Validation 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. Then, the WTRU may predict beam resources in a second set of beam resources based on the measurements of the first set of beam resources. The WTRU may report the predicted beam resources. 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. The WTRU may also perform measurements on one or more accuracy parameters of the received one or more first signals. The WTRU may transmit 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.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 395,587, filed August 5, 2022, the contents of which are incorporated herein by reference. [Background technology]

[0002] Beam management is a targeted use case of artificial intelligence (AI) / machine learning (ML) for the air interface in wireless communications. This technology can be a major basis in improving the performance and complexity of traditional beam management aspects, including beam prediction in time and / or spatial domains for reducing overhead and latency, improving beam selection accuracy, etc.

[0003] In wireless communications, traditional beam selection is based on beam sweeping at the gNode B (gNB) or base station side and the wireless transmit / receive unit (WTRU) or handset side. In frequency range 2 (FR2), traditional beam management can involve beam sweeping and measuring across multiple antennas at the gNB and WTRU sides. Once the best beam is selected, the WTRU can report up to four beams in the beam management procedure. In one example, the WTRU may report the beam based on reference signal received power (RSRP).

[0004] AI / ML models can be used to perform FR2 beam selection / prediction based on frequency range 1 (FR1) channel state information (CSI) measurements. However, realizing such a framework requires solving key challenges regarding beam measurement and reporting, as well as training and validation of AI / ML models in scenarios with hierarchical spatial relationships and associations between beam resources in different frequency ranges. Furthermore, using AI / ML model-based beam prediction is not always beneficial. For example, in non-line-of-sight (NLOS) communications, AI / ML-based beam prediction may be inaccurate, and traditional beam management procedures would be beneficial. Summary of the Invention

[0005] A wireless transmit / receive unit (WTRU) may determine one or more beam resources based on measurements made on 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 signals using one or more determined FR2 beam resources. Furthermore, the WTRU may perform a verification procedure based on one or more accuracy parameters.

[0006] In one example, the WTRU may perform measurements on a first set of beam resources. Then, the WTRU may predict beam resources in a second set of beam resources based on the measurements of the first set of beam resources. Further, the WTRU may report the predicted beam resources. Further, 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. The WTRU may also 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, provided that the measured one or more accuracy parameters of the received one or more first signals are acceptable. In one example, the accuracy parameters may be acceptable if the measured LOS is higher than an LOS threshold and the CQI is higher than a CQI threshold.

[0007] In a further example, the WTRU may receive one or more third signals using the first beam, provided that the measured one or more accuracy parameters of the received one or more first signals are acceptable.

[0008] In one example, the received one or more first signals may be physical downlink control channel (PDCCH) signals. In another example, the received one or more first signals may be channel state information-reference signals (CSI-RS).

[0009] Additionally, in one example, using the first beam may include activating the first beam, and in another example, using the first beam may include continuing to use the first beam.

[0010] In a further 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 one or more second beams. In one example, the one or more second beams may use beam resources in a second set of beam resources. In additional or alternative examples, the WTRU may continue to use the AI / ML model to predict the one or more second beams.

[0011] In an additional example, the WTRU may transmit 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 not acceptable. In one example, the measured LOS may be lower than an LOS threshold and the measured CQI may be lower than a CQI threshold.

[0012] In another example, the WTRU may transmit a request under a condition that one or more measured accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured LOS may be higher than an LOS threshold and the measured CQI may be lower than a CQI threshold. The transmitted request may include a request to update the AI / ML model. The transmitted request may include a request to retrain the AI / ML model. Furthermore, the transmitted request may include a request to predict and report a fourth beam using the AI / ML model.

[0013] Furthermore, the WTRU may fall back to a non-AI / ML beam management procedure to select and report the fifth beam under the condition that one or more measured accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured CQI may be below a CQI threshold and many time instances may have passed since the reception of the first signal using the first beam.

[0014] In a further 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 conditions where the measured one or more accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured LOS may be below an LOS threshold, the measured CQI may be below a CQI threshold, and many time instances may not have elapsed since the reception of the first signal using the first beam. [Brief explanation of the drawings]

[0015] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate similar elements and in which: [Figure 1A] 1 is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented. [Figure 1B] 1B is a system diagram illustrating an exemplary wireless transmit / receive unit (WTRU) that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1C] 1A is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1D] 1B is a system diagram illustrating a further exemplary RAN and a further exemplary CN that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 2] A system diagram illustrating an example of beam prediction for a second set of beam resources based on beam resource reporting for a first set of beam resources. [Figure 3] FIG. 10 is a flowchart illustrating an example of a verification procedure for beam prediction based on hierarchical spatial relationships. [Figure 4] FIG. 10 is a flow chart diagram illustrating an example of predicted beam management. DETAILED DESCRIPTION OF THE INVENTION

[0016] 1A is a diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. Communication system 100 may be a multiple-access system that provides content, such as voice, data, video, messaging, broadcasts, etc., to multiple wireless users. 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 use 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, filter bank multicarrier (FBMC), etc.

[0017] 1A, communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104, a core network (CN) 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, although it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a station (STA), may be configured to transmit and / or receive wireless signals and may include user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a mobile phone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable, 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., robots and / or other wireless devices operating in an industrial and / or automated processing chain context), a consumer electronics device, a device operating in a commercial and / or industrial wireless network, etc. Any of the UEs 102a, 102b, 102c, and 102d may be referred to interchangeably as a WTRU.

[0018] The communications system 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communications 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 a base transceiver station (BTS), a Node B, an eNode B (eNB), a Home Node B, a Home eNode B, a next generation Node B (gNode B (gNB), etc.), a new radio (NR) Node B, a site controller, an access point (AP), a wireless router, etc. Although the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0019] The base station 114a may be part of the RAN 104, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or base station 114b may be configured to transmit and / or receive radio signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide wireless service coverage for a particular geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one 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 may be used to transmit and / or receive signals in desired spatial directions.

[0020] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over the 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).

[0021] More specifically, as noted above, the communications system 100 may be a multiple-access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base station 114a and the WTRUs 102a, 102b, 102c of the RAN 104 may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High-Speed ​​Uplink (UL) Packet Access (HSUPA).

[0022] In an air interface embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0023] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR radio access, which may establish the air interface 116 using NR.

[0024] 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 jointly implement LTE radio access and NR radio access, e.g., using a 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 sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0025] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement a wireless technology such as IEEE 802.11 (i.e., Wireless Fidelity, WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access, WiMAX), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), or the like.

[0026] 1A 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 a local area such as a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, etc. 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 establish a picocell or a femtocell using a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.). As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not need to access the Internet 110 through the CN 106.

[0027] The RAN 104 may communicate with the CN 106, which may be any type of network configured to provide voice, data, application, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have various quality of service (QoS) requirements, such as different throughput, latency, error tolerance, reliability, data throughput, mobility, 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 shown in FIG. 1A , it will be understood that the RAN 104 and / or CN 106 may communicate directly or indirectly with other RANs that use 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 communicate with another RAN (not shown) employing GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0028] The CN 106 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network providing plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices, which use common communication protocols such as the transmission control protocol (TCP), the user datagram protocol (UDP), and / or the internet protocol (IP) of the TCP / IP Internet protocol suite. The networks 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the network 112 may include another CN connected to one or more RANs, which may use the same RAT as the RAN 104 or a different RAT.

[0029] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links.) For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with a base station 114a, which may employ a cellular-based wireless technology, and a base station 114b, which may employ an IEEE 802.2 wireless technology.

[0030] 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, 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 understood that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0031] The processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), any other type of integrated circuit (IC), a state machine, etc. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0032] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitting device / detector configured to transmit and / or receive, for example, IR signals, UV signals, or visible light signals. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF signals and light signals. It will be understood that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0033] 1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0034] The transceiver 120 may be configured to modulate signals transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers to enable the WTRU 102 to communicate via multiple RATs, such as, for example, NR and IEEE 802.11.

[0035] The processor 118 of the WTRU 102 may be coupled to and may receive user-entered 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. Additionally, the processor 118 may access information from and store data in any type of suitable memory, such as non-removable memory 130 and / or removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, etc. In other embodiments, the processor 118 may access information from and store data in memory that is not physically located on the WTRU 102, such as on a server or home computer (not shown).

[0036] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to other components in the WTRU 102. The power source 134 may be any suitable device for providing power to the WTRU 102. For example, the power source 134 may include one or more dry batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0037] The processor 118 may also be coupled to a GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or instead of, information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) 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 way of any suitable location-determination method while remaining consistent with an embodiment.

[0038] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, etc. The peripherals 138 may include one or more sensors. The sensor may be one or more of a gyroscope, an accelerometer, a Hall effect sensor, a magnetometer, a direction sensor, a proximity sensor, a temperature sensor, a time sensor, a geolocation sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, a humidity sensor, and the like.

[0039] The WTRU 102 may include a full-duplex radio where transmission and reception of some or all of the signals (e.g., associated with a particular subframe on both the UL (e.g., for transmission) and DL (e.g., for reception)) may be simultaneous and / or together. The full-duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference through either hardware (e.g., a choke) or signal processing via a processor (e.g., via a separate processor (not shown) or processor 118). In one embodiment, the WTRU 102 may include a half-duplex radio where transmission and reception of some or all of the signals (e.g., associated with a particular subframe on either the UL (e.g., for transmission) or DL ​​(e.g., for reception)) may be simultaneous and / or together.

[0040] 1C is a system diagram illustrating the RAN 104 and the CN 106, according to one embodiment. As noted above, the RAN 104 may employ E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0041] The RAN 104 may include eNodeBs 160a, 160b, and 160c, although it will be understood that the RAN 104 may include any number of eNodeBs while remaining consistent with an embodiment. The eNodeBs 160a, 160b, and 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In one embodiment, the eNodeBs 160a, 160b, and 160c may implement MIMO technology. Thus, the eNodeB 160a may, for example, use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0042] Each of the eNodeBs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, etc. As shown in FIG. 1C, the eNodeBs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0043] 1C 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 will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0044] The MME 162 may be connected to each of the eNodeBs 162a, 162b, 162c in the RAN 104 via an S1 interface and may function as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, activating / deactivating bearers, selecting a particular serving gateway during initial attach of the WTRUs 102a, 102b, 102c, etc. 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.

[0045] The SGW 164 may be connected to each of the eNodeBs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to and from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions such as anchoring the user plane during inter-eNodeB handovers, triggering paging when DL data is available to the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0046] The SGW 164 may be connected to a 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.

[0047] 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 landline communications devices. For example, the CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. Additionally, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0048] Although the WTRU is illustrated in FIGS. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments, such a terminal may use a wired communication interface (e.g., temporarily or permanently) with the communication network.

[0049] In a representative embodiment, the other network 112 may be a WLAN.

[0050] A WLAN in infrastructure Basic Service Set (BSS) mode may have an access point (AP) of the BSS and one or more stations (STAs) associated with the AP. The AP may have access to or interface with a distribution system (DS) or another type of wired / wireless network that carries traffic within and / or outside the BSS. Traffic originating from outside the BSS to a STA may arrive through the AP and be delivered to the STA. Traffic originating from a STA to a destination outside the BSS may be sent to the AP for delivery to the respective destination. Traffic between STAs within the BSS may be sent, for example, through the AP, where a source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent between (e.g., directly between) a source STA and a destination STA using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (e.g., all of the STAs) may communicate directly with each other. The IBSS mode of communication may be referred to herein as an "ad hoc" communication mode.

[0051] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, an AP may transmit 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 configured width. The primary channel may be the operating channel of the BSS and may be used by STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example, in an 802.11 system. With CSMA / CA, STAs (e.g., all STAs), including the AP, may sense the primary channel. If a particular STA senses / detects and / or determines that the primary channel is busy, the particular STA may back off. One STA (e.g., only one station) may transmit in a given BSS at any given time.

[0052] High Throughput (HT) STAs may use 40 MHz wide channels for communication, which may be formed, for example, through a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels.

[0053] A Very High Throughput (VHT) STA may support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. A 40 MHz and / or 80 MHz channel may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining eight contiguous 20 MHz channels or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, after channel encoding, the data may pass through a segment parser that may separate the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time-domain processing may be performed separately on each stream. The streams may be mapped to two 80 MHz channels, and the data may be transmitted by the transmitting STA. At the receiver of the receiving STA, the operations described above for the 80+80 configuration may be reversed, and the combined data may be sent to Medium Access Control (MAC).

[0054] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah compared to those used in 802.11n and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, while 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to representative embodiments, 802.11ah may support Meter Type Control / Machine-Type Communications (MTC), such as MTC devices, in macro coverage areas. MTC devices may have limited capabilities, including, for example, support for (e.g., only) certain and / or limited bandwidths. An MTC device may include a battery with a battery life above a threshold (eg, to maintain a very long battery life).

[0055] WLAN systems that can support multiple channels and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel that can be designated as a primary channel. The primary channel can have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be configured and / or limited by the STAs among all STAs operating in the BSS that support the minimum bandwidth operating mode. In an 802.11ah embodiment, the primary channel can be 1 MHz wide for STAs (e.g., MTC-type devices) that support (e.g., only) the 1 MHz mode, even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) configuration can depend on the status of the primary channel. For example, if a STA (that only supports 1 MHz mode of operation) transmitting to an AP has a busy primary channel, all of the available frequency bands may be considered busy even if most of the available frequency bands are idle.

[0056] In the United States, the available frequency band that can be used by 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 country regulations.

[0057] 1D is a system diagram illustrating the RAN 104 and the CN 106, according to one embodiment. As noted above, the RAN 104 may use NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0058] The RAN 104 may include gNBs 180a, 180b, and 180c, although it will be understood that the RAN 104 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, and 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, and 180c. Thus, the gNB 180a may transmit wireless signals to and / or receive wireless signals from the WTRU 102a using, for example, multiple antennas. In one embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum, while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNBs 180a and 180b (and / or 180c).

[0059] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of varying or scalable lengths (e.g., including varying numbers of OFDM symbols and / or varying lengths of absolute time duration).

[0060] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without accessing another RAN (e.g., eNodeBs 160a, 160b, 160c, etc.). In a standalone configuration, the WTRUs 102a, 102b, 102c may utilize one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in unlicensed spectrum. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate / connect with a gNB 180a, 180b, 180c while also communicating / connecting with another RAN, such as an eNodeB 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNodeBs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNodeBs 160a, 160b, 160c act as mobility anchors for the WTRUs 102a, 102b, 102c, and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0061] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support for network slicing, DC, interworking between NR and E-UTRA, routing of user plane data towards User Plane Functions (UPFs) 184a, 184b, routing of control plane information towards Access and Mobility Management Functions (AMFs) 182a, 182b, etc. As shown in FIG. 1D , the gNBs 180a, 180b, 180c may communicate with each other via an Xn interface.

[0062] 1D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While the foregoing elements are depicted as part of the CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0063] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N2 interface and may function as a control node. For example, the AMF 182a, 182b may be responsible for user authentication of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling different protocol data unit (PDU) sessions with different requirements), selection of a particular SMF 183a, 183b, management of registration areas, termination of non-access stratum (NAS) signaling, mobility management, etc. The network slicing may be used by the AMF 182a, 182b to customize CN support for the WTRUs 102a, 102b, 102c based on the type of service the WTRUs 102a, 102b, 102c are utilizing. 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 AMFs 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.

[0064] The SMFs 183a and 183b may be connected to the AMFs 182a and 182b in the CN 106 via an N11 interface. The SMFs 183a and 183b may also be connected to the UPFs 184a and 184b in the CN 106 via an N4 interface. The SMFs 183a and 183b may select and control the UPFs 184a and 184b and configure the routing of traffic through the UPFs 184a and 184b. The SMFs 183a and 183b may perform other functions, such as managing and assigning UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing DL data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0065] The UPFs 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks such as the Internet 110 to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPFs 184, 184b may perform other functions such as routing and forwarding packets, enforcing user plane policy, supporting multi-homed PDU sessions, handling user plane QoS, buffering DL packets, providing mobility anchoring, etc.

[0066] The CN 106 may facilitate communication with other networks. For example, the CN 106 may include or 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 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 local DNs 185a, 185b through the UPFs 184a, 184b via an N3 interface to the UPFs 184a, 184b and an N6 interface between the UPFs 184a, 184b and the DNs 185a, 185b.

[0067] 1A-1D and the corresponding description thereof, one or more or all of the functions described herein with respect to one or more of the WTRUs 102a-d, base stations 114a-b, eNodeBs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other devices described herein may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more or all of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functionality.

[0068] The emulation device may be designed to perform one or more tests of other devices in a laboratory environment and / or an operator network environment. For example, one or more emulation devices may perform one or more, or all, functions while fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices in the communication network. One or more emulation devices may perform one or more, or all, functions while temporarily implemented / deployed as part of a wired and / or wireless communication network. An emulation device may also be directly coupled to another device for testing and / or to perform testing using wireless communication.

[0069] One or more emulation devices may perform one or more (including all) functions while not implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a test lab and / or test scenarios in a non-deployed (e.g., test) wired and / or wireless communication network to perform tests of one or more components. One or more emulation devices may be test equipment. Direct RF coupling and / or wireless communication via RF circuitry (which may include, e.g., one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0070] In frequency range 2 (FR2), conventional beam management may involve beam sweeping and measuring across multiple antennas at the gNB and WTRU sides. After selecting the best beam, the WTRU may report up to four beams in the beam management procedure, for example, based on reference signal received power (RSRP).

[0071] Artificial intelligence (AI) / machine learning (ML) models can be used to perform FR2 beam selection / prediction based on frequency range 1 (FR1) channel state information (CSI) measurements. However, realizing such a framework requires solving key challenges regarding beam measurement and reporting, as well as training and validation of AI / ML models in scenarios with hierarchical spatial relationships and associations between beam resources in different frequency ranges. Furthermore, using AI / ML model-based beam prediction is not always beneficial. For example, in the case of non-line-of-sight (NLOS) communications, AI / ML-based beam prediction may be inaccurate, and traditional beam management procedures would be beneficial.

[0072] This results in different WTRU behavior in determining, measuring, and reporting beam resource associations, as well as in training, validating, activating, and / or deactivating AI / ML models. Therefore, further research into hierarchical beam prediction in NRAI / ML beam management is needed.

[0073] The embodiments and examples herein describe how to efficiently / dynamically activate / deactivate AI / ML model-based beam prediction, so that beam management procedures can be beneficially modified.

[0074] Methods for activating or deactivating an AI / ML model in beam prediction based on beam measurements on different beam resources in an AI / ML framework are provided in embodiments and examples herein. In one example, different beam resources may include resources with different beam widths, different frequency ranges, etc. This specification proposes determining the accuracy of an AI / ML model by considering different use cases and conditions, and provides different options for selecting for activating or deactivating the AI / ML model. This specification considers iterative retraining / updating of an AI / ML model based on AI / ML outputs and predicted beams, and in particular, provides conditions for AI / ML model retraining due to changes in the activation / deactivation set of transmission configuration indicator (TCI) states. Finally, this specification presents reciprocity-based AI / ML model validation for beam prediction.

[0075] Hereinafter, the terms "a" and "an" and similar terms or phrases may be interpreted as "one or more" and "at least one." Similarly, any term or phrase ending with the suffix "(s)" should be interpreted as "one or more" and "at least one." The term "may" should be interpreted as "may, for example."

[0076] As used in the embodiments and examples herein, AI may be broadly defined as behavior exhibited by a machine, which may mimic cognitive functions such as sensing, reasoning, adapting, and acting.

[0077] As used in the embodiments and examples herein, ML may refer to a type of algorithm that solves problems based on learning through experience (“data”) without being explicitly programmed (“constructing a rule set”). ML may be considered a subset of AI. Different machine learning transformations may be envisioned based on the nature of the data or feedback available to the learning algorithm. For example, supervised learning techniques 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 its corresponding output. For example, unsupervised learning techniques may involve detecting patterns in data without existing labels. For example, reinforcement learning techniques may involve performing a sequence of actions in an environment to maximize a cumulative reward. In some solutions, machine learning algorithms may be applied using a combination or interpolation of the above techniques. For example, semi-supervised learning techniques 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 is positioned between unsupervised learning, which does not use labeled training data, and supervised learning, which uses only labeled training data.

[0078] 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), 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 a nonlinear activation function multiple times. DNNs typically consist of multiple layers, each consisting of a linear transformation and a given nonlinear activation function. DNNs can be trained using training data via a backpropagation algorithm. Recently, DNNs have demonstrated state-of-the-art performance in various domains, such as speech, vision, and natural language, and for various supervised, unsupervised, and semi-supervised machine learning settings. The term AI / ML-based methods / processes may refer to achieving behavior and / or adapting to requirements by learning based on data, without the explicit construction of a series of action steps. Such methods may enable learning complex behaviors that are difficult to specify, difficult to implement, or both, using traditional methods.

[0079] The WTRU may transmit or receive a physical channel or a reference signal (RS) according to at least one spatial domain filter. The term "beam," as used in the embodiments and examples herein, may be used to refer to a spatial domain filter.

[0080] The WTRU may transmit a physical channel or signal using the same spatial domain filter as that used to receive an RS, such as a channel state information-reference signal (CSI-RS) or synchronization signal (SS) block. The WTRU transmission may be referred to as the "target," and the received RS or SS block may be referred to as the "reference" or "source." In such a case, the WTRU may be said to transmit the target physical channel or signal according to a spatial relationship relative to such RS or SS block.

[0081] The WTRU may transmit a first physical channel or signal according to the same spatial domain filter used to transmit a second physical channel or signal. The first and second transmissions may be referred to as the "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 relative to the second (reference) physical channel or signal.

[0082] 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, the WTRU may implicitly transmit physical uplink shared channel (PUSCH) transmissions and demodulation reference signals (DM-RS) for PUSCH according to the same spatial domain filter as a sounding reference signal (SRS) indicated by an SRS resource indicator (SRI) indicated in DCI or configured in RRC signaling. In 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 index."

[0083] The WTRU may receive a first (target) downlink channel or signal according to the same spatial domain filter 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 each DM-RS. When at least the first and second signals are reference signals, such an association may exist when the WTRU is configured with quasi-colocation (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 into a set of TCI states configured by RRC signaling and / or signaled by the MAC CE. Such an index may also be referred to as a "beam index."

[0084] As used herein, a transmission and reception point (TRP) may be used interchangeably with one or more of a transmission point (TP), reception point (RP), radio remote head (RRH), distributed antenna (DA), base station (BS), sector (of a BS), and cell while still being consistent with the embodiments and examples provided herein. In one example, a cell may be a geographic cell area served by a BS. Furthermore, as used herein, a multi-TRP may be used interchangeably with one or more of an MTRP, an M-TRP, and multiple TRPs while still being consistent with the embodiments and examples provided herein.

[0085] The WTRU may report a subset of 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 the panel used for reception at the WTRU (such as a panel identification or group identification), measurements 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 other channel state information such as at least a rank indicator (RI), a channel quality indicator (CQI), a precoding matrix indicator (PMI), a layer indicator (LI), and / or the like.

[0086] Embodiments herein include activating / deactivating beam predictions based on AI / ML modeling. Specifically, embodiments herein include options for activating / retraining / deactivating / fallback of AI / ML models. Furthermore, embodiments herein include determining the accuracy of AI / ML models. Also, embodiments herein include use cases and conditions under which AI / ML models can be used.

[0087] 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 beam prediction validation of AI / ML models based on reciprocity.

[0088] Embodiments and examples herein include activation / deactivation of 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 measurements. The WTRU derives one or more FR1 CSI parameters. One or more of the following may apply: The WTRU may determine one or more FR2 beam resources, predict one or more FR2 beam resources, or both. The WTRU may perform the determination, prediction, or both based on an AI / ML model, in one example. In one example, the beam resources may consist of TCI status, CSI-RS, or SSB for the downlink, or SRS resources or TCI status for the uplink. The WTRU may also report one or more FR1 CSI parameters (e.g., multi-CRI), and the base station or gNB may perform FR2 beam prediction accordingly. The beam prediction may be performed based on an AI / ML model, in one example.

[0089] Furthermore, the WTRU may receive one or more FR2 beam resources, which may be predicted FR2 resources. The WTRU may also receive one or more thresholds for accuracy levels in the verification procedure. For example, the WTRU may receive thresholds for LOS probability, CQI, block error rate (BLER), Doppler shift, etc. Furthermore, the WTRU may perform the verification procedure based on, for example, one or more accuracy parameters for the received FR2 beam resources.

[0090] Embodiments herein include options for activating / retraining / deactivating / fallback of AI / ML models. In one example, based on the measured / determined accuracy parameters, the WTRU may decide to use one or more of the following options: If the accuracy parameters are acceptable, the first option may be to use / activate the AI / ML model for beam prediction.

[0091] If the accuracy parameters are not acceptable, the WTRU may select from other candidate beam resources based on the AI / ML prediction in a second option. Furthermore, the WTRU may send a request for one or more FR2 candidate beam resources, e.g., as indicated by the base station or gNB, or as determined by the WTRU based on the AI / ML model. The WTRU may start a corresponding timer / counter. Furthermore, the WTRU may monitor / measure the candidate beams. If the accuracy measures are acceptable for the beam resources, the WTRU may indicate the respective beam via a physical random access channel (PRACH) or PUCCH. If the counter / timer exceeds the respective maximum count / time, the WTRU may switch to a fourth option, further described below.

[0092] In a third option, the parameters / models may be updated / retrained. The WTRU may, for example, send a request to update / retrain 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. If the accuracy measure is acceptable for the predicted FR2 beam resources, the WTRU may indicate the respective beam via PRACH or PUCCH. If the counter / timer exceeds the respective maximum count / time, the WTRU may switch to the fourth option, described below.

[0093] A fourth option may include fallback: the WTRU may send a request to deactivate the AI / ML model and / or fallback to conventional beam management mechanisms.

[0094] Embodiments herein include determining the accuracy of the AI / ML model. The WTRU may determine accuracy parameters of the predicted FR2 beam based on the verification procedure and respective thresholds. For example, for the FR2 predicted beam resource, if the measured CSI parameters and / or the hypothetical (Hyp) PDCCH BLER are higher and / or lower than corresponding thresholds, respectively, the WTRU may determine that the accuracy parameters (e.g., of the AI / ML model) are acceptable. In examples, the measured CSI parameters may include one or more of RSRP, signal-to-interference-and-noise ratio (SINR), CQI, etc.

[0095] Further, embodiments and examples herein include that the WTRU may determine the accuracy based on an association of one or more parameters. In an example, the one or more parameters may include one or more of the CQI, the hypothesis, the PDCCH BLER, the RSRP, the SINR, the probability of LOS, the Doppler shift, the Doppler spread, the average delay, the delay spread, etc. For example, for a beam resource predicted in FR2, the probability of LOS is higher than a first threshold (e.g., LOS_th), but the derived CQI is lower than the respective threshold (e.g., CQI_th). Therefore, the WTRU may decide to execute the third option. In another example, for a beam resource predicted in FR2, the probability of LOS is lower than a first threshold (e.g., LOS_th), and the derived CQI is lower than the respective threshold (e.g., CQI_th). Thus, the WTRU may decide to execute the second option or the fourth option based on, for example, the determined probability of LOS.

[0096] Additionally or alternatively, the WTRU may be configured with one or more use cases, e.g., a subset of one or more cases, and / or conditions under which the AI / ML model can be used, e.g., LOS, antenna panel configuration, etc. The WTRU may, for example, determine and send a request to the base station or gNB to fall back to FR2 beam management and deactivate AI / ML beam prediction based on the configured use case.

[0097] Therefore, one or more of the following may be applied: an LOS metric, a LOS probability, or both. Specifically, if the LOS probability for any of the CSI-RS resources is lower than a respective threshold, the WTRU may request a fallback. For example, the base station or gNB may configure multiple FR1 beams and find the most probable LOS to use in the AI / ML FR2 beam prediction.

[0098] Also, antenna panel configurations may be applied. In one example, if there is no same QCL Type-D assumption between FR1 and FR2 antenna ports and / or panels at the WTRU side, the WTRU may decide to fall back to FR2 beam management and send a request to the base station to deactivate AI / ML beam prediction.

[0099] Furthermore, the WTRU may use other conditions for activating / deactivating AI / ML. For example, other conditions may include the number of supported FR1 and FR2 beams. Further, other conditions may include the boresight of the antenna array, the beam direction of the antenna, or the antenna array configuration for FR1 and FR2 on the WTRU side, the base station or gNB side, or both. Further, other conditions may include WTRU capabilities.

[0100] Embodiments and examples herein include iterative training / updating of the AI / ML model based on the predicted beam of the AI / ML output. In one example, the WTRU receives a set of one or more FR1 and FR2 beam resources and derives beam resource parameters. The beam resources may consist of one or more of TCI states, CSI-RS or SSB for the downlink, SRS resources for the uplink, or TCI states for the uplink.

[0101] In initial training, the WTRU may use measured CSI parameters and TCI conditions in beam prediction AI / ML model training. The measured CSI parameters may include one or more of CQI, PMI, CRI, etc., in one example. 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.

[0102] Optionally, retraining may be used. If the accuracy is not acceptable, the WTRU may use the received FR2 beams to retrain and / or update the respective AI / ML model parameters. For example, the WTRU may determine the number of additional information, e.g., the number of FR2 beams for retraining.

[0103] The WTRU may use the measured CSI parameters in the retrained / updated beam prediction AI / ML model and determine one or more best FR2 beams accordingly, e.g., based on RSRP. The measured CSI parameters may include, in one example, one or more of CQI, PMI, CIR, etc. The WTRU may determine whether the model retraining and updating resulted in a different output, e.g., a different predicted FR2 beam, than the previous model.

[0104] If the retraining of the model results in a new / different output, e.g., 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, e.g., based on a timer or counter, and if unsuccessful, the WTRU decides to follow one or more of the activation / deactivation / fallback options.

[0105] Embodiments and examples herein include AI / ML model retraining due to a change in the activated / deactivated set of TCI states. A WTRU receives the 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 / modified, set of activated / deactivated TCI states, e.g., in the MAC-CE, one or more of the following may apply: The WTRU may determine whether retraining of the AI / ML model is necessary. 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 necessary. Otherwise, if the overlap is lower than a threshold, the WTRU may determine that retraining of the AI / ML is necessary.

[0106] Embodiments herein include reciprocity-based beam prediction AI / ML model verification. In an example, a WTRU determines / predicts one or more FR2 beams based on FR1 beam / CSI measurements. The WTRU performs transmission to a base station or gNB based on the WTRU-predicted FR2 beam. In one example, the transmission may include one or more of an SRS, a hybrid automatic repeat request (HARQ) acknowledgement (Ack), or a CSI-RS report. The base station or gNB may measure a channel, e.g., RSRP, based on the received FR2 signal. The base station or gNB may then modify or verify the WTRU's beam selection. The WTRU may receive one or more FR2 CSI-RS measurement and reporting configurations, which may be based on the beam selected at the base station or gNB. In one example, the measurement and reporting configurations may include one or more of CSI-RS resources, QCL information, TCI status, etc. The WTRU may measure the FR2 CSI and update / retrain the AI / ML model using the measured parameters. The WTRU may select and report the best beam and the respective CSI amount, eg, CSI-RSRP, CIR, etc.

[0107] The WTRU may use channel and / or interference measurements. For example, the WTRU may receive synchronization signal / physical broadcast channel (SS / PBCH) blocks. The SS / PBCH blocks (SSBs) may include a primary synchronization signal (PSS), a secondary synchronization signal (SSS), and a physical broadcast channel (PBCH). The WTRU may monitor, receive, or attempt to decode the SSBs during initial access, initial synchronization, radio link monitoring (RLM), cell search, cell switching, etc.

[0108] Furthermore, the WTRU may measure and report CSI, and the CSI for each connected mode may include or be configured with one or more of a CSI reporting configuration, a CSI-RS resource set, or a non-zero-power (NZP) CSI-RS resource. The CSI reporting configuration may include one or more of the following: a reporting quantity, such as CQI, RI, PMI, CRI, or LI; a CSI reporting type, such as aperiodic, semi-persistent, or periodic; a CSI reporting codebook configuration, such as Type I, Type II, or Type II port selection; or a 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 resources may include one or more of the following: NZP CSI-RS resource identity (ID), periodicity and offset, QCL information and TCI state, or resource mapping, e.g., number of ports, density, code division multiplexing (CDM) type, etc.

[0109] The WTRU may indicate, determine, or be configured with one or more reference signals. The WTRU may monitor, receive, and / or measure one or more parameters based on each reference signal. For example, one or more of the following may apply: The following parameters are non-limiting examples of parameters that may be included in reference signal measurements. One or more of these parameters may be included. Other parameters may be included.

[0110] SS reference signal received power (SS-RSRP) may be measured based on a synchronization signal, e.g., a demodulation reference signal (DMRS) in the PBCH or SSS. SS-RSRP may be defined as a linear average over the power contributions of resource elements (REs) carrying each synchronization signal. When measuring RSRP, power scaling for the reference signal may be required. In the case where SS-RSRP is used for L1-RSRP, measurement may be achieved based on the CSI reference signal in addition to the synchronization signal.

[0111] The CSI-RSRP may be measured based on a linear average over the power contributions of the REs carrying each CSI-RS. The CSI-RSRP measurements may be configured within the measurement resources for the configured CSI-RS occasions.

[0112] The SS-SINR may be measured based on a synchronization signal, e.g., DMRS in the PBCH or SSS. The SS-SINR may be defined as the linear average over the power contributions of the REs carrying the respective synchronization signals 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 achieved based on resources configured by higher layers.

[0113] The CSI-SINR may be measured based on the linear average of the power contributions of the REs carrying each CSI-RS divided by the linear average of the noise and interference power contributions. If CSI-SINR is used for L1-SINR, the noise and interference power measurement may be achieved based on resources configured by higher layers. Otherwise, the noise and interference power may be measured based on the resources carrying each CSI-RS.

[0114] A received signal strength indicator (RSSI) may be measured based on an average of the total power contributions over the configured OFDM symbols and bandwidth. The power contributions may be received from different resources, such as co-channel serving and non-serving cells, adjacent channel interference, thermal noise, etc.

[0115] A cross-layer interference received signal strength indicator (CLI-RSSI) may be measured based on the average of total power contributions over configured OFDM symbols of configured time and frequency resources. Power contributions may be received from different resources, such as cross-layer interference, co-channel serving and non-serving cells, adjacent channel interference, thermal noise, etc.

[0116] The sounding reference signals RSRP (SRS-RSRP) may be measured based on a linear average over the power contributions of the REs carrying each SRS.

[0117] A CSI reporting configuration, e.g., CSI-ReportConfigs, beam / CSI reporting configuration, etc., may be associated with a single bandwidth part (BWP), e.g., indicated by a BWP-Id, and 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 reporting configuration type, e.g., periodic, semi-persistent, and aperiodic; CSI-RS transmission periodicity for periodic and semi-persistent CSI reporting; CSI-RS transmission slot offset for periodic, semi-persistent, and aperiodic CSI reporting; CSI-RS transmission slot offset list for semi-persistent and aperiodic CSI reporting; time limit for channel and interference measurements; reporting frequency band configuration (e.g., wideband / subband CQI, PMI); thresholds and calculation modes for reporting quantities (e.g., CQI, RSRP, SINR, LI, RI); codebook configuration; group-based beam reporting; CQI table; subband size; non-PMI port index; port index; etc.

[0118] Examples provided herein may include CSI-RS resource configurations. A CSI-RS resource set, such as NZP-CSI-RS-ResourceSet, may include one or more of the CSI-RS resources, such as NZP-CSI-RS-Resource and CSI-ResourceConfig, and the WTRU may be configured with one or more of the following in the CSI-RS resources: CSI-RS periodicity and slot offset for periodic and semi-persistent CSI-RS resources; CSI-RS resource mapping defining the number, density, CDM type, OFDM symbols, and subcarrier occupancy of CSI-RS ports; bandwidth portion to which the configured CSI-RS is allocated; or a reference to a TCI-State containing the QCL source RS and the corresponding QCL type.

[0119] Examples provided herein may include an RS resource set configuration. The RS resource set may use one or more of the following configurations. Specifically, a WTRU may be configured with one or more RS resource sets. Furthermore, the RS resource set configuration may include one or more of the following: an RS resource set ID, one or more RS resources for the RS resource set, repetition (i.e., on or off); an aperiodic triggering offset (e.g., one of 0 to 6 slots), or tracking reference signal (TRS) information (e.g., true or false).

[0120] Examples provided herein may include an RS resource configuration. The RS resources may use one or more of the following configurations. For example, a WTRU may be configured with one or more RS resources. Furthermore, the RS resource configuration may include one or more of the following: an RS resource ID, a resource mapping, e.g., REs in a physical resource block (PRB), a power control offset (e.g., any value of -8, ..., 15), a power control offset by SS (e.g., -3 dB, 0 dB, 3 dB, 6 dB), a scrambling ID, a periodicity and offset, or QCL information, e.g., based on the TCI state.

[0121] In the following, the properties of a grant or allocation may consist of at least one of the following: frequency allocation, time allocation aspects such as duration, priority; modulation and coding scheme, transport block size; number of spatial layers; number of transport blocks; TCI state, CRI or SRI, repetition count; whether the retransmission scheme is Type A or Type B, whether the grant is a configured grant Type 1, Type 2 or dynamic grant, whether the allocation is a dynamic allocation or a semi-persistent scheduled (configured) allocation, configured grant index or semi-persistent allocation index; periodicity of the configured grant or allocation; channel access priority class (CAPC); or any parameters provided by MAC or by RRC in the DCI for scheduling the grant or allocation.

[0122] In the following, an indication by 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 properties such as the DCI format, the DCI size, the core set or search space, the aggregation level, the first resource element of the received DCI, e.g. the index of the first control channel element, where the mapping between properties and values ​​may be signaled by RRC or MAC.

[0123] Examples provided herein may include beam quality monitoring, radio link monitoring, or both. For example, the WTRU may use / receive / or configure one or more sets of reference signals per BWP to monitor and detect beam failure detection. For example, the term q0 may be used for the beam failure detection set. In another example, the term q0,0 or q0,1 may be used as the 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 signals may be CSI-RS resource configuration indices and / or SSB indices. The reference signals included in the beam failure detection RS set may be the same as the reference signals configured / used / received for RLM.

[0124] 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 respective 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 respective CORESET indicated by the TCI state.

[0125] The WTRU may measure 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 thresholds may be used, and the thresholds Q_out, Q_in, or both may be used to estimate the quality of the radio link and / or the respective beam. The terms Q_out and Q_in may be used to represent one or more attributes or parameters and the respective values ​​of the attributes or parameters.

[0126] The threshold Q_out may 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 may be used to determine a radio link and / or beam quality at which signal transmissions may be reliably received, corresponding to an in-sync block error rate (BLER_in). BLER_out, BLER_in, or both may be explicitly determined by the base station or gNB.

[0127] If BLER_out and / or BLER_in are not explicitly determined by the base station or gNB, they may be estimated based on one or more parameters. For example, the WTRU may use, receive, or configure PDCCH transmission parameters to perform out-of-sync evaluation, in-sync evaluation, or both. In one example, the number of control OFDM symbols, aggregation level, ratio of virtual PDCCH RE energy to average SSS RE energy, ratio of virtual 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.

[0128] 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. The tables are non-limiting examples of parameters that may be included when evaluating the out-of-sync and in-sync thresholds. One or more of them may be included. The values, numbers of PRBs, and options for each parameter are examples. Other values, numbers of PRBs, or options may be included.

[0129] [Table 1]

[0130] [Table 2]

[0131] Hereinafter, the term RS may be used interchangeably with one or more of RS resource, RS resource set, RS port, and RS port group while still being consistent with the embodiments and examples provided herein. Furthermore, the term RS may be used interchangeably with one or more of SSB, CSI-RS, SRS, DM-RS, TRS, PRS, and phase tracking reference signal (PTRS), while still being consistent with the embodiments and examples provided herein.

[0132] Hereinafter, the term reference signal may be used interchangeably with one or more of SRS, CSI-RS, DM-RS, PT-RS, and / or SSB, while still being consistent with the embodiments and examples provided herein.

[0133] Hereinafter, the term channel may be used interchangeably with one or more of PDCCH, PDSCH, PUCCH, PUSCH, PRACH, etc., while still being consistent with the embodiments and examples provided herein. Hereinafter, the phrase RS resource set may be used interchangeably with one or more of RS resource and beam group, while still being consistent with the embodiments and examples provided herein.

[0134] Hereinafter, the phrase beam reporting may be used interchangeably with one or more of CSI measurement, CSI report, and beam measurement, while still being consistent with the embodiments and examples provided herein. Hereinafter, the proposed solution for beam resource prediction may be used for beam resources belonging to a single or multiple cells and a single or multiple TRPs, while still being consistent with the embodiments and examples provided herein.

[0135] Hereinafter, the phrase CSI report may be used interchangeably with one or more of CSI measurement, beam report, and beam measurement, while still being 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), virtual PDCCH BLER, PDSCH BLER, probability of LOS, etc., while still being consistent with the embodiments and examples provided herein.

[0136] Embodiments and examples of activation / deactivation of beam prediction based on AI / ML modeling are provided herein. In one example, a WTRU may receive one or more CSI reporting configurations. For example, the WTRU may receive a CSI-ReportConfig. In one example, the WTRU may receive one or more CSI reporting configurations from a base station. The CSI reporting configurations may include CSI reporting quantities that may indicate CSI parameters that may be required to be measured / estimated / derived and reported. In one example, the CSI reporting quantities may be one or more of CQI, RI, PMI, CRI, LI, SINR, RSRP, etc.

[0137] A CSI reporting configuration may be associated with one or more CSI resource configurations, such as a CSI-ResourceConfig, for channel / interference measurements. A resource configuration may include a list of CSI resource sets, which may include references to one or more CSI-RS resource sets, SSB sets, or both types of sets.

[0138] 2 is a system diagram illustrating an example of beam prediction for a second set of beam resources based on a beam resource report for a first set of beam resources. The example shown in FIG. 2 presents a WTRU configured with a first set of beam resources. The first set of beam resources may be, for example, CSI-RS resources, TCI states, etc. Additionally, the first set of beam resources may be within a first frequency range, for example, FR1, and / or a first beamwidth, for example, wide beamwidth for a wide beam, which may be, for example, CSI-RS resources, TCI states, etc. 1、1 , C 1、2 , and C 1、3 is shown as:

[0139] The WTRU is also configured with a second set of beam resources, which may be, for example, CSI-RS resources, TCI states, etc. Furthermore, the second set of beam resources may be within a second frequency range, for example, FR2, and / or a second beamwidth, for example, narrow beamwidth for a narrow beam, which are shown as B in FIG. 2、1 , B 2、2 , ..., B 2、9 is shown as:

[0140] 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 is C 1、2 For example, the WTRU may determine that beam C 1、2 214 is the beam with the highest RSRP or LOS and therefore may determine that it is the best beam. For example, the WTRU may determine the best PMI(s) in the first set of CSI-RS resources, indicated by the directional arrows pointing from base station 214 to WTRU 202 and blockage 203. In the example shown in system diagram 200, blockage 203 reflects signals received from base station 214 back to WTRU 202.

[0141] The WTRU may be, for example, 1、2For each selected beam resource, such as, for example, FR2, the base station 214 may report the determined parameters, such as CSI parameters in the first set of CSI-RS resources, such as, for example, RSRP, RI, LI, SINR, PMI, CQI, etc. In one example, at the base station 214, which may be a gNB, the reported CSI parameters may be used to predict one or more of the best beam resources in a second frequency range, such as FR2, based on, for example, an AI / ML model.

[0142] 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, beam B in FIG. 2、4 and B 2、6 may be selected / determined / predicted based on, for example, the best PMI. In this manner, the WTRU may report the determined / selected beam resource, e.g., beam index or CRIS, and the respective predicted RSRP / SINR for the maximum number of beams, e.g., up to four beams. In one example, the respective predicted RSRP / SINR may include L1-RSRP, L1-SINR, etc. In other words, the best beam resource in the second frequency range may be determined based on the AI / ML model without excessive beam sweeping, whether by the base station 214, which may be a gNB, or the WTRU 202.

[0143] 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 as accurate and further confirmation and validation may be required. Those skilled in the art will understand that one or more problems are addressed by the embodiments and examples provided herein. For example, how is a beam prediction (e.g., based on AI / ML) validated? How can one distinguish whether a low quality prediction, e.g., a low RSRP of a predicted beam, is due to poor behavior of the AI / ML model or whether there are other causes? When the quality of the prediction is low, e.g., how do you address a predicted beam with low RSRP / CQI?

[0144] 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. Furthermore, the WTRU may determine the accuracy parameters of the beam predicted by the AI / ML model. Furthermore, the WTRU may deactivate the AI / ML beam prediction based on one or more of a line of sight (LOS) indicator, a probability of LOS, an antenna panel configuration, a number of supported beams, an antenna array, or WTRU capabilities. The WTRU may also use measured CSI parameters and TCI conditions in beam prediction for initial training of the AI / ML model.

[0145] In an example solution, the WTRU may decide to or be configured to perform validation on the AI / ML output. As an 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 in the WTRU and / or the gNB. The beam resources may consist of TCI states, CSI-RS or SSB for the downlink, and SRS resources or TCI states for the uplink.

[0146] The WTRU may be configured to determine, indicate, or receive and measure one or more CSI / beam resource parameters to verify the validity and / or accuracy of the AI / ML output. In one example, the WTRU may propose, report, or request the base station or gNB to transmit one or more channels / signals corresponding to the predicted beam resources, e.g., the same QCL, the same spatial relationship, or both. The one or more channels / signals may be, for example, PDCCH, CSI-RS signals, etc. In another example, the WTRU may be configured to receive and measure one or more channels / signals corresponding to the predicted beam resources, e.g., the same QCL, the same spatial relationship, or both, e.g., PDCCH, CSI-RS signals, etc. As an example, the requested / configured beam resources may be within a second frequency range, e.g., FR2.

[0147] The WTRU may determine or be configured to derive measurements for one or more parameters of the configured / determined beam resources. As an example, the WTRU may be configured to derive CSI parameters based on the configured / received CSI-RS signals, e.g., LOS probability, PMI, CQI, RSRP, SINR, Doppler shift, etc. In another example, the WTRU may be configured to derive parameters corresponding to the received channel, e.g., PDCCH virtual BLER. Furthermore, the WTRU may determine or be configured with one or more thresholds associated with the determined / configured parameters to be measured. The WTRU may also determine or be configured with one or more limit / maximum / minimum values ​​associated with timers / counters used in the verification procedure.

[0148] The WTRU may determine / report the validity of the AI / ML model, and the WTRU may determine / report the AI / ML as "valid" (measured accuracy is acceptable) or "invalid" (measured accuracy is not acceptable). Thus, if the measured parameters or association / combination of measured parameters are within an acceptable range, the WTRU may determine that the AI / ML model is "valid" and has "acceptable accuracy." Conversely, if the measured parameters or association / combination of measured parameters are not within an acceptable range, the WTRU may determine that the AI / ML model is "invalid" and that the model "does not have acceptable accuracy."

[0149] In an example solution, the WTRU may be configured to have one or more options to select for different conditions based on measurements, thresholds, and validation scenarios. Accordingly, one or more of the following examples may apply.

[0150] In option 1, the WTRU may use an AI / ML model in beam prediction, activate an AI / ML model in beam prediction, or both. For example, the WTRU may determine that the respective AI / ML model is valid and its accuracy is acceptable. Thus, the WTRU may decide to use / activate the respective AI / ML model, for example, for beam prediction.

[0151] In option 2, the WTRU may select from other candidate beam resources based on AI / ML predictions. For example, the WTRU may determine or be configured with one or more candidate (predicted) beams, e.g., based on an AI / ML model. In this manner, if the WTRU detects / determines that the best (predicted) beam does not exhibit acceptable accuracy, the WTRU may decide to monitor one or more of the candidate (predicted) beams. In examples, the lack of acceptable accuracy may be indicated by a CQI below a threshold, an RSRP below a threshold, or both, or by a PDCCH virtual BLER above a threshold.

[0152] In option 3, the parameters, the model, or both may be updated, retrained, or both. For example, the WTRU may determine that the AI / ML model is the reason why a beam predicted based on, for example, AI / ML does not have acceptable accuracy. As such, the WTRU may determine, propose, or transmit a request to update the AI / ML model, retrain the AI / ML model, or both.

[0153] In option 4, the WTRU may fall back to legacy procedures, deactivate the AI / ML model, or do both. For example, the WTRU may determine that the (predicted) beam quality, accuracy, or both are below one or more thresholds, in which case the WTRU may determine that the AI / ML model is invalid. Thus, the WTRU may decide to deactivate the AI / ML model, fall back to legacy, or do both. In one example, falling back to legacy may include using non-AI / ML model-based procedures.

[0154] In an example solution, the WTRU may decide to change the selected option based on measured accuracy parameters, one or more timers / counters, etc. In one example, the WTRU may decide to operate in option 2, in which case the WTRU may start a timer or counter, e.g., for the number of monitored candidate beams. If the timer (counter) expires (reaches a maximum) before the WTRU can find another candidate beam with acceptable accuracy, the WTRU may decide to select another option. For example, the WTRU may decide to select option 3 or 4. Additionally or alternatively, if the WTRU determines that one or more of the candidate beams has acceptable accuracy, such as before the timer (counter) expires (reaches a maximum), the WTRU may report the determined beam, and the WTRU may decide to select an option that uses / activates an AI / ML model, such as option 1.

[0155] In another example, the WTRU may decide to operate in Option 3, and the WTRU may start a timer, a counter, or both. If the model update / retraining results in the WTRU determining one or more beams with acceptable accuracy before the timer (counter) expires (reaches its maximum), the WTRU may decide to select an option to use and / or activate the (retrained / updated) AI / ML model, e.g., Option 1. Conversely, if the timer expires (and / or the counter reaches its maximum limit) and the WTRU determines that the AI / ML model update / retraining did not result in acceptable accuracy, the WTRU may decide to fall back or deactivate the AI / ML model, e.g., Option 4.

[0156] In an example solution, the WTRU may determine and / or establish accuracy parameters and / or verification procedures based on an association / combination of one or more CSI, beam, channel, environment, and / or mobility parameters. For example, the WTRU may decide to establish an association based on one or more parameters as follows:

[0157] The WTRU may decide to establish an association based on beam resource parameters, for example, the WTRU may determine parameters corresponding to beam resources and CSI amounts, such as RSRP, SINR, CQI, PMI, RI, L1, virtual PDCCH BLER, etc., along with their respective thresholds.

[0158] The WTRU may decide to establish an association based on channel, mobility, and environmental parameters. For example, the WTRU may determine parameters corresponding to the channel, environment, and mobility, such as the probability of LOS, Doppler shift, Doppler spread, mean delay, delay spread, etc., along with respective thresholds.

[0159] As an example, the WTRU may determine the accuracy parameter based on an association / combination of CSI and / or beam parameters along with the environment, mobility, and channel parameters of the (predicted) beam resources for the respective thresholds. For example, the WTRU may determine one or more accuracy levels based on a CQI association, a CQI combination, or both, and the probability of LOS. 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 respective thresholds, the WTRU may determine that the performance of the AI / ML model is acceptable and, therefore, the WTRU may validate the AI / ML model and decide to use / activate the respective AI / ML model, e.g., as in Option 1.

[0160] For example, the measured probability of LOS may be higher than the respective thresholds, but the measured received power and / or channel quality (e.g., CQI, RSRP, SINR, etc.) is lower than the respective thresholds. In that case, the WTRU may determine that the accuracy of the AI / ML is unacceptable. Thus, the WTRU may decide to update the AI / ML model, e.g., as in option 3. For example, if the measured probability of LOS and the measured received power and / or channel quality (e.g., CQI, RSRP, SINR, etc.) are lower than the respective thresholds, the WTRU may decide to monitor / measure one or more candidate (predicted) beams, e.g., as in option 2.

[0161] In an example solution, the WTRU may propose, request, or report the results of the verification and the determined options, such as activating / deactivating the AI / ML model, to the base station or gNB. In one example, the WTRU may propose, request, or report the results and options as part of a CSI report, as a flag in HARQ-ACK, as a parameter in PUCCH, as a parameter in PRACH, or via uplink control information (UCI) in PUSCH.

[0162] 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 the use, activation, or deactivation of an AI / ML model. By way of example, the WTRU may decide to activate an AI / ML model, deactivate an 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.

[0163] For example, using the LOS indicator, the LOS probability, or both, the WTRU may deactivate the AI / ML model if the LOS probability is lower than a respective 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 and / or report the beam with the best LOS probability, the beam with the highest LOS probability, or both, among multiple beams, in the first frequency range, e.g., in FR1. The determined / reported beam may then be used for AI / ML beam prediction at the base station or gNB and / or the WTRU, such as in a second frequency range, e.g., in FR2.

[0164] In an example using an antenna panel configuration, the WTRU may deactivate the AI / ML model if there is not the same QCL Type-D assumption between the antenna ports, panels, or both (at the WTRU side) for the first and second frequency ranges, e.g., FR1 and FR2.

[0165] The WTRU may use other conditions for AI / ML activation / deactivation, such as the number of supported beams, beam properties, WTRU capabilities, or all of these. For example, using the number of supported beams, the WTRU may determine or be configured to use / activate the AI / ML model only for a range of beams within the first and second frequency ranges, e.g., FR1 and FR2.

[0166] For example, using beam properties, the WTRU, the gNB or base station, or both the WTRU and the gNB or base station, etc., may determine or be configured to activate the AI / ML model if one or more determined or configured parameters, such as the boresight of the antenna array, the beam direction of the antenna, or the antenna array configuration, for the first and second frequency ranges, are within an acceptable range. Otherwise, the WTRU may decide to deactivate the AI / ML model.

[0167] For example, using the WTRU capabilities, the WTRU may decide or be configured to activate the AI / ML model if it has one or more WTRU capabilities, e.g., processing time, antenna switching time, BWP switching time, etc. Otherwise, the WTRU may decide to deactivate the AI / ML model.

[0168] Examples of AI / ML model activation / retraining / deactivation / fallback options are provided herein. One or more of the following configurations may be used for the CSI / beam reporting configuration: A WTRU may be configured with one or more CSI reporting configurations. A WTRU may also be configured with one or more beam reporting configurations. The CSI reporting configuration may include one or more of the following: a reporting configuration type (e.g., periodic, semi-persistent on PUCCH, semi-persistent on PUSCH, or aperiodic); a 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); a reporting frequency configuration; a CQI format indicator such as wideband CQI or subband CQI; a PMI format indicator such as wideband PMI or subband PMI; a CSI reporting band; a time limit for channel measurement; a time limit for interference measurement; a codebook configuration; a group-based beam reporting; a CQI table; a subband size; a non-PMI port index; a reporting slot configuration / offset list; a CSI reporting periodicity and offset; one or more PUCCH resources for CSI reporting; a port index; or a combination of any or all of these.

[0169] One or more of the following configurations may be used for the measurement configuration of the CSI / beam report. The WTRU may be configured with one or more CSI measurement configurations. The WTRU may also 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, aperiodic trigger state list, semi-persistence on PUSCH trigger state list, associated CSI resource configuration, associated CSI reporting configuration, or any combination of all of these. Similar parameters may be included in the beam measurement configuration.

[0170] One or more of the following configurations may be used for the CSI resource configuration: The WTRU may be configured with one or more CSI resource configurations, which may include one or more of the following: a CSI resource configuration ID, one or more RS resource sets for channel measurements, one or more RS resource sets for interference measurements, bandwidth portion, or resource type, e.g., aperiodic, semi-persistent, or periodic.

[0171] In an example solution, the WTRU may trigger a procedure to activate / apply an AI / ML model, deactivate an AI / ML model, update / retrain an AI / ML model, or select one or more new beams. Activation of an AI / ML model may include one or more of the following: activating one or more RS resources / resource sets associated with the AI / ML model, activating one or more CSI reporting configurations associated with the AI / ML model, activating one or more measurement configurations associated with the AI / ML model, activating one or more CSI resource configurations associated with the AI / ML model, resetting / starting one or more counters associated with the AI / ML model, or resetting / starting one or more timers associated with the AI / ML model.

[0172] Deactivating the AI / ML model may include one or more of the following: deactivating one or more RS resources / resource sets associated with the AI / ML model, deactivating one or more CSI reporting configurations associated with the AI / ML model, deactivating one or more measurement configurations associated with the AI / ML model, deactivating one or more CSI resource configurations associated with the AI / ML model, resetting one or more counters associated with the AI / ML model, or resetting one or more timers associated with the AI / ML model.

[0173] The procedure for updating / retraining the AI / ML model or associated parameters / weights may include one or more of the following: sending a request / indication to update the AI / ML model or associated parameters / weights, resetting / starting one or more counters associated with the procedure, resetting / starting one or more timers associated with the procedure, 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 RSs / beams based on the updated AI / ML model and associated parameters / weights. The WTRU may select one or more RSs / beams based on quality. For example, the WTRU or the base station or the gNB may select one or more RSs / beams with the best quality.

[0174] The procedure for updating / retraining the AI / ML model or associated parameters / weights may further include one or more of the following: measuring one or more selected RSs / beams based on the updated AI / ML model and associated parameters / weights, indicating the one or more selected RSs / beams, or, if the procedure is not successful, indicating deactivation of the AI / ML model and / or fallback to a conventional beam management mechanism. In an example solution for indicating one or more selected RSs / beams, the WTRU or base station or gNB may indicate one or more selected RSs / beams. For example, the WTRU and / or base station or gNB may indicate one or more selected RSs / beams if the measured quality of the one or more selected RSs / beams is greater than or equal to (>=) a threshold.

[0175] Example solutions include indicating deactivation of the AI / ML model and / or fallback to conventional beam management mechanisms if the procedure is not successful. For example, the WTRU may determine that the procedure is not successful if one or more of the following conditions are met: a timer (if a timer associated with the procedure expires, the WTRU may determine that the procedure is not successful), a counter (the WTRU may increment a counter when it measures a candidate RS and / or the measured quality of the candidate RS is less than one or more first thresholds, and if the counter is greater than a second threshold, the WTRU may determine that the procedure is not successful), or measured quality (if the measured quality of one or more candidate beams is less than a threshold, the WTRU may determine that the procedure is not successful).

[0176] The procedure 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 procedure, resetting / starting one or more timers associated with the procedure, monitoring / measuring the candidate beams / RS, selecting one or more RSs / beams, indicating one or more selected beams, or, if the procedure is not successful, indicating deactivation of the AI / ML model and / or fallback to conventional beam management mechanisms. In one example of selecting one or more RSs / beams, the WTRU may select one or more beams based on quality. For example, the WTRU or the base station or gNB may select one or more RSs / beams with the best quality.

[0177] In one example of indicating one or more selected beams, the WTRU may indicate the one or more selected beams to the base station or gNB. Further, the WTRU may indicate the one or more beams by transmitting one or more UL resources. The one or more UL resources may be one or more of the following: PRACH (e.g., the WTRU may transmit one or more PRACHs (e.g., in PRACH resources associated with 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 procedure 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). Further, the WTRU may receive a confirmation from the base station or gNB. For example, the WTRU may receive one or more PDCCHs within one or more CORESETs / search spaces associated with, for example, the procedure.

[0178] In another example of indicating one or more selected beams, the base station or gNB may indicate one or more selected beams to the WTRU, for example, via one or more of RRC, MAC CE, and DCI. Further, the WTRU may receive an indication based on one or more of the following: TCI state or beam index. In an example of receiving a TCI state, the WTRU may receive an indication of one or more TCI states associated with the selected beam. In an example of receiving a beam index, the WTRU may receive an indication of one or more beam indices associated with the selected beam.

[0179] In one example of indicating deactivation of the AI / ML model and / or fallback to conventional beam management mechanisms if the procedure is not successful, the WTRU may determine that the procedure is not successful if one or more of the following conditions are met: timer, counter, or measured quality. For example, if a timer associated with the procedure expires, the WTRU may determine that the procedure is not successful. In a counter example, the WTRU may increment a counter when the WTRU measures a candidate RS and / or the measured quality of the candidate RS is less than one or more first thresholds. If the counter is greater than a second threshold, the WTRU may determine that the procedure is not successful. In a measured quality example, the WTRU may determine that the procedure is not successful if the measured quality of one or more candidate beams is less than (<) a threshold.

[0180] Activation of an AI / ML model, deactivation of an AI / ML model, updating / retraining of an AI / ML model and associated parameters / weights, and triggering a new beam selection procedure may be based on one or more of the following: a base station or gNB indication, or a WTRU indication. In an example solution, the WTRU may receive one or more indications, e.g., RRC signaling, MAC CE, or DCI, from the 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 procedure. The indication may be based on one or more of the following: an explicit indication, or an indication based on one or more configurations associated with one or more AI / ML models.

[0181] In one example of an explicit indication, the WTRU may receive an indication of activation / deactivation or triggering of an update procedure for one or more AI / ML models or trigger beam selection procedure. The explicit indication may include one or more of the following:

[0182] For example, the WTRU may receive an indication of a procedure type, for example, the WTRU may receive one or more of an activation, a deactivation, an update, or a new beam selection.

[0183] The indicator may include an instruction to trigger an AI / ML model procedure update. For example, a 1 bit may indicate to trigger an AI / ML model procedure update. For example, if the bit is "1", a procedure update may be triggered. If the bit is "0", a procedure update may not be triggered.

[0184] The indicator may include an indicator to trigger a new beam selection procedure. For example, a 1 bit may indicate that a new beam selection procedure is to be triggered. For example, if the bit is "1", a new beam selection procedure may be triggered. If the bit is "0", a new beam selection procedure may not be triggered.

[0185] 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 a new beam selection is triggered, the explicit indication may not include an AI / ML model ID.

[0186] The index may include a bitmap of AI / ML models. For example, each bit in the bitmap may be associated with a respective 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. When a new beam selection is triggered, the explicit index may not include a bitmap of AI / ML models.

[0187] In one example, the indication may be based on one or more configurations associated with one or more AI / ML models. For example, the WTRU may receive an activation / deactivation / update indication for one or more configurations. For example, if the WTRU receives an activation indication 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 a deactivation indication 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 update indication 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 a 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 the following: a CSI reporting configuration, a measurement configuration, a CSI resource configuration, an RS resource configuration, and / or an RS resource set configuration.

[0188] The following include examples of activating an AI / ML model, deactivating an AI / ML model, updating / retraining an AI / ML model and associated parameters / weights, and triggering a new beam selection procedure based on a WTRU's indicator. In an example solution, the WTRU may indicate a preferred mode, e.g., one or more of activation, deactivation, update, and new beam selection, to the base station or gNB. The indicator may be based on one or more of the following: an explicit indicator for all AI / ML models, an indicator per AI / ML model, an indicator per configuration, or a quality measurement.

[0189] The WTRU may explicitly indicate a preferred mode for all AI / ML models. For example, a single bit of information may be used to indicate activation / deactivation. For example, 1 may indicate activation of all AI / ML models or activation of the AI / ML mode, and 0 may indicate deactivation of all AI / ML models or deactivation of the AI / ML mode. For example, a single 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 no update of all AI / ML models. For example, a single bit of information may be used to trigger a new beam selection procedure. 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 no selection of one or more new beams / RSs.

[0190] 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 no update of the AI / ML model associated with the indication. For example, 1 may indicate selection of one or more new beams, a new RS, or both for the AI / ML model associated with the indication, and 0 may indicate no selection of one or more new beams, a new RS, or both for the AI / ML model associated with the indication.

[0191] The WTRU may indicate a preferred mode per configuration or 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 no update of the AI / ML model associated with the configuration. 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 no selection of one or more new beams, new RSs, or both for the AI / ML model associated with the configuration. A configuration may be one or more of the following: a CSI reporting configuration, a measurement configuration, a CSI resource configuration, an RS resource configuration, or an RS resource set configuration.

[0192] In an example solution, the WTRU may activate / deactivate / update one or more AI / ML models or trigger a new beam selection procedure based on one or more measured qualities. In an example solution, the procedures may be based on a threshold and a quality measurement, e.g., a quality reported to the base station or gNB for each procedure. For example, if the measured quality is greater than or equal to (≧) the threshold, the WTRU may indicate and / or decide to activate the AI / ML model. If the measured quality is less than (<) the threshold, the WTRU may indicate and / or decide to deactivate the AI / ML model.

[0193] For example, if the measured quality is above (≧) a threshold, the WTRU may indicate and / or decide not to update the AI / ML model. If the measured quality is below (<) a threshold, the WTRU may indicate and / or decide to update the AI / ML model. In another example, if the measured quality is above (≧) a threshold, the WTRU may indicate / decide not to update the AI / ML model. If the measured quality is below (<) a threshold, the WTRU may indicate / decide not to update the AI / ML model.

[0194] In an example solution, the procedure may be based on two or more thresholds and quality measurements. For example, if the measured quality is greater than or equal to (≧) a first threshold, the WTRU may indicate and / or decide to activate the AI / ML model. If the second threshold is less than (<) the measured quality, i.e., less than (<) the first threshold, the WTRU may trigger / indicate / decide a new beam selection procedure. If the measured quality is less than (<) the second threshold, the WTRU may indicate and / or decide to deactivate the AI / ML model.

[0195] For example, if the measured quality is greater than or equal to (≧) a first threshold, the WTRU may indicate and / or decide to activate an AI / ML model. If the second threshold may be less than (<) the measured quality, i.e., less than (<) the first threshold, the WTRU may trigger / indicate / decide to perform an AI / ML update procedure. If the measured quality is less than (<) the second threshold, the WTRU may indicate and / or decide to deactivate an AI / ML model.

[0196] In an example solution, the procedure may be based on two or more quality measurements and two or more thresholds. For example, if a first measured quality, e.g., RSRP, RSRQ, SINR, MCS, or CQI, is greater than or equal to (≧) a first threshold and a second measured quality, e.g., the probability of LOS, is greater than or equal to (≧) a second threshold, the WTRU may indicate and / or decide to activate an AI / ML model. If the first measured quality, e.g., RSRP, RSRQ, SINR, MCS, or CQI, is less than (<) the first threshold and a second measured quality, e.g., the probability of LOS, is greater than or equal to (≧) a second threshold, the WTRU may indicate and / or decide to update an AI / ML model. If a first measured quality, e.g., RSRP, RSRQ, SINR, MCS, or CQI, is less than (<) a first threshold and a second measured quality, e.g., LOS probability, is less than (<) a second threshold, the WTRU may indicate, decide, or both, to deactivate the AI / ML model, trigger a new beam selection procedure, or both.

[0197] If the WTRU reports more than one measured quality, the WTRU may indicate triggering of an activation / deactivation / new beam selection procedure based on one or more of the following: an indicator for each measured quality, an indicator for all measured qualities, or both. The WTRU may indicate triggering of an activation / deactivation / new beam selection procedure for each measured quality. The WTRU may indicate triggering of an activation / deactivation / new beam selection procedure for all measured qualities. The WTRU may determine triggering of an activation / deactivation / new beam selection procedure based on one or more of the following. For example, the WTRU may determine triggering of an activation / deactivation / new beam selection procedure based on an average. Further, in one example where the WTRU may average all measured qualities, the WTRU may determine triggering of an activation / deactivation / new beam selection procedure, and the WTRU may indicate activation if the average quality is greater than (>=) a threshold. The WTRU may also determine a trigger for an activation / deactivation / new beam selection procedure based on the number of measured qualities greater than (>=) a threshold. Furthermore, the WTRU may determine a trigger for an activation / deactivation / new beam selection procedure, where the WTRU may indicate activation if the number of measured qualities is greater than or equal to (>) a threshold.

[0198] In an example solution, the WTRU may receive a confirmation of the WTRU index / decision. For example, the WTRU may receive a PDCCH within one or more CORESETs / search spaces associated with the WTRU index. In another example, the WTRU may receive a confirmation message via one or more of RRC signaling, MAC CE, or DCI.

[0199] Provided herein are examples of methods for determining or obtaining the accuracy of an AI / ML model. The terms 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 terms frequency domain 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.

[0200] The WTRU may determine the effectiveness or accuracy of the AI / ML model. The WTRU may be configured with resources to perform measurements to determine the effectiveness of the AI / ML model. The resources may be in one or more frequency domains. For example, the AI / ML model may take input from a first frequency domain and determine behavior in a second frequency domain. To determine the effectiveness of the AI / ML model, the WTRU may be configured with measurement resources in the first frequency domain or the second frequency domain.

[0201] The WTRU may determine whether the behavior of the second frequency domain determined from the AI / ML model matches the behavior of the second frequency domain determined from the measurement resources in the second frequency domain. In one example, the WTRU may be configured with a periodic or sparse reference signal in the second frequency domain to perform a legacy, e.g., 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 domain.

[0202] The effectiveness or accuracy of an AI / ML model may be determined by at least one of the performance of associated features, statistical performance of associated features, performance of frequency domain transmissions of features associated with the AI / ML model, comparison of legacy results with AI / ML results, measurements and / or failure counters. In an example, the effectiveness or accuracy of an AI / ML model may be determined by the performance of associated features.

[0203] For example, an AI / ML model may be used to support or provide feedback or enable a function. The function may include one or more of 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 validity of the AI / ML model based on the performance of the associated function. The WTRU may be configured with a metric for determining the performance of the associated function. For example, the WTRU may be configured with an AI / ML model that supports beam management. The WTRU may be configured with a metric such as determining the best beam. If the AI / ML model determines the best beam, the AI / ML model may be considered valid.

[0204] Effectiveness metrics associated with beam management may include at least one of the following: The metric may include a best beam prediction. For example, an AI / ML model predicts the best beam. The metric may include a predicted beam measurement within a threshold offset from the best beam. In one example, the threshold may be configurable. In another example, the threshold offset may be used to compare RSRP measurements. The metric may include the N predicted best beams that match at least the M actual best beams. The metric may include a beam failure detection rate.

[0205] In an example, the effectiveness or accuracy of an AI / ML model may be determined by the statistical performance of an associated function. For example, a WTRU may qualify as an AI / ML model if the AI / ML model meets the metric of the associated function a percentage of times over a period of time.

[0206] In an example, the effectiveness or accuracy of an AI / ML model may be determined by performance of transmission in a frequency domain of a function associated with the AI / ML model. For example, the WTRU may determine the effectiveness of an AI / ML model having an associated function in a second frequency domain based on performance of transmission in the second frequency domain. The performance of transmission may be determined based on at least one of BLER, virtual PDCCH BLER, HARQ-ACK / negative ACK (NACK) performance or ratio, latency, throughput, spectral efficiency, outage probability, etc.

[0207] In an example, the effectiveness or accuracy of an AI / ML model may be determined by comparing the AI / ML results with legacy, e.g., non-AI / ML-based, results. For example, the WTRU may perform frequency domain measurements of the associated function to compare with the output of the AI / ML model. The WTRU may determine the effectiveness 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, e.g., applicable frequency domain measurements using legacy methods.

[0208] In an example, the effectiveness or accuracy of an AI / ML model may be determined by measurements. For example, the WTRU may determine the effectiveness based on measurements performed on the RS. The measurements may include at least one of RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, channel occupancy (CO), probability of LOS, Doppler shift, Doppler spread, mean delay, or delay spread. The WTRU may compare at least one measurement to one or more thresholds to determine the accuracy or effectiveness of the model.

[0209] In an example, the effectiveness or accuracy of an AI / ML model may be determined by 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. In another example, the WTRU may count the number of times a prediction is off by more than a (possibly configurable) threshold. The counter may be valid for a period of time. At the end of the period, the counter may be reset. The period may be fixed or configurable. The WTRU may start or restart the period if a failure occurs.

[0210] The WTRU may stop the period or reset the counter if N (N is configurable) outputs of the AI / ML model are deemed accurate, e.g., if the predictions are within a configurable threshold from the actual value. The WTRU may determine the accuracy or effectiveness of the AI / ML model based on the counter value when the period has elapsed. In another example, the WTRU may determine the accuracy or effectiveness of the AI / ML model based on a failure counter reaching a particular value. For example, if the failure counter reaches X, the WTRU may consider the model invalid.

[0211] The WTRU may report the validity of the AI / ML model to the base station or gNB. The WTRU may report one of two states: valid or invalid. In another example, the WTRU may report an accuracy metric of the AI / ML model. The accuracy metric may indicate a validity value for the AI / ML model. The validity value may provide an accuracy parameter of the AI / ML model.

[0212] The validity of the AI / ML model may be reported on a PUCCH resource, a PUSCH resource, a RACH, an RRC message, or a MAC CE. The validity of the AI / ML model may be reported using a new message. In another example, the validity of the AI / ML model may be reported implicitly, for example, by the WTRU indicating a failure of an associated function, for example, the detection of a beam failure. Such a failure report may include a new element indicating that the cause of the failure is due to the AI / ML model being no longer valid.

[0213] The WTRU may request resources, e.g., DL reference signals, to determine the validity of the AI / ML model. The WTRU may indicate to the base station or gNB the type of resources needed, the AI / ML model, e.g., the AI / ML model index, and associated capabilities.

[0214] The WTRU may be configured to determine the accuracy of the ML model. The configuration may include a set of periodic time instances during which the WTRU may determine the accuracy of the AI / ML model. The configuration may also include, for example, reporting resources associated with one or more periodic time instances during which the WTRU may report the accuracy of the AI / ML model.

[0215] 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.

[0216] The WTRU may be triggered to determine the accuracy of the AI / ML model by at least one of time, a timer, receipt of an RS signal, an indication from a base station or gNB, performance of a function associated with the AI / ML model, performance of a frequency domain transmission of a function associated with the AI / ML model, detection of a beam failure or determination of a radio link failure, cell activation or deactivation, a BW change, a cell change, a measurement, and / or a failure counter.

[0217] 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 at a particular time instance, such as a slot, subframe, or symbol.

[0218] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by 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 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 performance of a function associated with the AI / ML model. For example, if an AI / ML model is used for beam prediction, the WTRU may start or restart the timer if it determines that the prediction is within a required range.

[0219] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by receiving an RS signal. For example, the WTRU may be triggered to determine the accuracy of the AI / ML model based on receiving an RS intended to determine the accuracy of the AI / ML model.

[0220] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by the performance of a function associated with the AI / ML model. For example, if the AI / ML model is used for beam prediction, the WTRU may be triggered to determine the accuracy of the AI / ML model if the prediction is determined to be outside of an acceptable range. Other examples of the performance of a function associated with an AI / ML model from the section regarding determining the validity or accuracy of an AI / ML model may be applicable here.

[0221] In an example, the WTRU may be triggered to determine the accuracy of an AI / ML model by performance of transmission in a frequency domain of a feature associated with the AI / ML model. For example, the WTRU may be triggered to determine the effectiveness or accuracy of an AI / ML model having an associated feature in a second frequency domain based on performance of transmission in the second frequency domain. The performance of the transmission may be determined based on at least one of BLER, a virtual PDCCH BLER, HARQ-ACK / NACK performance or ratio, latency, throughput, spectral efficiency, outage probability, etc.

[0222] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by a cell change. In one example, the cell change may be from a cell handover (HO). In another example, the cell change may be from a cell selection. In a further example, the cell change may be from a cell reselection.

[0223] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by measurements. For example, the WTRU may be triggered to perform a determination of the accuracy of the AI / ML model based on measurements on the RS. The measurements may include at least one of RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, CO, probability of LOS, Doppler shift, Doppler spread, mean delay, or delay spread.

[0224] In an example, the WTRU may be triggered to determine the accuracy of the AI / ML model by 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. In another example, the WTRU may count the number of times a prediction is off by more than a (possibly configurable) threshold. The counter may be valid for a period of time. At the end of the period, the counter may be reset. The period may be fixed or configurable. The WTRU may start or restart the period if a failure occurs.

[0225] The WTRU may stop the period or reset the counter if N (N is configurable) outputs of the AI / ML model are deemed accurate, e.g., if the predictions are within a configurable threshold from the actual value. The WTRU may be triggered to perform a determination of the accuracy of the AI / ML model based on the counter value when the period has elapsed. In another example, the WTRU may be triggered to perform a determination of the accuracy or validity of the AI / ML model based on a failure counter reaching a particular 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.

[0226] In an example, the WTRU may engage in the following behaviors when determining the accuracy of an AI / ML model: The WTRU may determine an appropriate behavior based on the determined accuracy or validity of the AI / ML model. The WTRU behavior may depend on the method used to determine the accuracy or validity of the AI / ML model. The WTRU behavior may be determined as a function of one or more of measurements or combinations of measurements compared to thresholds. Measurements may be triggered based on the determination of the accuracy or validity of the AI / ML model. The measurements may include at least one of BLER, virtual PDCCH BLER, RSRP, RSSI, RSRQ, CSI, CQI RI, PMI, LI, CRI, CO, probability of LOS, Doppler shift, Doppler spread, average delay, or delay spread. The WTRU behavior may include at least one of continuing to use the AI / ML model, selecting a secondary output of the AI / ML model, updating or training the AI / ML model, and / or ceasing to use the AI / ML model and using or falling back to a legacy method for the associated functionality.

[0227] Examples herein include cases 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. The WTRU may consider the AI / ML model to be accurate if its accuracy is greater than a threshold.

[0228] Examples herein include cases where the WTRU's behavior includes selecting a secondary output of an AI / ML model. For example, if the AI / ML model is deemed accurate on average but inaccurate for a particular outcome, the WTRU may select the secondary output, if available.

[0229] As an example, if for a beam resource predicted at FR2, the probability of LOS is higher than a first threshold, e.g., LOS_th, and the derived CQI is lower than a respective threshold, e.g., CQI_th, the WTRU may update or retrain the AI / ML model. As another exemplary embodiment, if for a beam resource predicted at FR2, the probability of LOS is lower than a first threshold, e.g., LOS_th, and the derived CQI is lower than a respective threshold, e.g., CQI_th, the WTRU may decide, e.g., based on the determined LOS probability, to either select a second output of the AI / ML model or fall back to legacy operation.

[0230] The ML model for beam selection and / or prediction may reside in the WTRU and / or the network. In a first exemplary solution in which the ML model resides in the WTRU, the WTRU may be configured with one or more use cases for which the ML model may be used, which may include, for example, a subset of one or more use cases. The WTRU may also be configured to perform 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 include any one or more of the following: LOS / NLOS indicator / probability, changes in LOS / NLOS indicator / probability, signal-to-noise ratio (SNR) / SINR measurement / calculation, additional channel measurements or changes in channel measurements, number of supported FR1 and FR2 beams, changes in bandwidth part (BWP), WTRU capabilities, network assistance, antenna panel configuration at the WTRU, other antenna parameters, and / or model validity / accuracy.

[0231] Examples are provided herein that include a WTRU using an LOS / NLOS indicator / probability 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, and find the beam with the best LOS probability so that it is more likely to exceed a preconfigured LOS probability. In such a scenario, the WTRU may use only the FR1 beam with the best LOS probability, such as above a preconfigured threshold, as input to the ML model.

[0232] In one example, the WTRU may determine that for any of the CSI-RS resources, the LOS indicator is negative or the probability of LOS is below a preconfigured threshold. The WTRU may decide to deactivate the AI / ML model and rely on legacy beam management procedures. In one example, the WTRU may make the decision based on historical poor performance of the ML model in NLOS scenarios previously observed by the WTRU.

[0233] Examples are provided herein that include a WTRU using changes in LOS / NLOS indicators / probabilities to determine whether to use an ML model. In one example, the WTRU may decide to activate / deactivate the ML model based on changes in LOS / NLOS conditions. For example, if the LOS indicator goes from "1" to "0," indicating loss of LOS, the WTRU may decide to deactivate the ML model and revert to legacy beam management procedures.

[0234] In another example, the WTRU may measure a sudden drop in LOS / NLOS probability below a threshold pre-configured by the WTRU or the base station or gNB, which may trigger the WTRU to deactivate the use of the ML model and switch to legacy beam management procedures.

[0235] Examples are provided herein that include a WTRU using SNR / SINR measurements / calculations to determine whether to use an ML model. The WTRU may be configured to perform / calculate SNR / SINR measurements, such as SS-SINR, CSI-SINR, etc. The WTRU may decide 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 above the threshold may trigger the WTRU to switch to legacy procedures, which in one example may be legacy beam management procedures.

[0236] In another example, the WTRU may be configured with a second frequency range, e.g., FR2, an SNR / SINR range in which the use of the ML selection / prediction model provides the best output for beam prediction based on measurements input in the first frequency range, e.g., FR1. An SNR / SINR measurement / calculation outside the pre-configured range may trigger the WTRU to deactivate the ML model and revert to a conventional framework, which in one example may be a conventional beam management framework.

[0237] Examples are provided herein that include a WTRU using additional channel measurements, such as channel coherence time, channel coherence bandwidth, Doppler spread, BLER, or changes in channel measurements, to determine whether to use an ML model. The WTRU may perform additional channel measurements, such as channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc. The channel condition measurements and / or changes in the measurements may constitute a trigger for using or not using an ML model.

[0238] In one example, if the WTRU measures and records a large channel coherence time that exceeds a configured or preconfigured threshold, it may indicate a slow-fading channel, and the WTRU activates an ML model that predicts the best FR2 beam based on FR1 beam information / measurements. In another example, if the channel coherence time is lower than a preconfigured threshold, the FR2 prediction model may perform poorly due to fast-fading conditions. In this case, the WTRU may deactivate the model and resort to traditional methods for FR2 beam selection.

[0239] In one example, the WTRU may measure a sudden change in any one of the channel parameters, such as channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc. In one example, a change in channel coherence time from a large measured value to a small value may signify a sudden deterioration in channel conditions such that the WTRU determines that the channel conditions are no longer valid / stable enough to use the FR2 beam ML predictor and therefore reverts / falls back to the legacy method of FR2 beam selection.

[0240] In one example, the WTRU may be configured with a range corresponding to any one of the channel parameters, e.g., channel coherence time, channel coherence bandwidth, Doppler spread, BLER, etc., such that the WTRU may decide to activate the FR2 beam selection / prediction ML model only when the channel measurements are within the configured / preconfigured / determined range.

[0241] An example is provided herein that includes a WTRU using the number of supported FR1 and FR2 beams to determine whether to use an ML model. The WTRU may activate / deactivate the ML model based on the number of beams supported in the first and second frequency ranges. In one example, a low number of supported beams in the second frequency range, e.g., FR2, may trigger the WTRU to deactivate the beam ML model for prediction in the second frequency range, e.g., FR2, because the WTRU may determine that a legacy measurement method selects the best FR2 beam with a lower number of supported beams. In such a scenario, the minimum number of supported beams in the second frequency range, e.g., FR2, that will trigger the use of the ML model may be determined by the WTRU through historical data, e.g., historical validation of the accuracy of the ML model assessed against the number of supported FR2 beams.

[0242] An example is provided herein that includes a WTRU using a BWP change to determine whether to use an ML model. The WTRU may decide to deactivate the ML model after changing / switching the BWP. In one example, when the WTRU changes / switches the BWP due to the expiration of a timer, the WTRU may determine that the model is no longer suitable for the new BWP.

[0243] Examples are provided herein including a WTRU that uses WTRU capabilities to determine whether to use an ML model. The WTRU may determine to use an ML model based on the WTRU capabilities. In one example, a WTRU with reduced capability and / or a non-ML-capable WTRU may not be configured with any ML model and may need to use legacy methods, such as legacy methods of beam selection. In another example, a less capable WTRU may be able to use an ML model for current beam selection / decision in a second frequency range, e.g., FR2, based on beam measurements in a first frequency range, e.g., FR1, but may not be able to predict future beams based on the current measurements, e.g., as a result of the WTRU making fewer measurements compared to the larger number of measurements that a WTRU with four receive antennas would make. In one example, the less capable WTRU may be a WTRU with two receive antennas compared to four receive antennas.

[0244] Examples are provided herein that include a WTRU using network assistance to determine whether to use an ML model. The network may send assistance to the WTRU regarding an indication of when the WTRU can activate an ML model. During registration, the network may send a "WTRU Capability Inquiry" to the WTRU, specifying which capabilities 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 that reports "1" if the WTRU is configured with an ML model and "0" otherwise, or may report additional parameters, such as an SNR range over which the ML model is activated in the WTRU. Assistance may be provided to the WTRU on when to activate each ML model based on base station or gNB measurements, such as on channel conditions.

[0245] An example is provided herein that includes a WTRU using an antenna panel configuration to determine whether to use an ML model. In one example, the antenna panel configurations between antenna ports of a first and second frequency range may be incompatible, such that measurements taken in a first frequency range, e.g., FR1, may not result in the best beam selection in a second frequency range, e.g., FR2. For example, there may not be the same QCL Type-D assumptions between antenna ports and / or panels for different frequency ranges, e.g., on the WTRU side. The WTRU may decide to deactivate the ML prediction model and revert / fall back to a legacy procedure, such as a legacy beam selection procedure.

[0246] Examples are provided herein that include a WTRU using other antenna parameters to determine whether to use an ML model. The WTRU may decide to activate / deactivate / retrain the ML model based on one or more of the other antenna parameters, such as the boresight of the antenna array, the beam direction of the antenna, or the antenna array configuration of the first and / or second frequency ranges at the WTRU and / or the base station or gNB. 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 the ML model, for example, because the model may need to be retrained with a new beam direction.

[0247] Examples are provided herein that include a WTRU using model effectiveness / accuracy to determine whether to use an ML model. The WTRU may activate / deactivate an ML model based on the model effectiveness / accuracy, which the WTRU may determine through any of the methods described elsewhere in the embodiments and examples herein. The activation / deactivation of the ML model may be triggered by any of the triggers described elsewhere in the embodiments and examples herein.

[0248] In any use case involving a determination that one method of beam selection / prediction is no longer valid, leading to a switch from another method of beam selection / prediction, e.g., an ML model, to legacy (beam management) procedures, the WTRU may be configured with procedures for a smooth transition. In one example, the temporary procedures may involve triggering a time window after the WTRU decides to transition to legacy procedures, to allow time for measurements, such as SS and / or CSI-RS measurements and / or SRS, to be made / sent / reported to the base station or gNB, before the ML model is deactivated.

[0249] In an example solution where the ML model resides in the base station or gNB, the WTRU may provide feedback / reporting to the base station or gNB regarding the accuracy / quality of the beam selected by the base station or gNB, e.g., in UCI. After feedback from the WTRU, the base station or gNB may decide whether to continue using the ML model for beam selection / prediction, deactivate the ML model, retrain the ML, or revert / fall back to legacy / non-ML methods for beam selection, etc.

[0250] In one example, the WTRU may be configured with the base station or gNB to perform RSRP measurements on a beam selected by the ML model in a second frequency range, e.g., FR2, which may be based on data / information input / reported in a first frequency range, e.g., FR1, from the WTRU. If the WTRU measures an RSRP value below a threshold, the WTRU may report the measurement to the base station or gNB and may fall back to legacy (beam management) procedures. In one example, the threshold may be one or more of configured, pre-configured, determined, or predetermined by the WTRU or the base station or gNB.

[0251] In one example, the WTRU may be configured to perform additional measurements at the beginning of a validation period when an ML model is used at the base station or gNB, particularly 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 to report channel measurements only when the channel measurements are above / below a (pre-)configured / determined threshold by the network, or to report changes in channel measurements only when they are below / above a (pre-)configured / determined threshold.

[0252] Provided herein are embodiments and examples of dynamic retraining / updating of AI / ML models. Further provided herein are examples of iterative retraining / updating of AI / ML models based on predicted AI / ML beam outputs.

[0253] An example aspect of AI / ML model configuration is provided herein. A WTRU may be configured with an AI / ML model to perform prediction of beam resources and / or beam resource properties associated with a second frequency band, e.g., FR2, based on beam resources and / or beam resource properties in a first frequency band, e.g., FR1. Here, the beam resources may consist of TCI conditions, CSI-RS, or SSB for the downlink, and SRS resources or TCI conditions for the uplink. As used herein, beam resource properties 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. In an example solution, the WTRU may apply the measured AI / ML model to the FR1 beam resource properties as input and obtain the best beam resources and / or beam resource properties associated with FR2 as output. In one example, for a first frequency band, e.g., FR1, the beam resource properties may include one or more of RSRP, CSI, PMI, CIR, probability of LoS, and the like.

[0254] In an example solution, the WTRU may be configured to report the output of the AI / ML model to a base station or gNB. For example, the WTRU may measure the FR1 beam resource, apply it as an input to the AI / ML model, obtain a predicted RSRP for the FR2 beam resource as an output from the AI / ML model, and report the predicted RSRP for the FR2 beam resource to the base station or gNB.

[0255] Examples of monitoring / verifying the accuracy of an AI / ML model are provided herein. A WTRU may be configured to determine the accuracy of an ML model. The mechanism for determining the accuracy of an 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 and / or radio link failure determination, mobility, measurement reporting, etc. For example, the WTRU may compare predicted FR2 beam resource values, e.g., from the output of an AI / ML model, with actual FR2 beam resource values, e.g., based on measurements of the FR2 beam resource. In embodiments and examples elsewhere herein, several example methods for determining the accuracy of an AI / ML model are described.

[0256] In an example solution, the WTRU may be configured with an accuracy threshold for operation of the AI / ML model. For example, such an accuracy threshold may be semi-statically configured via RRC configuration. In one possible example, such an accuracy threshold may be signaled as part of the AI / ML model configuration. In another example, the accuracy threshold may be signaled in a MAC control element. In some cases, such an accuracy threshold may be signaled along with an activation command for the AI / ML model. When the model is active, the WTRU may be configured to monitor the accuracy of the AI / ML model. In some cases, such monitoring may be performed for a preconfigured period of time. In an example solution, if the accuracy of the AI / ML model does not meet the preconfigured accuracy threshold, the WTRU may autonomously deactivate the AI / ML model and send a report to the network. In some cases, the WTRU may be configured to fall back to legacy methods for functions performed by the AI / ML model. In some cases, the WTRU may initiate retraining of the AI / ML model.

[0257] 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 upon completion of the retraining procedure. In another example solution, the WTRU may restart the timer upon successful execution of AI / ML model retraining via 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 activation.

[0258] 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 the accuracy of the AI / ML model. 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 embodiments and examples provided elsewhere herein. If the determined accuracy falls below 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 the performance of the AI / ML model based on, for example, metrics associated with features enabled by the AI / ML model. For example, the performance metrics may include one or more of the following: BLER performance on FR2 beams reported 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, L1, CRI, RSRP); etc.

[0259] In another example solution, the trigger may be based on a change in a configuration aspect. For example, the configuration aspect may include RS configuration, bandwidth portion configuration, SCell configuration, etc. In yet another example solution, the trigger may be based on a mobility event. For example, the mobility event may include a serving cell / TRP change due to HO / conditional handover (CHO) / dual active protocol stack (DAPS) handover, radio link failure (RLF), etc. In an example solution, the trigger condition may be based on a network command. For example, the WTRU may receive an implicit or explicit indication in a deactivation command associated with an AI / ML model, and the deactivation command may indicate that the WTRU should retrain the AI / ML model. In a possible example, the deactivation command may additionally indicate the configuration of resources applicable for retraining.

[0260] Examples of iterative procedures for training, retraining, or both of an AI / ML model are provided herein. When one or more triggers for training, retraining, or both of an AI / ML model are met, the WTRU may indicate to the network that a retraining procedure has been triggered and may further provide a reason for the retraining. For example, the reason may be expressed as a cause value, and different code points within the cause value may be associated with different trigger conditions. In a possible example, the indicator may include an AI / ML performance and / or accuracy value. In some cases, the WTRU may include assistance information to enable the network to configure resources for retraining. For example, the assistance information may include one or more of the number of beam resources for retraining, periodicity, density of RSs in the frequency domain, etc.

[0261] The WTRU may train, retrain, or both, the AI / ML model based on configuration parameters received from the base station or gNB. For example, such configuration parameters may include one or more of a configuration of FR1 beam resource(s), a configuration of FR1 beam resource(s) properties, a configuration of FR2 beam resource(s), a configuration of FR2 beam resource(s) properties, a configuration of FR2 beam resource(s), a configuration of a loss function including parameterization, thresholds, etc. For example, the loss function may be associated with a metric indicative of the difference between the predicted FR2 beam resource(s) and the actual FR2 beam resource(s), such as a cross-entropy loss, a hinge loss, a squared hinge loss, a mean squared error, etc.

[0262] In an example solution, the WTRU may determine that the retraining was successful based on preconfigured criteria and indicate completion of the retraining to the base station or gNB. For example, the WTRU may determine that the retraining is complete if the accuracy of the AI / ML model after retraining exceeds a preconfigured threshold.

[0263] In an example solution, the WTRU may be configured to iteratively retrain the AI / ML model until the model output is updated. For example, the WTRU may be configured to use measured CSI parameters, such as CQI, PMI, CIR, etc., in retraining / updating the beam prediction of the AI / ML model and may determine one or more best FR2 beams, for example, based on RSRP. When the model retraining results in a different output, e.g., a predicted FR2 beam that differs from the AI / ML model before retraining, the WTRU may determine that retraining is complete. The WTRU may be configured to indicate the success of the retraining to the network via a MAC control element, pre-configured PUCCH resources, or preamble resources. The WTRU may optionally indicate the accuracy value of the AI / ML model in the retraining success indicator.

[0264] In an exemplary solution, the WTRU may determine that retraining is unsuccessful based on preconfigured criteria. For example, if retraining is not successful within a preconfigured period, the WTRU may declare a retraining failure. For example, if the accuracy of the AI / ML model does not improve beyond a preconfigured accuracy threshold, the WTRU may declare a retraining failure. For example, if the model output before and after retraining results in the same output, e.g., the same predicted FR2 beam, the WTRU may declare a retraining failure. For example, if the beam resources configured for training are no longer available, e.g., the beam resources are released / deactivated by the network or due to blockage or WTRU mobility, and the accuracy of the AI / ML model is still below the preconfigured accuracy threshold, the WTRU may declare a retraining failure. If retraining fails, the WTRU may deactivate the AI / ML model (if active) and fall back to a conventional beam management mechanism. The WTRU may be configured to send an indication of retraining failure to the network via a MAC control element. In another example solution, the WTRU may transmit an indication of retraining failure over a pre-configured PUCCH resource or a pre-configured preamble resource.

[0265] 3 is a flowchart illustrating an example of a verification procedure for beam prediction based on hierarchical spatial relationships. In the example shown in flowchart 300, a WTRU performs measurements on parameters of a first set of beam resources, and then the WTRU may predict beam resources from a second set of beam resources based on the measured parameters of the first set of beam resources (310). In one example, a base station may transmit to the WTRU using the first set of beam resources. The WTRU may then report the predicted beam resources. In one example, the WTRU may report these predicted beam resources to the base station.

[0266] In a further example, the WTRU may receive one or more thresholds for accuracy verification (315). These thresholds may be used in measuring the first set of beam resources. In an example, the thresholds for accuracy verification may include one or more of a CQI threshold, an RSRP threshold, an SINR threshold, a probability of LOS threshold, a hypothetical BLER threshold, etc. The WTRU, in one example, may receive the one or more thresholds from the base station.

[0267] Further, the WTRU may receive one or more signals on one or more channels based on the beam resources in the second set of beam resources (320). The WTRU may also 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.

[0268] The one or more signals may include one or more PDCCH signals (325) in one example. Also, the one or more signals may include one or more PDSCH signals. In another example, the one or more signals may include one or more CSI-RS. Similar signals may be received in other examples. Furthermore, the one or more channels may include one or more PDCCHs. Additionally, the one or more channels may include one or more PDSCHs. Similar channels may be used for reception in other examples.

[0269] The WTRU may further perform a validation procedure to determine whether one or more measured accuracy parameters are within an acceptable range (330). If the one or more measured accuracy parameters are within an acceptable range, the WTRU may determine that the AI / ML model is valid (340). Further, if the AI / ML model is determined to be valid, the WTRU may activate use of the AI / ML model to predict the best beam. In an additional or alternative example, if the AI / ML model is determined to be valid, the WTRU may continue to use the AI / ML model to predict the best beam. Further, the WTRU may transmit, receive, or both based on the predictions for the determined best beam(s) (390).

[0270] If one or more measured accuracy parameters are not within an acceptable range, the WTRU may determine that the predicted beam is invalid (350). The WTRU may then select one or more predicted beams from one or more other candidates. The WTRU may then restart the verification procedure. 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 lower than an LOS threshold and one or more channel parameters is lower than a channel parameter threshold (355). The one or more channel parameters may include one or more CQI parameters, in one example.

[0271] If the WTRU restarts the verification procedure (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 procedure. If the timer has expired (375), the WTRU may fall back to legacy beam management (370).

[0272] During the validation procedure, 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). The WTRU may then update the AI / ML model, retrain the AI / ML model, or both. The WTRU may also predict a new beam. The WTRU may then restart the validation procedure. 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 higher than an LOS threshold, but one or more channel parameters are lower than a channel parameter threshold (365). The one or more channel parameters may include one or more CQI parameters, in one example.

[0273] If the WTRU restarts the verification procedure (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 procedure. If the timer has expired (375), the WTRU may fall back to legacy beam management (370).

[0274] If the WTRU falls back to legacy beam management, the WTRU may deactivate the AI / ML model and then determine the best beam using legacy beam management 370. Further, the WTRU may transmit, receive, or both based on predictions for the determined best beam(s) 390.

[0275] 4 is a flowchart illustrating an example of predicted beam management. In the example shown in flowchart 400, the WTRU may perform measurements on a first set of beam resources (410). The base station, in one example, may transmit to the WTRU using the first set of beam resources. In one 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. The second set of beam resources may, in one example, be FR2 beam resources. Further, the WTRU may report the predicted beam resources (430). In one example, the WTRU may report the predicted beam resources to the base station.

[0276] Further, the WTRU may receive one or more first signals using the first beam (440). In one example, the WTRU may receive one or more first signals from the base station. In one example, the first beam may use beam resources in the second set of beam resources.

[0277] The WTRU may also perform measurements on one or more accuracy parameters of the received one or more first signals (450). Further, 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). The accuracy parameters may be acceptable, in one example, if the measured LOS is higher than an LOS threshold and the CQI is higher than a CQI threshold. In one example, the WTRU may transmit the one or more second signals to the base station.

[0278] In a further example, the WTRU may receive one or more third signals using the first beam, provided that the measured one or more accuracy parameters of the received one or more first signals are acceptable. The WTRU, in one example, may receive the one or more third signals from a base station.

[0279] In one example, the received one or more first signals may be PDCCH signals, and in another example, the received one or more first signals may be CSI-RS.

[0280] Additionally, in one example, using the first beam may include activating the first beam, and in another example, using the first beam may include continuing to use the first beam.

[0281] In a further 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. Also, the one or more accuracy parameters may include one or more CQI parameters.

[0282] In a further example, the WTRU may also activate the AI / ML model to predict one or more second beams. In one example, the one or more second beams may use beam resources in the second set of beam resources. In a further or alternative example, the WTRU may continue to use the AI / ML model to predict one or more second beams.

[0283] In a further example, the WTRU may transmit 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 not acceptable. In one example, the measured LOS may be lower than an LOS threshold and the measured CQI may be lower than a CQI threshold. In one example, the WTRU may transmit the request to a base station. In a further example, the base station may respond to the request. As a result, the WTRU may select the third beam. Furthermore, the WTRU may report the third beam to the base station.

[0284] In another example, the WTRU may transmit a request under a condition that one or more measured accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured LOS may be higher than an LOS threshold and the measured CQI may be lower than a CQI threshold. The transmitted request may include a request to update the AI / ML model. The transmitted request may include a request to retrain the AI / ML model. Further, the transmitted request may include a request to predict a fourth beam using the AI / ML model and report the fourth beam. In one example, the WTRU may transmit the request to a base station. Further, in one example, the base station may respond to the request. As a result, the WTRU may update the AI / ML model. In additional or alternative examples, the WTRU may retrain the AI / ML model. Also, the WTRU may predict the fourth beam using the AI / ML model. Further, the WTRU may report the fourth beam. In one example, the WTRU may report the fourth beam to the base station.

[0285] Furthermore, the WTRU may fall back to a non-AI / ML beam management procedure and select and report a fifth beam under the condition that one or more measured accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured CQI may be lower than a CQI threshold and many time instances may have passed since the reception of the first signal using the first beam. In one example, the WTRU may then select a sixth beam. Furthermore, the WTRU may report the sixth beam. In one example, the WTRU may report the sixth beam to the base station.

[0286] In a further 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 conditions where the measured one or more accuracy parameters of the received one or more first signals are not acceptable. In one example, the measured LOS may be below an LOS threshold, the measured CQI may be below a CQI threshold, and many time instances may not have elapsed since the reception of the first signal using the first beam. The WTRU, in one example, may receive one or more fourth signals from the base station.

[0287] Provided herein are examples of dynamic retraining / updating of AI / ML models based on changing the activated / deactivated set of TCI states. The TCI states provide QCL information necessary for the WTRU to receive various reference signals and / or channels. The WTRU may be configured with multiple TCI states, e.g., by RRC signaling, and a subset of the configured TCI states therein may be activated via signaling, e.g., MAC-CE signaling. To receive reference signals, channels, or both, the WTRU may select at least one TCI state from the set of activated TCI states, e.g., based on a DCI indicator or according to a (predefined) configuration, e.g., using a default QCL assumption for receiving DM-RS for PDSCH when the scheduling offset is less than (<) timeDurationForQCL. The WTRU may activate a new set of TCI states upon receiving new signaling / indications, e.g., via MAC-CE.

[0288] For example, a change in the set of activated TCI states can be seen as an indication of a change in the radio wave propagation environment due to various factors, such as rotation, movement, or both of the WTRU, or a change in other objects in the surrounding environment. Thus, if the set of activated TCI states of a WTRU changes, the WTRU may decide to evaluate the need to retrain the AI / ML models used for beam selection and / or prediction.

[0289] The WTRU may be configured and activated in a first set of TCI states by a first, e.g., MAC-CE, indication when an AI / ML model for beam prediction and / or selection is trained. After training of the AI / ML model is performed, the WTRU may be activated in a second set of TCI states by a second, e.g., MAC-CE, indication. Upon receiving second, e.g., MAC-CE, signaling indicating activation of the second set of TCI states, the WTRU may determine and / or evaluate and indicate to the base station or gNB the need to retrain the AI / ML model. The need to retrain the AI / ML model may be reported to the base station or gNB, for example, in PUCCH resources, PUSCH resources, RACH, an RRC message, or MAC CE.

[0290] In an example solution, the WTRU may compare a first set of TCI states with a second set of TCI states and determine an overlap level (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 retraining of the AI / ML model is necessary. If the L_overlap is higher than the configured / pre-configured / determined threshold level, the WTRU may determine that retraining of the AI / ML model is not necessary. The WTRU may determine and / or receive the TCI state overlap threshold from the base station or gNB, for example, via RRC / MAC-CE signaling.

[0291] In another example solution, the WTRU may determine the number of new TCI states (N_add) activated in the second set of TCI states that were not part of the first set and / or the number of TCI states (N_del) in the first set of TCI states that were not included in the second set. If N_add and / or N_del are above respective configured / pre-configured / determined thresholds, the WTRU may determine that retraining of the AI / ML model is necessary. If N_add and / or N_del are below respective thresholds, the WTRU may determine that retraining of the AI / ML model is not necessary. The WTRU may receive the respective thresholds for N_add and N_del from the base station or gNB, for example, via RRC / MAC-CE signaling.

[0292] In an additional or alternative example solution, the WTRU may report one or more 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 calculated parameters as soft information. For example, the WTRU may report information regarding the level of accuracy / effectiveness / reliability.

[0293] Provided herein are embodiments and examples of beam prediction verification of an AI / ML model based on reciprocity. A WTRU may receive and measure one or more parameters, such as CSI or beam parameters, such as RSRP, CQI, PMI, SINR, etc., for one or more beam resources in a first frequency range, such as FR1. The WTRU may determine / predict, based on an AI / ML model, one or more beam resources in a second frequency range, such as FR2, based on the respective measurements. The beam resources may consist of TCI states, CSI-RS or SSB for the downlink, and SRS resources or TCI states 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 with a reference ID.

[0294] Those skilled in the art will appreciate that the embodiments and examples provided herein address one or more problems. For example, one problem addressed is how the determined / predicted beam resources in the second frequency range and the respective AI / ML models are validated.

[0295] In an example solution, the WTRU may perform one or more uplink transmissions (e.g., SRS, PUCCH, PUSCH), and the WTRU may determine the association taking into account the spatial relationship between (each of) the uplink transmissions and (one of) the determined / predicted (downlink) beam resources. In this manner, 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 associated with each uplink transmission in the context of the spatial relationship.

[0296] In one example, a WTRU may be scheduled / configured with one or more UL transmissions of signals and / or channels. In this manner, the WTRU may decide to transmit the configured UL signals or channels using the same spatial filter that may be defined for the determined / predicted beam resources. For example, the WTRU may decide to use the same determined spatial domain filter to transmit (uplink) resource reference signals or channels on either the determined beam resources, the predicted beam resources, or both. In other words, the WTRU may decide to consider the same QCL relationship between the determined / predicted (downlink) beam resources and the transmitted (uplink) signals or channels.

[0297] In an example solution, the base station or gNB may measure parameters corresponding to the received uplink signal and channel, beam resource, RSRP, CIR, angle of arrival (AoA), PDCCH virtual BLER, etc. The base station or gNB may modify, update, or confirm the determined beam resource, the predicted beam resource, or both.

[0298] The WTRU may receive one or more signaling from the base station or gNB, e.g., via DCI, 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 a flag, e.g., in the DCI, indicating whether the predicted / determined beam resources are valid or invalid. For example, a flag value of 0 may indicate invalid, and a flag value of 1 may indicate valid. In another example, the WTRU may receive one or more CSI-RS measurement and reporting configurations, e.g., CSI-RS resources, QCL information, TCI status, etc., at the base station or gNB, that may be based on the selected beam resources.

[0299] The WTRU may receive one or more signals and channels in one or more beam resources, e.g., a second frequency range, based on the transmitted / reported uplink signals / channels, and the WTRU may measure CSI and / or beam parameters using the received signals. The WTRU may further use the measurements to update / retrain the AI / ML model. The WTRU may select and report the best beam and respective CSI quantities. The respective CSI quantities may include, for example, CSI-RSRP, CIR, etc.

[0300] While features and elements are described above in particular combinations, those skilled in the art will understand that each feature or element can be used alone or in any combination with the other features and elements. Those skilled in the art will also understand that the above-described features and elements include means for performing the methods described herein. Additionally, the methods described herein may be implemented in a computer program, software, or firmware embodied in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and digital versatile disks (DVDs). A processor associated with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

1. 1. A method for use in a wireless transmit / receive unit (WTRU), comprising: receiving first configuration information including a configuration of one or more reference signal (RS) resources for measurement and a configuration of one or more RS resources for prediction; receiving second configuration information including a configuration of one or more RS resources with respect to availability; performing measurements on the one or more RS resources related to measurements; determining a prediction for one or more best RS resources of the one or more RS resources related to a prediction based on the measurements for the one or more RS resources related to a measurement; performing measurements on the one or more RS resources regarding availability; determining one or more best RS resources of the one or more RS resources in terms of availability based on the measurements of the one or more RS resources in terms of availability; determining that the prediction for the one or more best RS resources of the one or more RS resources related to the prediction is a valid prediction under the condition that at least one RS resource from the prediction for the one or more best RS resources of the one or more RS resources related to the prediction corresponds to an RS resource among the one or more best RS resources of the one or more RS resources related to validity; reporting the determination that the prediction for the one or more best RS resources of the one or more RS resources related to the prediction is a valid prediction; and A method comprising:

2. 2. The method of claim 1, wherein the determination that the prediction for the one or more best RS resources of the one or more RS resources related to the prediction is a valid prediction is made over a preconfigured period of time.

3. 2. The method of claim 1, wherein the one or more RS resources for measurement are one or more RS resources for channel measurement.

4. The method of claim 1 , wherein the one or more RS resources related to validity are one or more RS resources related to accuracy of prediction.

5. 2. The method of claim 1 , wherein the one or more RS resources related to measurement are one or more beam RS resources related to measurement, the one or more RS resources related to prediction are the one or more beam RS resources related to prediction, and the one or more RS resources related to validity are the one or more beam RS resources related to validity.

6. reporting up to a configured number of RS resources from the prediction for the one or more best RS resources of the one or more RS resources related to the prediction. The method of claim 1 further comprising:

7. 2. The method of claim 1, wherein the one or more RS resources for measurement are in a first frequency range and the one or more RS resources for prediction are in a second frequency range.

8. receiving information providing a match between the one or more RS resources with respect to prediction and the one or more RS resources with respect to validity; The method of claim 1 further comprising:

9. 2. The method of claim 1, wherein the one or more best RS resources of the one or more RS resources for prediction have the highest reference signal received power (RSRP) from among the one or more RS resources for prediction.

10. 2. The method of claim 1, wherein the one or more best RS resources of the one or more RS resources in terms of availability have the highest RSRP from among the one or more RS resources in terms of availability.

11. 1. A wireless transmit / receive unit (WTRU), comprising: transceivers, and a processor operably coupled to the transceiver Equipped with the transceiver and the processor are configured to receive first configuration information including a configuration of one or more reference signal (RS) resources for measurement and a configuration of one or more RS resources for prediction; the transceiver and the processor are configured to receive second configuration information including a configuration of one or more RS resources with respect to availability; the transceiver and the processor are configured to perform measurements on the one or more RS resources related to measurements; the processor is configured to determine, based on the measurement for the one or more RS resources related to a measurement, a prediction for one or more best RS resources of the one or more RS resources related to a prediction; the transceiver and the processor are configured to perform measurements on the one or more RS resources for availability; the processor is configured to determine one or more best RS resources of the one or more RS resources in terms of availability based on the measurement of the one or more RS resources in terms of availability; The processor is configured to determine that the prediction for the one or more best RS resources of the one or more RS resources related to the prediction is a valid prediction under a condition that at least one RS resource from the prediction for the one or more best RS resources of the one or more RS resources related to the prediction corresponds to an RS resource among the one or more best RS resources of the one or more RS resources related to validity; The transceiver and the processor are configured to report the determination that the prediction for the one or more best RS resources of the one or more RS resources related to the prediction is a valid prediction. WTRU

12. 12. The WTRU of claim 11, wherein the determination that the prediction for the one or more best RS resources of the one or more RS resources for prediction is a valid prediction is made over a preconfigured period of time.

13. 12. The WTRU of claim 11, wherein the one or more RS resources for measurements are one or more RS resources for channel measurements.

14. 12. The WTRU of claim 11, wherein the one or more RS resources related to validity are one or more RS resources related to prediction accuracy.

15. 12. The WTRU of claim 11, wherein the one or more RS resources related to measurement are one or more beam RS resources related to measurement, the one or more RS resources related to prediction are the one or more beam RS resources related to prediction, and the one or more RS resources related to validity are the one or more beam RS resources related to validity.

16. 12. The WTRU of claim 11, wherein the transceiver and the processor are further configured to report up to a configured number of RS resources from the prediction for the one or more best RS resources of the one or more RS resources related to the prediction.

17. 12. The WTRU of claim 11, wherein the one or more RS resources for measurement are in a first frequency range and the one or more RS resources for prediction are in a second frequency range.

18. 12. The WTRU of claim 11, wherein the transceiver and the processor are further configured to receive information providing a match between the one or more RS resources for prediction and the one or more RS resources for validity.

19. 12. The WTRU of claim 11, wherein the one or more best RS resources of the one or more RS resources for prediction have the highest reference signal received power (RSRP) from among the one or more RS resources for prediction.

20. 12. The WTRU of claim 11, wherein the one or more best RS resources of the one or more RS resources for availability have the highest RSRP from among the one or more RS resources for availability.

Images