment. Thus, when the set of activated TCI states of the WTRU changes, the WTRU may determine to evaluate the need to retrain the AI / ML model used for beam selection and / or prediction.

[0300] When the AI / ML model for beam prediction and / or selection is trained, the WTRU may be configured and activated using a first set of TCI states via a first (e.g., MAC-CE) indication. After performing AI / ML model training, the WTRU may be activated using a second set of TCI states via a second (e.g., MAC-CE) indication. Upon receiving a second (e.g., MAC-CE) signaling indicating activation of a second set of TCI states, the WTRU may determine the need and / or evaluation for retraining the AI / ML model and indicate the need for retraining the AI / ML model to the base station or gNB. The need for retraining the AI / ML model may be reported to the base station or gNB, for example, in a PUCCH, PUSCH, RACH, RRC message, or MAC CE.

[0301] In an example solution, the WTRU may compare a first set of TCI states and a second set of TCI states and determine a level of overlap (L_overlap) between the two sets. If the L_overlap of the two sets is below a configured / pre-configured / determined threshold level, the WTRU may determine that the AI / ML model needs to be retrained. If the L_overlap is above a configured / pre-configured / determined threshold level, the WTRU may determine that the AI / ML model does not need to be retrained. The WTRU may determine and / or receive a threshold for TCI state overlap from a base station or gNB, for example, via RRC / MAC-CE signaling.

[0302] In another example solution, the WTRU may determine the number of new TCI states activated in the second set of TCI states that are not part of the first set (N_add) and / or the number of TCI states in the first set of TCI states that are not included in the second set (N_del). If N_add and / or N_del are above corresponding configured / preconfigured / determined thresholds, the WTRU may determine that AI / ML model retraining is required. If N_add and / or N_del are below corresponding thresholds, the WTRU may determine that AI / ML model retraining is not required. The WTRU may receive corresponding thresholds for N_add and N_del from a base station or gNB, for example, via RRC / MAC-CE signaling.

[0303] In an additional or alternative example solution, the WTRU may report one or more of the calculated parameters L_overlap, N_add, and N_del to the base station or gNB. In one example, the WTRU may report one or more of the calculated parameters as soft information. For example, the WTRU may report information about accuracy / validity / confidence level.

[0304] Provided herein are implementations and examples of reciprocity-based AI / ML model beam prediction verification. The WTRU may receive and measure one or more parameters (e.g., CSI or beam parameters, such as RSRP, CQI, PMI, SINR, etc.) regarding one or more beam resources in a first frequency range (e.g., FR1). The WTRU may determine / predict (e.g., based on an AI / ML model) one or more beam resources in a second frequency range (e.g., FR2) based on the corresponding measurements. The beam resources may consist of a TCI state for the downlink, a CSI-RS or SSB, an SRS resource, or a TCI state for the uplink. The WTRU may define / determine one or more spatial filters for the determined / predicted beam resources. The WTRU may identify the determined / predicted beam resources by a reference ID.

[0305] A person skilled in the art will appreciate that one or more problems are solved by the embodiments and examples provided herein. For example, one problem solved is how to verify the determined / predicted beam resources in the second frequency range and the corresponding AI / ML model.

[0306] In an example solution, the WTRU may perform one or more uplink transmissions (e.g., SRS, PUCCH, PUSCH), wherein the WTRU may determine an association taking into account a spatial relationship between (each of) the uplink transmission and one of the determined / predicted (downlink) beam resources. In this way, the WTRU may determine to use a spatial domain filter for the uplink transmission that the WTRU may have determined for the associated determined / predicted beam resource. The WTRU may indicate a reference ID corresponding to the determined / predicted beam resource, which is associated with the corresponding uplink transmission in the context of the spatial relationship.

[0307] In one example, the WTRU may be scheduled / configured with one or more UL transmissions of a signal and / or channel. In this way, the WTRU may determine to use the same spatial filter to transmit the configured UL signal or channel, which spatial filter may be defined for the determined / predicted beam resources. For example, the WTRU may determine to use the same spatial domain filter, which is determined to transmit the (uplink) resource reference signal or channel on the determined beam resources, the predicted beam resources, or either of the two. In other words, the WTRU may determine to consider the same QCL relationship between the determined / predicted (downlink) beam resources and the (uplink) transmitted signal or channel.

[0308] In an example solution, the base station or gNB may measure parameters corresponding to the received uplink signal and channel, beam resources, RSRP, CIR, angle of arrival (AoA), PDCCH hypothesized BLER, etc. The base station or gNB may change, update, or confirm the determined beam resources, the predicted beam resources, or both.

[0309] The WTRU may receive one or more signalings from a base station or gNB, for example, via a DCI, a MAC CE, etc., indicating whether the base station or gNB has changed, updated, or confirmed the determined / predicted beam resources. In one example, the WTRU may receive, for example, in a DCI, a flag indicating whether the predicted / determined beam resources are valid or invalid. For example, a flag value of zero may indicate invalid and a flag value of one may indicate valid. For another example, the WTRU may receive one or more CSI-RS measurement and reporting configurations, such as CSI-RS resources, QCL information, TCI status, etc., which may be based on the selected beam resources, such as at a base station or gNB.

[0310] The WTRU may receive one or more signals and channels in one or more beam resources (e.g., in a second frequency range) based on the uplink transmitted / reported signals / channels, wherein the WTRU may use the received signals to measure CSI and / or beam parameters. The WTRU may also use the measurements to update / retrain the AI / ML model. The WTRU may select and report the best beam and the corresponding CSI amount. For example, the corresponding CSI amount may include CSI-RSRP, CIR, etc.

[0311] Although the features and elements are described above in specific combinations, it will be understood by those of ordinary skill in the art that each feature or element may be used alone or in any combination with other features and elements. In addition, it will be appreciated by those of ordinary skill in the art that the features and elements described above include means for performing the methods described herein. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated into a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (sent via a wired or wireless connection) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media (such as built-in hard disks and removable disks), magneto-optical media, and optical media (such as CD-ROM disks and digital versatile disks (DVDs)). A processor associated with software may be used to implement a radio frequency transceiver used in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

1. A method for use in a wireless transmit / receive unit (WTRU), the method include: performing measurements on a first set of beam resources; predicting beam resources in a second set of beam resources based on the measurements of the first set of beam resources; Report the predicted beam resources; receiving one or more first signals using a first beam, wherein the first beam uses beam resources in the second set of beam resources; performing measurements on one or more accuracy parameters of the received one or more first signals; as well as Under the condition that one or more measured accuracy parameters of the received one or more first signals are acceptable, wherein the measured line of sight (LOS) is above a LOS threshold and the measured channel quality indicator (CQI) is above a CQI threshold, one or more second signals are sent using the first beam.

2. The method according to claim 1, further comprising: include: One or more third signals are received using the first beam under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

3. The method of claim 1 or 2, wherein the received one or more first signals include one or both of a physical downlink control channel (PDCCH) signal or a channel state information-reference signal (CSI-RS). The method of claim 1 , wherein using the first beam comprises activating the first beam. 5 . The method of claim 1 , wherein using the first beam comprises continuing to use the first beam.

6. The method of any one of claims 1 to 5, wherein the one or more accuracy parameters include one or more of a LOS parameter, a channel parameter, or a CQI parameter.

7. The method according to any one of claims 1 to 6, further comprising: include: An artificial intelligence (AI) / machine learning (ML) model is activated to predict one or more second beams, wherein the one or more second beams use beam resources in the second set of beam resources.

8. The method according to any one of claims 1 to 7, further comprising: include: Continue using the AI / ML model to predict one or more second beams, wherein the one or more second beams use beam resources in the second set of beam resources.

9. The method according to any one of claims 1 to 8, further comprising: include: Under the condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is below a LOS threshold and the measured CQI is below a CQI threshold, sending a request to select and report a third beam.

10. The method according to any one of claims 1 to 9, further comprising: include: Under a condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is above a LOS threshold and the measured CQI is below a CQI threshold, sending a request to: Updating or retraining at least one of the AI / ML models; and The AI / ML model is used to predict and report the fourth beam.

11. The method according to any one of claims 1 to 10, further comprising: include: Under the condition that one or more measured accuracy parameters of the received one or more first signals are unacceptable, wherein the measured CQI is below a CQI threshold, and multiple time instances have passed since the first signal was received using the first beam, fall back to a non-AI / ML beam management process to select and report a fifth beam.

12. The method according to any one of claims 1 to 11, further comprising: include: Under the condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is below a LOS threshold and the measured CQI is below a CQI threshold, and a plurality of time instances have not elapsed since the first signal was received using the first beam, continuing: receiving one or more fourth signals using one or more sixth beams; and One or more accuracy parameters of the received one or more fourth signals are measured.

13. A wireless transmit / receive unit (WTRU) configured for predicted beam management, the WTRU include: Transceiver; and a processor operatively coupled to the transceiver; wherein: The transceiver and the processor are configured to perform measurements on a first set of beam resources; The processor is configured to predict beam resources in a second set of beam resources based on the measurements of the first set of beam resources; The transceiver and the processor are configured to report the predicted beam resources; The transceiver is configured to receive one or more first signals using a first beam, wherein the first beam uses beam resources in the second set of beam resources; The transceiver and the processor are configured to perform measurements of one or more accuracy parameters of the received one or more first signals; and The transceiver and the processor are configured to transmit one or more second signals using the first beam under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

14. The WTRU of claim 13, wherein the transceiver is further configured to receive one or more third signals using the first beam under the condition that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

15. The WTRU of claim 13 or 14, wherein the received one or more first signals include one or both of a physical downlink control channel (PDCCH) signal or a channel state information-reference signal (CSI-RS).

16. The WTRU of any one of claims 13 to 15, wherein using the first beam comprises activating the first beam.

17. The WTRU of any one of claims 13 to 16, wherein using the first beam comprises continuing to use the first beam.

18. The WTRU of any one of claims 13 to 17, wherein the one or more accuracy parameters include one or more of a line of sight (LOS) parameter, a channel parameter, or a channel quality indicator (CQI) parameter.

19. A WTRU according to any one of claims 13 to 18, wherein the processor is further configured to activate an artificial intelligence (AI) / machine learning (ML) model to predict one or more second beams, wherein the one or more second beams use beam resources in the second set of beam resources.

20. The WTRU according to any one of claims 13 to 19, wherein the processor is further configured to continue using the AI / ML model to predict one or more second beams, wherein the one or more second beams use beam resources in the second set of beam resources.

21. A WTRU according to any one of claims 13 to 20, wherein the transceiver and the processor are further configured to send a request to select and report a third beam under the condition that one or more measured accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is below a LOS threshold and the measured CQI is below a CQI threshold.

22. The WTRU of any one of claims 13 to 21, wherein the transceiver and the processor are further configured to, under a condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is above a LOS threshold and the measured CQI is below a CQI threshold, send a request for: Updating or retraining at least one of the AI / ML models; and The AI / ML model is used to predict and report the fourth beam.

23. The WTRU of any one of claims 13 to 22, wherein the transceiver and the processor are further configured to, under a condition that one or more measured accuracy parameters of the received one or more first signals are unacceptable, wherein the measured CQI is below a CQI threshold, and a plurality of time instances have elapsed since the first signal was received using the first beam, fall back to a non-AI / ML beam management process to select and report a fifth beam.

24. The WTRU of any of claims 13 to 23, wherein the transceiver and the processor are further configured to, under a condition that the measured one or more accuracy parameters of the received one or more first signals are unacceptable, wherein the measured LOS is below a LOS threshold and the measured CQI is below a CQI threshold, and a plurality of time instances have not elapsed since the first signal was received using the first beam, continue: receiving one or more fourth signals using one or more sixth beams; and One or more accuracy parameters of the received one or more fourth signals are measured.

Images