Validating AIML models

Abstract

A wireless transmit / receive unit (WTRU) receives an association rule for determining area and / or time validity of an artificial intelligence or machine learning (AIML) model from a network entity. The WTRU may receive an activation command associated with the AIML model. The WTRU measures a plurality of positioning reference signals (PRSs) and determines a validity for the AIML model based on the association rule and reports the determined validity to the network.

Description

VALIDATING AIML MODELSCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application number 63 / 572,609, filed April 1, 2024, the entire contents of which are incorporated herein by reference.BACKGROUND

[0002] A “downlink (DL) positioning method” may refer to any positioning method that uses downlink reference signals (RSs) such as positioning reference signals (PRSs). A wireless transmit / receive unit (WTRU) may receive multiple reference signals from transmission points (TP(s)) and measure DL reference signal time difference (RSTD) and / or reference signal received power (RSRP). Examples of DL positioning methods are DL-angle of departure (AoD) or DL-time difference of arrival (TDOA) positioning. An “uplink (UL) positioning method” may refer to any positioning method that uses uplink reference signals such as sounding reference signals (SRSs) for positioning. The WTRU transmits SRS to multiple reception points (RPs) and the RPs measure the UL relative time of arrival (RTOA) and / or RSRP. Examples of UL positioning methods are UL-TDOA or UL-angle of attack (AoA) positioning. A “DL & UL positioning method” may refer to any positioning method that uses both uplink and downlink reference signals for positioning. In one example, a WTRU transmits SRS to multiple TRPs and a gNB measures receive (Rx)-transmit (Tx) time difference which is calculated based on the time of arrival of DL RS (e.g. , PRS). The gNB can measure RSRP for the received SRS. The WTRU measures Rx-Tx time difference for PRS transmitted from multiple TRPs. The WTRU can measure RSRP for the received PRS. The Rx-TX difference and possibly RSRP measured at WTRU and gNB are used to compute round trip time. Here “WTRU Rx - Tx time difference” refers to the difference between arrival time of the reference signal transmitted by the transmission / reception point (TRP) and transmission time of the reference signal transmitted from the WTRU. An example of DL & UL positioning method is multi-round trip time (RTT) positioning.

[0003] Machine learning may refer to types of algorithms that solve problems based on learning through experience (e.g., using ‘data’), without explicitly being programmed (e.g., ‘configuring sets of rules’). Machine learning can be considered as a subset of artificial intelligence (Al). Different machine learning paradigms may be envisioned based on the nature of data and / or feedback available to the learning algorithm. For example, a supervised learning approach may involve learning a function that maps input to an output based on labeled training examples. Each training example may be a pair comprising input and the corresponding output. For example, an unsupervised learning approach may involve detecting patternsin the data with no pre-existing labels. In examples, a reinforcement learning approach may involve performing sequence(s) of actions in an environment to maximize the cumulative reward. In some solutions, it is possible to apply machine learning algorithms using a combination or interpolation of the above-mentioned approaches. For example, a semi-supervised learning approach may use a combination of a small amount of labeled data with a large amount of unlabeled data during training. In this regard semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data).SUMMARY

[0004] A user equipment (UE) may send a request for measurement forwarding from the network. The request may include area and / or time intervals within or during which the measurements should be made. Based on measurements made by the WTRU, forwarded measurements, determined WTRU location estimates, ground truths, forwarded WTRU location estimates and / or ground truths, the WTRU may determine the training data. Based on the training data (e.g., measurements, ground truth), the WTRU may determine one or more validity conditions for the trained AIML model. The WTRU may report the determined validity condition(s) to the network.

[0005] A WTRU may receive an indication of a set of measurement time windows and an association rule related to area and time validity from a network entity. The WTRU may receive an activation command associated with a measurement time window and determine a measurement in accordance with the activated measurement time window. The WTRU may determine a duration of the measurement. The WTRU may receive a set of forwarded measurements and a forwarded ground truth. The WTRU may determine to use one or more of the forwarded measurements and / or ground truth fortraining an artificial intelligence markup language (AIML) model. The WTRU may determine a validity condition for the AIML model based on the association rule; and report the determined validity condition to the network.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] FIG. 1 A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0007] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1 A according to an embodiment.

[0008] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1 A according to an embodiment.

[0009] FIG. 1 D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1 A according to an embodiment.

[0010] FIG. 2 is a system diagram illustrating an example neural network.

[0011] FIG. 3 is a diagram illustrating example parameters for a time window.

[0012] FIG. 4 is a block diagram illustrating an example use of an AIML model to estimate WTRU location.

[0013] FIG. 5 is a block diagram illustrating an example hierarchal structure for PRS configurations.

[0014] FIG. 6 is a block diagram illustrating an example training algorithm.

[0015] FIG. 7 is a system diagram illustrating an example determination of time validity conditions for an AIML model at the target WTRU.

[0016] FIG. 8 is a system diagram illustrating an example of determination of a periodicity of measurements in the effective measurement duration.

[0017] FIG. 9 is a system diagram illustrating an example of determination of an area validity condition by a target WTRU.

[0018] FIG. 10 is a block diagram illustrating an example procedure for requesting validity conditions.

[0019] FIG. 11 is a system diagram illustrating example exchanges between a WTRU and a location management function (LMF) to obtain validity conditions.DETAILED DESCRIPTION

[0020] FIG. 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA), zero-tail unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0021] As shown in FIG. 1 A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a RAN 104 / 113, a CN 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a “station” and / or a “STA”, may be configured to transmit and / or receive wireless signals and may include a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fl device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a WTRU. Further, any description herein that is described with reference to a UE may be equally applicable to a WTRU (or wee i / ersa). For example, a WTRU may be configured to perform any of the processes or procedures described herein as being performed by a UE (or wee versa).

[0022] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106 / 115, the I nternet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a NR NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0023] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to asa cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0024] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0025] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 115 / 116 / 117 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 UL Packet Access (HSUPA).

[0026] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-APro).

[0027] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0028] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multipletypes of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0029] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA20001X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0030] The base station 114b in FIG. 1 A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0031] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing a NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0032] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or the other networks 112. The PSTN 108 may include circuit- switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 113 or a different RAT.

[0033] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0034] FIG. 1 B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0035] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1 B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0036] The transmit / recei ve element 122 may be configured to transmit signals to, or receive signals from, a base station (e. g . , the base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0037] Although the transmit / receive element 122 is depicted in FIG. 1 B 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.

[0038] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0039] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0040] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 maybe any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0041] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable locationdetermination method while remaining consistent with an embodiment.

[0042] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and / or Augmented Reality (VR / AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0043] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the UL (e.g., for transmission) and downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit 139 to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WRTU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e.g., for transmission) or the downlink (e.g., for reception)).

[0044] FIG. 1 C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicatewith the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0045] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a.

[0046] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, and the like. As shown in FIG. 1 C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0047] The CN 106 shown in FIG. 1 C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0048] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0049] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter- eNode B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0050] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0051] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0052] Although the WTRU is described in FIGS. 1 A-1 D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0053] In representative embodiments, the other network 112 may be a WLAN.

[0054] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic in to and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to- peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an “ad- hoc” mode of communication.

[0055] When using the 802.11 ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signaling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA)may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g. , every ST A), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular ST A, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0056] High Throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0057] Very High Throughput (VHT) STAs may support 20MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above described operation for the 80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0058] Sub 1 GHz modes of operation are supported by 802.11 af and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.11 af and 802.11 ah relative to those used in 802.11 n, and 802.11 ac. 802.11af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11 ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11 ah may support Meter Type Control / Machine- Type Communications, such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0059] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11 n, 802.11 ac, 802.11 af, and 802.11 ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In theexample of 802.11 ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0060] In the United States, the available frequency bands, which may be used by 802.11 ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11 ah is 6 MHz to 26 MHz depending on the country code.

[0061] FIG. 1D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0062] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0063] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wirelesstransmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0064] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non-standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0065] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards User Plane Function (UPF) 184a, 184b, routing of control plane information towards Access and Mobility Management Function (AMF) 182a, 182b and the like. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0066] The CN 115 shown in FIG. 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 each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0067] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different PDU sessions with different requirements), selecting a particular SMF 183a, 183b,management of the registration area, termination of NAS signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b in order to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for machine type communication (MTC) access, and / or the like. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0068] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating WTRU IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0069] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0070] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g. , an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local Data Network (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0071] In view of Figures 1 A-1 D, and the corresponding description of Figures 1 A-1 D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station 114a-b,eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-ab, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other device(s) described herein, may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0072] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily i mplemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0073] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g. , testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0074] An example of a neural network is shown in FIG. 2 at 200. The objective of training is to apply input and adjust weights, indicated as w and x in the figure (which may be referred to as neuron weights or link weights), such that the output from the neural network approaches the desired target values which are associated with the input values. In the example shown in FIG. 2 at 200, the neural network consists of 3 layers. During the training, for given input, the difference between output and desired values may be computed and the difference used to update the weights in the neural network. If a large difference between output and desired values is observed, large changes in weights are expected while small difference will lead to small changes in weights.

[0075] In examples, for positioning, input can be reference signal parameters and output can be estimated position. The desired value can be location information acquired using a global navigational satellite system (GNSS) with high accuracy. Once the neural network completes its training (e.g., the differencebetween the output and desired values is below a threshold), it can be applied for positioning by feeding input and using the output as the expected outcome for the associated input. The output may be an estimated position or location of the WTRU.

[0076] Important factors for training a neural network include, but are not limited to, the following: the input for the neural network; the expected output associated with input; and the actual output from the neural network against which the target values are compared.

[0077] In examples, a neural network model can be characterized by the following parameters: the number of weights; the number of layers in the neural network; and / or the number of neurons per layer. A Neural Network is characterized by a) the number and types of layers, and b) the values of parameters (e.g., weights) associated with each layer.

[0078] Deep learning may refer to a class of machine learning algorithms that employ artificial neural networks, such as Deep Neural Networks (DNNs). DNNs are a special class of machine learning model which were loosely inspired by biological systems (e.g., the human brain) and may include one or more hidden layer(s). The input to a DNN may be linearly transformed and pass through non-linear activation function multiple times. DNNs typically comprise multiple layers where each layer comprises linear transformations and / or given non-linear activation functions. The DNNs can be trained using the training data (e.g., via back-propagation algorithms). Recently, DNNs have shown state-of-the-art performance in a variety of domains including speech, vision, natural language, etc. DNNs have used various machine learning settings such as supervised, un-supervised, and semi-supervised. In addition, “events” or “occasions” may be used interchangeably herein.

[0079] In current 3GPP specifications, radio access technology (RAT) dependent positioning methods are specified. These methods require the WTRU to be in a line-of-sight environment with respect to transmission reception points (TRPs), limiting the applicable use cases. In non-line of sight environments, the performance of RAT dependent positioning methods can deteriorate.

[0080] For WTRU-side AIML models, the WTRU may train AIML models based on an available and potentially limited amount of data. The WTRU may determine which measurement data to use. In such a scenario, the details of the training data may become unclear to the network. In such cases, the network may not be able to determine the validity condition. The network should know the validity conditions, so the network can determine to configure AIML based positioning for the WTRU. The discussion herein relates to how the WTRU can determine time and / or area validity conditions for the model in such a situation.

[0081] An artificial intelligence markup language (AIML) model may be trained with measurements and / or ground truths. A wireless transmit / receive unit (WTRU may determine time and area validity conditions for an AIML model based on the duration and timestamps of forwarded measurements, the WTRU’s measurements, and / or the ground truth.

[0082] The WTRU may be configured with a PRS configuration.

[0083] The WTRU may be configured by the network with a set of measurement time windows and associated configurations (e.g., periodicity, duration of a gap).

[0084] The WTRU may receive a configuration for AIML based positioning comprising an association rule for determining AIML model validity. For example, the association rule may comprise for area and time validation conditions (e.g., and a priority of determination between time and area validity).

[0085] In examples, an AIML model may be valid for the area (e.g., cell, zone in a cell) if the number or density of WTRUs from which measurements and corresponding ground truth are collected is above the configured threshold.

[0086] In examples, the WTRU may determine area validity based on geographical distribution or density of WTRUs in the area (e.g., cell(s), zone(s)). For example, the WTRU may be configured with a validity condition in the form of density (e.g., 1 WTRU per 10 square meters, 5 WTRUs per 20 square meters).

[0087] In examples, the WTRU may determine measurements (e.g., of PRSs) based on consistency among measurements (e.g., if two measurements are made by the target and second WTRU, where both WTRUs are the reduced capability WTRU; if two measurements are made using the same PRS configuration; if two measurements are associated with the same PRS resource ID; and / or if two measurements are made by the same WTRU type, such as WTRUs in the same category).

[0088] In examples, an AIML model may be valid for a duration or time period (e.g., 24 hours) if the timespan and periodicity of collected measurements and corresponding ground truth are above the configured threshold. For example, the model may be valid for 24 hours if the measurements were made over 48 hours at 1 hour interval. If the measurements are made by more than one WTRUs, the timespan may be based on the shortest timespan. Similarly, the periodicity may be based on the longest periodicity.

[0089] The WTRU may receive an activation command for one of the measurement time windows in the list from the network. The activation command (e.g., MAC-CE) may contain a timestamp (e.g., absolute time or relative time). Each measurement time window in the list may be associated with an ID.

[0090] The WTRU may make measurements on the received PRS during the activated measurement time window.

[0091] The WTRU may receive a deactivation command for the measurement time window and determine the duration of the measurement.

[0092] The WTRU may receive forwarded measurements and / or associated ground truth(s) from the network. A timestamp (e.g., absolute time) and / or a measurement time window ID may be associated with the measurements and / or ground truth(s).

[0093] The WTRU may select which measurements to use for training and train AIML model(s) using the selected measurements (e.g., based on at least the measured PRSs).

[0094] The WTRU may receive priorities associated with time and area validity determinations (e.g., time validity is determined first then area validity is determined).

[0095] The WTRU may determine a time validity for the AIML model based on the received association rule (e.g., effective measurement duration determined based on measurement duration, start and / or end time of the measurement period).

[0096] Based on the effective measurement duration (e.g., the chosen WTRUs to determine the effective measurement duration), the WTRU may determine an area validity for the AIML model based on the number of the WTRU per area and received association rule.

[0097] The WTRU may receive a request to report the determined validity condition.

[0098] The WTRU may report the determined validity condition (e.g., indicating the validity of the AIML model) to the network (e.g., LMF).

[0099] The WTRU may receive a request for AIML based positioning.

[0100] Using absolute time for time validation may be beneficial, for example, if the AIML model will be valid for a long time (e.g., beyond time range that can be expressed in SFN).

[0101] The measurement duration between the WTRUs and other WTRUs / PRU’s may be the same (e.g., controlled by the network). For example, the same measurement gap, indicated by the measurement gap ID, may be configured for more than one WTRUs by the network so the WTRUs can make measurements during the same interval.

[0102] General WTRU behavior is discussed herein. The WTRU may send a request to the network for configuration (e.g., PRS configurations, SRSp configurations) via physical uplink shared channel (PUSCH), physical uplink control channel (PUCCH), uplink control information (UCI), medium access control (MAC)- control element (CE), radio resource control (RRC) and / or LTE positioning protocol (LPP) messaging. The request from the WTRU may include configurations of a measurement gap, and / or a PRS processing window or window for transmission of SRS for positioning (SRSp).

[0103] The WTRU may send an acknowledgement message in PUSCH or PUCCH for the grant received from the network.

[0104] One, or more than one conditions / criteria can be used in a combination. The WTRU may be configured with more than one conditions and associated WTRU behavior. The WTRU may determine which behavior the WTRU shall use based on the applicable condition.

[0105] The WTRU can measure DL-PRS inside or outside of an active BWP. The WTRU may transmit SRSp inside or outside of the active BWP.

[0106] The WTRU may be preconfigured with parameters (e.g., related to measurement gaps, PRS processing windows, PRS configurations, SRSp configurations) via a semi-static message (e.g., an LPP or RRC message).

[0107] Any actions the WTRU determines to take may be configured by the network. For example, the WTRU may be configured with a rule. According to the rule, the WTRU may determine to take an associated action.

[0108] In addition to the measurements made on PRS, the WTRU may include one or more of the following cell-related measurements: Synchronization Signal Block (SSB) RSRP from the serving cell with corresponding cell ID; SSB RSRP from the neighboring cell(s) with corresponding cell I D(s); RSRP of Channel State Information (CSI)-RS with CSI-RS resource ID; or RSRP of Demodulation Reference Signals (DM-RSs).

[0109] Herein, “Network” may include, but is not limited to, one or more of an access and mobility management function (AMF), a location management function (LMF), a gNB or a next generation-radio access network (NG-RAN).

[0110] The terms “pre-configuration” and “configuration” may be used interchangeably herein. The terms “non-serving gNB” and “neighboring gNB” may be used interchangeably herein. The terms “gNB” and “TRP” may be used interchangeably herein. The terms “PRS”, “SRS”, “SRS for positioning (SRSp)” or “SRS for positioning purpose” can be used interchangeably herein. The terms “PRS” or “PRS resource” may be used interchangeably herein. The terms “PRS(s)” or “PRS resource(s)” may be used interchangeably herein. The aforementioned “PRS(s)” or “PRS resource(s)” may belong to different PRS resource sets. The terms “PRS” or “DL-PRS” or “DL PRS” may be used interchangeably herein. The terms “Measurement gap” or “Measurement gap pattern” may be used interchangeably herein. “Measurement gap pattern” may include parameters such as measurement gap duration or measurement gap repetition period or measurement gap periodicity.

[0111] A location management function (LMF) is a non-limiting example of a node or entity (e.g., network node or entity) that may be used for or to support positioning. Any other node or entity may be substituted for LMF and still be consistent with this disclosure.

[0112] The WTRU may receive a preconfigured threshold(s) from the network (e.g., LMF, gNB).

[0113] The LOS indicator may be hard (e.g., 1 or 0) or soft indicator (e.g., 0, 0.1, 0.2..., 1). The LOS indicator may indicate the likelihood of the presence of an LOS path between TRP and WTRU or along PRS. The LOS indicator can be associated with a TRP or PRS resource ID (e.g., index). The WTRU may receive the LOS indicator from the network per TRP or resource ID. Additionally, or alternatively, the WTRU may determine the LOS indicator per TRP, or resource ID based on measurements.

[0114] Herein, the terms “ID” and “index” may be used interchangeably.

[0115] A WTRU location may be expressed in terms of altitude, latitude, geographic coordinate, and / or local coordinates, for example.

[0116] A PRU may be a WTRU whose location is known or verified by the network.

[0117] Examples of “absolute time” include UTC time, GNSS time, and locally defined absolute time (e.g., LTE or NR Time).

[0118] Configurations for RS for positioning are discussed herein. In examples, the WTRU may receive PRS and / or SRS configurations for positioning purpose from the network (e.g., LMF). The LMF may forward the PRS configuration and SRS configurations to the gNB so that the gNB can schedule PRS transmission or SRS reception at the TRP, TP and / or RP.

[0119] Configurations for PRS are discussed herein. In examples, a PRS configuration may contain one or more of the following parameters: number of symbols, transmission power, number of PRS resources included in PRS resource set, muting pattern for PRS (for example, the muting pattern may be expressed via a bitmap), periodicity, type of PRS (e.g., periodic, semi-persistent, or aperiodic), slot offset for periodic transmission for PRS, vertical shift of PRS pattern in the frequency domain, time gap during repetition, repetition factor, RE (resource element) offset, comb pattern, comb size, spatial relation (e.g., with respect to other PRSs or UL RS such as SRS for positioning purpose), quasi co-location (QCL) information (e.g., QCL target, QCL source) for PRS, number of TRPs, Absolute Radio-Frequency Channel Number (ARFCN), subcarrier spacing, expected RSTD, uncertainty in expected RSTD, start Physical Resource Block (PRB), bandwidth, bandwidth part (BWP) ID, number of frequency layers, start / end time for PRS transmission, on / off indicator for PRS, TRP ID, PRS ID, cell ID, global cell ID and applicable time window.The WTRU may apply a PRS configuration under the condition that the current time is within the applicable time window. The term, “ID,” may be used interchangeably with “index”.

[0120] Configurations for SRS for positioning are discussed herein. In examples, SRS for positioning (SRSp) or SRS configuration may include one or more of: resource ID; comb offset values, cyclic shift values; start position in the frequency domain; number of SRSp symbols; shift in the frequency domain for SRSp; frequency hopping pattern; type of SRSp (e.g., aperiodic, semi-persistent or periodic); sequence ID used to generate SRSp, or other IDs used to generate SRSp sequence; spatial relation information, indicating which reference signal (e.g., DL RS, UL RS, CSI-RS, SRS, DM-RS) or SSB (e.g., SSB ID, cell ID of the SSB) the SRSp is related to spatially where the SRSp and DL RS may be aligned spatially; QCL information (e.g., a QCL relationship between SRSp and other reference signals or SSB); QCL type (e.g., QCL type A, QCL type B, QCL type C, QCL type D); resource set ID; list of SRSp resources in the resource set; transmission power related information; pathloss reference information which may contain index for SSB, CSI-RS or PRS; periodicity of SRSp transmission; and / or spatial information such as spatial direction information of SRSp transmission (e.g., beam information, angles of transmission), spatial direction information of DL RS reception (e.g., beam ID used to receive DL RS, angle of arrival). “ID” may be used interchangeably with “index”.

[0121] Measurements, including timing measurements, are discussed herein. In examples, RSTD may be defined by the difference in time of arrival between PRSs transmitted from a reference transmission / reception point (TRP) and target TRP. The WTRU may be configured with the reference TRP index and target TRP index. The WTRU may be configured with the PRS resource indices to make measurements. The WTRU may determine the time of arrival from TRP based on one or more PRS resources associated with the TRP. In examples, the RSTD may be defined as the difference in time of arrival between the reference PRS transmitted from a TRP and the target PRS transmitted from a TRP.

[0122] In examples, “WTRU Rx - Tx time difference” refers to the difference between arrival time of the reference signal transmitted by the TRP and transmission time of the reference signal transmitted from the WTRU. The WTRU Rx-Tx time difference may be associated with PRS resource ID and / or SRSp resource ID.

[0123] Phase measurements are discussed herein. In examples, RSCP (RS Carrier Phase) may be defined as the carrier phase measurement on the PRS. RSCPD (RSCP Difference) may be defined as difference in carrier phase measurements between two PRS resources.

[0124] Power measurements are discussed herein. In examples, RSRP (Reference Signal Received Power) per path may be defined as the RSRP per path if the WTRU observes a multipath channel in the measurement. The WTRU may determine RSRP for a DL RS resource. RSRP or RSRPP (RSRP per path) may be reported using units dBm or relative power difference compared to a reference, e.g., RSRP of the first path, in dB.

[0125] Details related to channel impulse response and its association to RS configurations are discussed herein. An example of measurement may be a channel impulse response. A channel impulse response, comprising N paths, may be defined by the following / i(t)> Tk) where hk(t) = h_k (t) and tk= i_k are time-varying complex valued coefficient (e.g., expressed by a+bj where H(-1) for the channel impulse response and delay, measured in seconds, for the kAth path, respectively. The delta function is defined as 6(t)=1 for t=0 and 6(t)=0 for t 0.

[0126] For simplicity, the coefficients may be assumed to be constant over time, (e.g., h_k (t)=h_k). The WTRU may report h_k and r_k for each path k to the network. The WTRU may report the number of paths, N, to the network. Additionally, or alternatively, the WTRU may receive h_k and i_k for each path k from the network and / or the number of paths.

[0127] In examples, the WTRU may obtain channel impulse response CIR (Channel Impulse Response) from the network. The network may indicate PRS configuration(s) such as PRS resource IDs associated with the CIR. In examples, the CIR may be associated with one or more PRS resource IDs. For example, the CIR may be associated with PRS resource ID. In this case, the WTRU may determine that the CIR is derived based on the measurements made on the PRS resource associated with the ID. Additionally, or alternatively, the WTRU may determine that the channel along the direction of transmission of the PRS or reception of the PRS corresponds to the CIR.

[0128] In examples, the CIR may be associated with a TRP ID. In this case, the WTRU may determine that the CIR represents the channel between the associated TRP and WTRU In examples, the CIR may be associated with more than one TRPs where the network may include TRP indices associated with the CIR.

[0129] In examples, the CIR may be associated with a cell. In this case, the WTRU may receive cell ID or index associated with the CIR from the network.

[0130] In examples, CIR may be associated with more than one TRPs or PRS resource IDs. In this case, the WTRU may determine that the channel between the TRPs and the WTRU corresponds to the CIR. Additionally, or alternatively, the WTRU may determine that the channel along the transmission directions of PRSs associated with IDs or reception directions of the PRS correspond to the CIR.

[0131] In examples, more than one Cl Rs may be associated with one parameter from PRS configurations (e.g., TRP ID, PRS resource ID, frequency layer ID). For example, the WTRU may receive information related to 2 CIRs associated with a TRP from the network, e.g., h^t)- T ) and~T2,k) from the network. Additionally, or alternatively, the WTRU may report information related to more than one CIRs associated with PRS configuration (e.g., TRP ID, PRS resource ID) based on the measurements to the network. There can be one or more CIRs associated with a PRS configuration, for example, because the WTRU or network may observe different channel characteristics based on AoA of DL RS or UL RS.

[0132] Channel impulse response may be represented by delay profile or power delay profile. A power delay profile may be defined as a set of delays and power profiles, such as [T_0, T_1 , -, T_(N-1 )] and [p_0, p_1 , • • -,P_(N-1 )], where p_k corresponds to relative power at the kAth path compared to the first path. A delay profile may be defined as a set of delays [T_0, T_1 , •••, T_(N-1 )] which indicates path delay for each path above a threshold, such as pjhreshold. The WTRU may receive p_threshold from the network to derive delay profile from power delay profile.

[0133] In examples, the WTRU may receive an indication from the network on how to generate CIR (Channel Impulse Response), PDP (Power Delay Profile) or DP (Delay Profile) based on timing, phase and / or power measurements. The WTRU may send a request to the network to receive an indication on which methods to use to generate CIR, power delay profile (PDP) or DP based on the measurements the WTRU made. For example, the WTRU may receive a message from the network (e.g., via LPP, RRC, MAC-CE, DCI) indicating the PRS resource indices and associated measurement type(s) (e.g., RSTD, AOA) to use to generate CIR, PDP, or DP. The WTRU may receive an indication from the network indicating to generate CIR, PDP, or DP.

[0134] The WTRU may send measurements in a report to the network (e.g., LMF, gNB) via a semi-static (e.g., LPP, RRC) or dynamic message (e.g., UCI, UL MAC-CE).

[0135] In the examples herein, the terms PRS, DL-RS (e.g., CSI-RS, DM-RS, TRS) and SSB may be used interchangeably.

[0136] The CIR, PDP, or DP may be derived based on extended CP (cyclic prefix) or normal CP. The WTRU may indicate the length of the CP used to derive the CIR, PDP, or DP.

[0137] Measurement time windows are discussed herein.

[0138] A measurement time window may be characterized by one or more of (e.g., any combination of) the following: a start time (e.g., expressed in terms of absolute time, SFN, frame index, subframe index,slot index, symbol index); an end time (e.g. , expressed in terms of absolute time, SFN, frame index, subframe index, slot index, symbol index); a duration (e.g., in absolute time such as hours, number of slots, frames, subframes);and / or a periodicity (e.g., measurement time may occur periodically). The periodicity of the window may be expressed in terms of the number of symbols, slots, frames or subframes, for example; an “on” duration, (e.g., “on” time may be the time the WTRU makes measurements on the received PRS). The duration of “on” time may be expressed in terms of the number of symbols, slots, frames or subframes; and / or an index or ID associated with a window or configuration of a window.

[0139] The WTRU may determine that a measurement time window is activated or deactivated based on a command (e.g., via MAC-CE) sent by the network. An illustration of a time window is shown in FIG. 3 at 300, where periodicity, “on” duration, start time and end time are illustrated in the figure.

[0140] In examples, the WTRU may determine that the measurement time window is configured for the WTRU and other WTRUs or PRUs simultaneously. For example, the network may configure the window(s) for more than one WTRUs during the same time or time interval such that simultaneous measurements among the WTRUs can be performed.

[0141] In examples, the activation command for the measurement time window may contain a timestamp (e.g., absolute time), indicating the time the window is activated.

[0142] The WTRU may determine the start and / or end time of the time window from the network via signaling (e.g., RRC, LPP, MAC-CE, downlink control information (DCI)). The WTRU may determine activation or deactivation of the window via signaling (e.g., MAC-CE).

[0143] Measurement forwarding by the LMF is discussed herein. The WTRU may receive measurements made by other WTRUs from the LMF. Such functionality may be referred to as “measurement forwarding” in the examples described herein. In measurement forwarding, the WTRU which receives the measurements from the LMF may be referred as the “target WTRU”. The WTRUs which reports the measurements to the LMF, and whose measurements are forwarded to the target WTRU, may be referred as the “second WTRU” or “other WTRU” in the examples described herein. Forwarded information from the LMF to the target WTRU may include one or more of (e.g., any combination of) measurements made by other WTRUs, the ground truth(s) associated with other WTRUs, and / or location estimates of other WTRUs determined by the other WTRUs. The measurements or ground truth(s) forwarded by the LMF to the target WTRU may be referred to as “forwarded measurements” and / or “forwarded ground truths”, respectively.

[0144] The contents of measurement or location reports are discussed herein. In examples, the WTRU may receive a request from the network to report its location and / or measurements made on the PRS. TheWTRU may report to the network one or more of (e.g., any combination of) the following in the measurement report: PRS ID associated with measurements and / or WTRU location estimate; TRP ID associated with measurements and / or WTRU location estimate; Cell ID associated with measurements and / or WTRU location estimate; ARFCN associated with measurements and / or WTRU location estimate; PRS Resource ID(s) associated with measurements and / or WTRU location estimate; PRS Resource Set ID(s) associated with measurements and / or WTRU location estimate; Frequency layer ID (s) associated with measurements and / or WTRU location estimate; Timestamp indicating when the measurements are made or when the report is made; RSTD associated with PRS resource I D(s) for each path in multipaths; RSRP associated with PRS resource I D(s) for each path in multipaths; Phase measurement (e.g., RSCP, RSCPD) for each path in multipaths; Uncertainty information (e.g., expressed in terms of a range such as ±2 us (microseconds)); quality information for measurements (e.g., indicating whether the indicated measurement is in the unit of 0.1 us or 0.01 us); TEG (timing error group) associated with measurements or PRS resource ID or PRS resource set ID; LOS indicator associated with PRS resource ID or TRP ID;WTRU location (e.g., absolute location with geographical coordinates expressed by x and y coordinates, relative location with respect to a reference point such as an indicated TRP or cell center); Uncertainty information for the determined WTRU location (e.g., expressed in terms of a range such as ±2 meter); quality information for the determined WTRU location (e.g., indicating whether the indicated WTRU location is in the unit of 0.1 meter or 0.01 meter); an Indication of which method (e.g., RAT dependent positioning method such as DL-TDOA, DL-AoD, or AIML based positioning) is used to determine the WTRU location; and / or Channel impulse response and associated DL-RS configurations used to determine CIRs.

[0145] Artificial intelligence (Al) for positioning is discussed herein. Artificial intelligence may be broadly defined as the behavior exhibited by machines that mimic cognitive functions to sense, reason, adapt, act, and provide the ability to discern patterns.

[0146] Inputs and outputs for Al for positioning are discussed herein. An example of using an AIML model to obtain WTRU location is shown in FIG. 4 at 400. Such a positioning method may be referred to as AIML based positioning or AIML positioning in the example described herein. As shown in FIG. 4 at 400, the WTRU provides measurements (e.g., timing, phase, power measurements such as RSTD, time of flight, ToA, ToD, carrier phase measurement, carrier phase difference measurement, RSRP, RSRP per path) as inputs to the AIML model and the WTRU obtains the WTRU location from the AIML model. The output of the AIML model may be referred to as an “inference”.

[0147] As an input to the AIML model, if the AIML model is associated with or trained with measurements from more than one TRPs, the WTRU may use measurements made from more than one TRPs. If the AIML model is trained with measurements from more than one TRPs, the WTRU may receive an indication or configuration from the network about identification information about the TRPs (e.g., TRP IDs, PRS IDs) the AIML model is trained with. In the examples described herein, “AIML” and “AI / ML” can be used interchangeably.

[0148] Examples of inputs for an AIML model for positioning may include one or more of (e.g., any combination of) the following: RSRP of PRS resource(s); Statistical measure(s) of RSRP (e.g., mean, variance etc.) per PRS resource(s); Maximum or minimum values of RSRP per PRS resource(s); RSRP of PRS resource(s) per path; RSRP of PRS resource(s) per antenna port; Reference signal carrier phase (RSCP) of PRS resource(s) per path; RSCP of PRS resource(s) per antenna port; RSTD and / or RSCPD of PRS resource(s); Statistical measures of RSTD per PRS resource(s); Maximum or minimum values of RSTD per PRS resource(s); RSTD and / or RSCPD of PRS resource(s) per path; RSTD and / or RSCPD of PRS resource(s) per antenna port; Time of arrival per PRS resource(s); Time of arrival per PRS resource(s) per path; Time of arrival per PRS resource(s) per port; Statistical measure of Time of arrival per PRS resource(s); Maximum or minimum value of time of arrival per PRS resource(s); CIR estimated based on DL-RS(s) (e.g., PRS, CSI-RS, DM-RS) where CIR may be associated with a TRP or TRPs; PDP estimated based on DL-RS(s) (e.g., PRS, CSI-RS, DM-RS) where CIR may be associated with a TRP or TRPs; and / or DP estimated based on DL-RS(s) (e.g., PRS, CSI-RS, DM-RS) where CIR may be associated with a TRP or TRPs.

[0149] A WTRU may be configured to report output of an AIML model from the WTRU to the network.

[0150] In examples, the WTRU may receive a request to report the location estimate determined by the WTRU and / or AIML model at the WTRU.

[0151] Examples of output for an AIML model for positioning may include one or more of (e.g., any combination of) the following: a Location estimate expressed in terms of geographical coordinates; and / or a Location estimate expressed in terms of relative coordinate with respect to a reference location (e.g., TRP location, location of a PRU, indicated location).

[0152] If the WTRU receives a request from the network to report location estimate, the WTRU may report, in addition to the location estimate, a timestamp (e.g., expressed in terms of SFN, absolute time). The timestamp may indicate at least one of the following: When the location estimate was made by the WTRU or AIML model; When the location estimate is valid (e.g., the location estimate made by the AIMLmodel is valid at the absolute time indicated by the timestamp); and / or when the location estimate is reported by the WTRU.

[0153] If the WTRU receives a request from the network, the WTRU may report the validity duration. The validity duration may express how long the location estimate is valid. The WTRU may report the validity duration in terms of the number of slots, frames, subframes, symbols, SFN, absolute time, etc. For example, the WTRU may report that the location estimate reported by the WTRU is valid for 24 hours from the time the network receives the WTRU report or the time when the WTRU transmits the report to the network.

[0154] FIG. 5 depicts an example of hierarchies in PRS configurations at 500. As illustrated in FIG. 5, PRS parameters may be organized in a hierarchical manner. Parameters associated with a higher layer may be used by parameters at lower layer(s). For example, if a frequency layer has a parameter comb factor = 2, PRS resource sets, TRPs and PRS resources under the frequency layer can also use comb factor =2. Organizing the parameters in a hierarchical manner may reduce signaling overhead from the network.

[0155] Examples of usage of a ground truth label quality indicator are discussed herein.

[0156] An example of training an AIML model at the WTRU is shown in FIG. 6 at 600. In the example, an AIML model is trained with measurements and desired output (e.g., a ground truth). The ground truth may be the location of the WTRU, expressed by geographical coordinates. In examples, the ground truth may be associated with the inputs (e.g., measurements) to the AIML model. The “ground truth” and “UE location estimate” may be used interchangeably in the examples herein.

[0157] In examples, the ground truth may be the location of the PRU or WTRU. This location may be known by the network. In ^examples, the ground truth may be derived by the WTRU or PRU using a RAT dependent positioning method or RAT independent positioning method. The WTRU may determine the WTRU location estimate using a RAT dependent positioning method or RAT independent positioning method.

[0158] The measurements used as an input to the AIML model may include one or more of, but are not limited to RSTD (Reference Signal Time Difference), RSRP (Reference Signal Received Power), RSCP (Reference Signal Carrier Phase), RSCPD (Reference Signal Carrier Phase Difference), CIR, PDP, and / or DP for example. The output from the AIML model may be compared against the desired output and difference between the two may be used to train the AIML model (e.g., adjust weights in the AIML model) so that the difference between the actual output and desired output can be minimized.

[0159] Ground truth indicators are discussed herein. The ground truth may have an associated ground truth label quality indicator. Based on the quality indicator the WTRU may determine whether to use the ground truth fortraining or not. An example of usage of the ground truth label quality indicator is shown in Table 1. In examples, the WTRU may determine to weigh the ground truth by the quality indicator. In the table below, “Label quality indicator” can be used interchangeably with “Ground truth label quality indicator.”

[0160] Table 1, below, shows an example of label quality indicator and ground truth.

[0161] In the examples described herein, “ground truth” and “ground truth label” may be used interchangeably. In the examples described herein, “ground truth label quality indicator”, “quality indicator” and “ground truth quality indicator” may be used interchangeably.

[0162] In examples, the ground truth label quality indicator may be a hard indicator, where the value of “1” and “0” may indicate that the associated ground truth is suitable or unsuitable for training an Al ML model, respectively. In examples, “1” and “0” may indicate that the associated ground truth is reliable or not unreliable fortraining an AIML model, respectively. In examples, “1” and “0” may indicate that the associated ground truth is valid or invalid for training an AIML model, respectively. In examples, a hard indicator of “1” may indicate that the associated ground truth is generated by a PRU whose location may be known by the network. In examples, a hard indicator of “0” may indicate that the associated ground truth is generated by a WTRU whose location estimate may be generated by the WTRU based on the measurements. In examples, the ground truth label quality indicator may be a soft indicator. The value of “0.8” may indicate relatively high confidence in using the associated ground truth fortraining an AIML model. On the other hand, the value of “0.2” may indicate relatively low confidence in using the associated ground truth fortraining an AIML model.

[0163] In examples, for soft or hard quality indicators, the value of “1” may correspond to the ground truth generated with no or minimum uncertainty. For a soft quality indicator with value less than 1 and greater than 0, it may be used to indicate quality of the ground truth generated with uncertainty. For a soft or hardquality indicator with the value equal to 0, it may indicate that the ground truth label quality indicator cannot be assigned to the ground truth.

[0164] In examples, the ground truth label quality indicator x=1 may indicate that the location information associated with the ground truth label may be generated for or by the positioning reference unit (PRU). The ground truth label quality indicator between 0 and 1, e.g., 0<x<1, may indicate that the location information associated with the ground truth label may be generated by the WTRU using a RAT dependent positioning method or RAT independent positioning method. If the ground truth label quality indicator is 0, e.g., x=0, it may indicate that the WTRU generated the virtual ground truth and or virtual measurements based on available ground truth or measurements. For example, the WTRU may determine the virtual ground truth or virtual measurements based on interpolation of available ground truth(s) or measurement(s) at the WTRU. The WTRU may determine to generate virtual measurements using an AIML model at the WTRU based on available measurements. In examples, the WTRU may generate a virtual ground truth based on measurements and / or virtual measurements. The WTRU or network may determine to associate the virtual ground truth with the ground truth label quality indicator value of 0. When the WTRU reports virtual measurements (e.g., interpolated or extrapolated measurements) to the network, the WTRU may indicate to the network that the reported measurements are virtual measurements (e.g., with a flag indicating whether the measurements are virtual measurements or actual measurements made on the received PRS).

[0165] In examples, the indicator may have a range defined by minimum value and maximum value. For example, the minimum and maximum value for the soft indicator may be 0 and 1 , respectively. The WTRU may be preconfigured or configured with the range of the indicator by the network. The granularity of the soft indicator may be predefined, e.g., 0.1, 0.01, etc.

[0166] In examples, the WTRU may determine parameters related to the ground truth label quality indicator (e.g., granularity of a soft indicator, hard or soft indicator) based on WTRU capability. For example, the WTRU may be able to process a hard indicator for the ground truth quality indicator. The WTRU may indicate such limitation by signaling the WTRU capability to the network.

[0167] In examples, the indicator may be a range of values, indicating uncertainty in the ground truth (e.g., WTRU or PRU location estimate). For example, if the ground truth is expressed as a coordinate (x, y), the indicator may be a range of uncertainty for each value, x and y, such as x±0.2 meters, for example. In the example, ±0.2 meters is the uncertainty in the ground truth in each coordinate.

[0168] In examples, a ground truth label quality indicator may be associated with each coordinate of the ground truth. For example, there may be two indicators for a ground truth (x, y) where each of “x” and “y” may be associated with a ground truth label indicator.

[0169] The associated ground truth label quality indicator may indicate a confidence level of the ground truth location. For example, the ground truth obtained by DL-TDoA in non-Line of Sight (NLOS) heavy environment may be associated with a low ground truth label indicator. On the other hand, the ground truth obtained by DL-TDoA in Line of Sight (LOS) heavy environment may be associated with a high ground truth label indicator.

[0170] In examples, the WTRU may be configured with an association table which associates the ground truth label quality indicator with a range of uncertainty in the ground truth. In examples, the ground truth label quality indicator can become an index for the configured association table where the index indicates the uncertainty (e.g., ±2 meters) in the ground truth.

[0171] In examples, the ground truth label quality indicator may be associated with more than one ground truths. For example, the WTRU may determine a ground truth label quality indicator associated with more than one ground truths where each ground truth may be determined at different time instances (e.g., at different day, hour, minute, second). The WTRU may receive a ground truth label quality indicator from the network associated with more than one ground truths where each ground truth may be determined at different time instances (e.g., at different day, hour, minute, second).

[0172] The WTRU may receive an indication or request from the network to determine the ground truth label quality indicator for N ground truths where N is the number of ground truths and configured by the network. In examples, N may correspond to different time instances the WTRU determines the ground truth. The time instance may correspond to the measurement reporting instances (e.g., periodic measurement reporting instances, semi-persistent reporting instances) or measurement instances.

[0173] In examples, the WTRU may receive information about the reference ground truth (e.g., geographical coordinates) from the network in assistance information (e.g., via LPP, RRC) for the WTRU to know the reference used, by the network, to derive the relative threshold.

[0174] A WTRU may be configured to determine time and area validity.

[0175] In examples, the WTRU may make measurements on the received PRS. The WTRU may send a request for measurement forwarding from the network. The WTRU may determine training data based on one or more of: the measurements made by the WTRU, forwarded measurements, a determined WTRU location estimate, ground truth, forwarded WTRU location estimates, and / or ground truths. Using thedetermined training data, the WTRU may train an Al ML model at the WTRU. The WTRU may determine validity conditions of the AIML model based on the training data (e.g., measurements, ground truth), and / or the association rule (e.g., threshold for the density of WTRUs in a cell). The WTRU may report the determined validity condition to the network. Based on the validity condition, the WTRU may determine to use the AIML model for positioning or perform a fallback procedure (e.g., report an error to the network, perform RAT dependent or independent positioning).

[0176] In examples, the WTRU may generate a dataset or receive, from the network, a dataset with which the WTRU trains an AIML model. The dataset may be associated with a dataset ID. Examples of a dataset are described herein.

[0177] In examples, a dataset may include some or all of the following information: Ground truth(s) or location estimate(s) (PRU or WTRU location); Measurements made by WTRU / PRU at each ground truth; a Timestamp (e.g., absolute time, SFN, relative time with respect to the SFN initialization time) for each measurement and / or ground truth; PRS configs or positioning methods (e.g., RAT dependent, RAT independent) used to generate measurements or determine location estimates; a Number of ground truth(s) and / or the number of measurements associated with ground truth(s) included in the dataset; a Ground truth label quality indicator associated with the ground truth; and / or an Associated dataset ID (e.g., indicated during periodic delivery of PRU / UE measurement forwarding). In examples, PRS configuration(s) (e.g., PRS resource IDs, TRP IDs) may be associated with an ID or index (e.g., PRS configuration ID). The dataset may be associated with the PRS configuration ID. The WTRU may determine, from the PRS configuration ID, that the dataset associated with the PRS configuration ID is generated based on the measurements made with the PRS configuration ID. In examples, the WTRU may determine quality of the dataset based on the ground truth label quality indicator associated with the dataset The WTRU may receive such an indicator from then network. In examples, if the WTRU receives a request from the network, the WTRU may report the PRS configuration ID associated with the dataset used to train the AIML model.

[0178] In examples, a dataset may include some or all of the following information: Ground truth(s) (e.g., WTRU / PRU location); Ground truth label quality indicator(s) associated with the ground truth(s); Measurements made by WTRU or PRU at each ground truth; Timestamps (e.g., absolute time, SFN) for each measurement and / or ground truth; PRS configurations used to generate measurements; a Number of ground truth(s) or measurements included in the dataset; and / or an Associated dataset ID indicated inactivation / deacti vation command. The network may determine to terminate in the middle of PRU / WTRU measurement forwarding.

[0179] In examples, a dataset may include some or all of the following information: a Dataset ID indicated in LPP or RRC message, included in PDCCH or PDSCH; PRS config or positioning method(s) used to generate measurements or determine ground truth in the dataset; and / or a Timestamp (e.g., absolute time, SFN).

[0180] In examples, a dataset may include some or all of the following information: PRS configurations; Start time(s) and / or end time(s) (e.g., or duration of measurements); and / or an Associated dataset ID included in the message containing start or end time of the measurement and / or PRS configuration.

[0181] In examples, a dataset may include some or all of the following information: a PRS configuration; an Activation and / or deactivation command; and / or a dataset ID associated with the activation / deactivation command.

[0182] The Content of forwarded measurements from the network is discussed herein.

[0183] The target WTRU may receive measurements, made by a PRU or another WTRU from the network. “PRU” and “WTRU” may be used interchangeably in the examples discussed herein. The target WTRU may receive information that is determined by the network. The information may include one or more of (e.g., any combination of) the following.

[0184] The information may include measurements (e.g., timing, power, phase, CIR, PDP, DPs) made by the PRU and DL-RS resource IDs and / or RS configurations (e.g., PRS resource set IDs, frequency layer IDs, TRP IDs) associated with the measurements; a Location of the PRU (e.g., geographical coordinates of the PRU); a Location or location estimate of the WTRU; Location information and associated measurements; PRU and / or WTRU ID; Timestamp(s) (e.g., absolute time, symbol index, slot index, subframe index, frame index, SFN) associated with measurements and / or inference where the timestamps may indicate when the measurements are made or when the measurements, ground truths and / or WTRU location estimates are reported by the PRU or WTRU; a Number of ground truths or location estimates to be provided; and / or a Number of repetitions for provision of ground truth and associated information. In examples, a timestamp in the forwarded measurement may be associated with one set or more than one set of measurements, ground truth(s) and / or WTRU location estimate(s). For example, one timestamp may be associated with measurements and ground truth(s) associated with more than one PRUs. Such a timestamp may indicate, for example, the time when the network forwarded the measurements and / or ground truth to the WTRU.

[0185] The WTRU may receive one or more (e.g., all) of the aforementioned measurements, and / or associated information made by the PRU as assistance information from the network via LPP or RRC message, for example.

[0186] In examples, the WTRU may receive, from the network, measurements made by more than one PRUs. The WTRU may receive measurements and / or inference from the network in one set of assistance information or more than one set of assistance information. Each set may contain measurements made by one PRU.

[0187] In examples, the WTRU may receive measurements from more than one PRUs or WTRUs in a sequential manner from the network. For example, the WTRU may be configured with a set of PRUs or WTRUs identified by indices. If periodic delivery of measurements is configured, the WTRU may receive an indication from the network of the order of delivery of measurements and / or ground truth. For example, the WTRU may receive an indication that the measurements and associated ground truth made by PRUs will be delivered to the WTRU first, followed by the delivery of measurements and associated location estimate made by WTRUs. The WTRU may receive a set of indices. Each index may correspond to a WTRU or PRU, from the network, indicating the order of delivery. For example, if there are three PRUs with respective index, 1, 2 and 3, the WTRU may receive the set of indices

[0123] indicating an order of delivery of the measurements from PRUs. In examples, the WTRU may be configured to receive measurements in increasing order of the indexes.

[0188] In examples, the WTRU may receive forwarded measurements in the form of assistance information from the network. For example, the WTRU may receive the assistance information in an LPP or RRC message. The WTRU may receive the assistance information from the network periodically or in an aperiodic manner (e.g., one-shot). The WTRU may send a request for periodic or aperiodic delivery of assistance information from the network. The WTRU may indicate a periodicity of the delivery of assistance information from the network.

[0189] A WTRU may be configured to determine which ground truth(s) or measurement(s) to use for training an Al ML model at the WTRU.

[0190] In examples, the WTRU may determine to select or determine measurements and associated ground truth(s) fortraining an AIML model at the WTRU.

[0191] In examples, the target WTRU may determine to select forwarded measurements and / or measurements made by WTRUs based on consistency among measurements. Examples of consistency may include but are not limited to the following.

[0192] In examples, two measurements (e.g., power, phase, timing, CIR, PDP, DP) may be considered consistent if the measurements are made by the same type of WTRU (e.g., reduced capability WTRUs or PRUs), where the two measurements are a forwarded measurement and the measurement made by the target WTRU.

[0193] In examples, two measurements may be considered consistent if they are made using the same PRS configuration (e.g., two measurements are associated with the same PRS resource ID) where the two measurements are forwarded measurement and the measurement made by the target WTRU.

[0194] In examples, two measurements may be considered consistent if they are made by the same category of WTRU (e.g., WTRUs with the same WTRU capability) where the two measurements are the forwarded measurement and the measurement made by the target WTRU.

[0195] In examples, two measurements may be considered consistent if the measurements are made within a time interval (e.g., expressed in terms of seconds, hours, number of symbols, number of slots, number of frames, number of subframes) where the two measurements are the forwarded measurement and the measurement made by the target WTRU.

[0196] The WTRU may determine to select the measurements and / or associated ground truths based on their quality. In examples, the WTRU may determine to use measurements and associated ground truth(s) if the ground truth label quality indicator(s) (e.g., soft indicator, standard deviation of the ground truth) associated with the ground truth(s) is above a configured threshold. In examples, the WTRU may determine to use the measurements and associated ground truth(s) if the quality indicator for the measurements (e.g., uncertainty, variance, standard deviation) is below the configured threshold.

[0197] The measurements described herein may refer to the forwarded measurements and / or measurements made by the target WTRU.

[0198] Validity conditions for the AIML model may be determined by the network.

[0199] In examples, the WTRU may receive time and / or area validity conditions for the AIML model at the WTRU from the network (e.g., LMF, gNB). For example, the WTRU may report measurement results and / or a determined WTRU location to the network. If the WTRU receives a request to report information related to AIML models at the WTRU, the WTRU may report parameters related to AIML model(s) at the WTRU. The parameters may include, but are not limited to one or more of (e.g., any combination of) the following: a Model ID; a Number of layers; numbers of neurons per layer; a Number of inputs to the AIML model; and / or an Input type (e.g., measurements such as CIR, PDP, DP, RSRP, RSTD, RSCPD used as input).

[0200] A WTRU may be configured to determine time validity conditions.

[0201] In examples, the WTRU may determine time validity conditions based on the measurements made by the WTRU and / or forwarded measurements. The WTRU may determine time validity conditions based on the forwarded ground truth(s) and WTRU location estimate(s), and / or WTRU location estimate® determined by the WTRU. An example is illustrated in FIG. 7 at 700. In the illustration, the target WTRU receives forwarded measurements from the LMF where the measurements are made by other WTRUs (e.g., WTRU1, WTRU2, WTRU3 and WTRU4 in the illustration) and / or PRUs. The WTRU may determine to use forwarded measurements and / or associated ground truth(s) as training data to train the AIM L model(s) at the WTRU. The WTRU may determine to use the measurements made by the WTRU and / or ground truth or WTRU location estimate determined by the WTRU to train the AIML model(s) at the WTRU. The WTRU may determine a time validity of the trained AIML model based on characteristics of forwarded measurements and associated ground truths, and / or measurements and associated ground truth or location estimate made or determined by the WTRU.

[0202] Based on the forwarded measurements and / or the measurements made by the target WTRU, the target WTRU may determine an effective measurement duration. Examples of parameters for effective measurement duration may be at least one or combination of the following: a Duration of the measurement (e.g., expressed in terms of the number of slots, symbols, frames, subframes); a Periodicity of the measurement; and / or Start and / or stop times of the measurement expressed in terms of absolute time, relevant time with respect to a reference, SFN, subframe index, frame index, symbol index, slot index, for example.

[0203] In examples, the start and / or end times of the effective measurement duration may be expressed in terms of timestamps.

[0204] In examples, each forwarded measurement or the measurements made by the target WTRU may be associated with an ID for a measurement time window.

[0205] The target WTRU may determine the effective measurement duration. As illustrated in FIG 7, the target WTRU may determine the effective measurement duration based on measurement duration(s) made by WTRUs or PRUs. For example, the effective measurement duration may be a part of the measurement durations made by other WTRUs or PRUs.

[0206] As illustrated in FIG. 8 at 800, the WTRU may determine a periodicity of the effective measurement during the effective measurement duration based on the periodicity of the measurements made by otherWTRUs. For example, the effective measurement periodicity may be the shortest periodicity among periodicities of the measurements reported by the other WTRUs.

[0207] In examples, based on the effective measurement duration, the WTRU may determine time validity based on a configured association rule. For example, the WTRU may be configured with an association rule associating the effective measurement duration and time validity. An example rule is shown in Table 2.

[0208] Table 2 shows an example of an association rule between time validity and measurement duration.

[0209] In examples, the WTRU may determine the effective measurement duration and / or periodicity based on one or more of (e.g., any combination of) the following parameters for the measurement(s) made by other WTRU(s): the Time window IDs used to generate the measurements; a Duration of the measurements; and / or a Start and / or end time of the measurements (e.g., expressed in absolute time).

[0210] In examples, the WTRU may receive, from the network, restrictions on the effective measurement duration (e.g., duration, start, end time). For example, the WTRU may receive an indication or configuration (e.g., via LPP, RRC, DCI, MAC-CE) about the restriction on the start or end time of the effective measurement in terms of SFN, frame or subframe index, slot index, symbol index and / or absolute time. For example, the WTRU may receive an indication from the network to set the start time of the effective measurement duration later than 3PM EST on Jan 2, 2025. In examples, the WTRU may receive an indication from the network to set the effective measurement duration longer or shorter than the configured threshold (e.g., 1 hour).

[0211] The definition of timing is discussed herein.

[0212] The validity conditions for WTRU’s AIML model may depend on the dataset used to train the model. As the environment changes, the original dataset used to train the model may not be relevant to the new environment. To determine the validity of an AIML model over time, an AIML positioning timeline can be used.

[0213] A network may acquire measurements and position information from WTRUs and PRUs. These measurements may then be processed and reformatted into a dataset that can be used by WTRUs to trainan Al ML model. The Network Dataset Time (TNW) may refer to the time network completes the process of preparing this positioning dataset.

[0214] The WTRU may make measurements on the received PRS. It can also estimate its position using positioning mechanisms (e.g., RAT dependent positioning methods). The Local Dataset Time (TLocal) may be the time the WTRU finishes the process of gathering measurements and positioning information and reformatting it into a local dataset. This dataset may be combined with the one received from the network and used to train the AIML model.

[0215] The WTRU may start training an AIML positioning model as soon as the dataset(s) become available. Depending on the computation and power resources at the WTRU, the training process could take hours or days to complete. The Model Training Time (TModel) may refer to the time the training of an AIML model is complete and it is ready to be used for inference.

[0216] To optimize resource usage, the WTRU may be configured to perform training at night (e.g., only at night) or when it is connected to an external power source (e.g., when it is being charged). However, the WTRU should not wait for a long time after TLocal or TNW to start the training as a dynamic environment could render the trained model obsolete after the training. A maximum “Training Delay” value can be used to make sure the WTRU starts training as soon as possible after the datasets become available.

[0217] The WTRU may be configured, by the network, with an AIML model and the model may be associated with TNW, T ocai and / or Twodei.

[0218] The validity of the AIML model can be determined by comparing the current time with any or a combination of the times mentioned above. Additionally, or alternatively, a “Validity Expiration Warning” time can be used (e.g., before the actual expiration of the model) so that the WTRU or network can prepare for dataset generation and training of a new model. Thus, by the time the current model expires, a new model can be ready to be used for inference.

[0219] In examples, the WTRU may be configured with a threshold (e.g., via LPP or RRC message). The WTRU may determine time validity of the AIML model based on the current time (e.g., the time the WTRU determines to use the AIML positioning, the time the WTRU determines to generate inference using the AIML model, the time the WTRU receives a request from the network to perform AIML based positioning) and TNW, TLocal and / or TModel. For example, the threshold may be the expiry duration expressed in seconds. The WTRU may determine the elapsed time by calculating the difference between TLocal and the current time and comparing the difference against the threshold. If the difference is above the threshold, the WTRU may determine that the AIML model associated with TLocal is invalid. If thedifference is less than or equal to the threshold, the WTRU may determine that the Al M L model associated with TLocal is valid.

[0220] The network and Local dataset can be created simultaneously. To reduce the duration between when the dataset becomes available and when a trained model becomes operational, the WTRU and network can coordinate the dataset preparation processes to ensure the network dataset and Local dataset become available around the same time.

[0221] The process explained here is applicable to offline learning of the AIML model where a dataset is created first, then the model is trained on the dataset, and then the model is used for inference. In an online training setting, the training process can continue with new local or network datasets while it is also being used for inference.

[0222] A WTRU may be configured for determination of area validity conditions.

[0223] In examples, the WTRU may determine to use the measurements made by the WTRU and / or ground truth or WTRU location estimates determined by the WTRU to train the AIML model(s) at the WTRU. In examples, the WTRU may determine an area validity of the trained AIML model based on characteristics of forwarded measurements and associated ground truths, and / or measurements and associated ground truth or location estimate made or determined by the WTRU.

[0224] Examples of an area may include one or more of the following. In examples, an area may be defined as a group of one or more cell IDs. In examples, an area may be defined by an area ID. In examples, an area may be outside of the cell coverage and defined by a zone ID. In examples, a cell may include more than one areas, wherein each area is associated with an area ID, and the cell ID is associated with each area ID.

[0225] An example is illustrated in FIG. 9 at 900, where the target WTRU determines area validity based on the measurements forwarded by the LMF. At 902, WTRUs and / or PRUs may send measurements to an LMF. The target WTRU may receive measurements made by WTRUs or PRUs. The measurements may be associated with a cell ID or area ID. As illustrated in FIG. 9, the target WTRU may receive measurements made by WTRUs in cell#1 , cell#2 and cell#3 from the LMF. The WTRU may determine to select the forwarded measurements fortraining an AIML model (e.g., as shown at 904). Based on the number of the measurements selected by the WTRU, the WTRU may determine the area validity for the AIML model (e.g., as shown at 906).

[0226] The WTRU may determine that the AIML model is valid for an area or cell based on one or more of (e.g., any combination of) the following.

[0227] In examples, the target WTRU may be configured with a threshold for the number of WTRUs per area (e.g., cell). If the number of WTRUs in the forwarded measurements associated with a cell is greater than the threshold, the WTRU may determine that the AIML model trained with the measurements and the corresponding ground truth is valid in the cell.

[0228] In examples, the WTRU may be configured with a threshold for density of WTRUs per area (e.g., cell). For example, the density may be expressed in terms of the number of WTRUs per unit (e.g., square meter, square feet, square miles). One example of the threshold for the density is 10 WTRUs per 100 square meters. If the density of the ground truth(s) and / or estimated WTRU location estimate(s) for an area (e.g., cell) is greater than the threshold, the WTRU may determine that the AIML model trained based on the ground truth and associated measurement is valid within the area.

[0229] In examples, the target WTRU may determine that the forwarded measurements and / or target WTRU’s measurements satisfy a criterion (e.g., the density of WTRUs per cell is greater than threshold) in more than one cells. In such a case, the target WTRU may determine that the AIML model is valid in more than one cells. For example, in the example illustrated in FIG. 9, the criterion may be that measurements and associated ground truth(s) from at least 2 WTRUs need to be collected by the target WTRU. In this case, the target WTRU may determine that the AIML model is valid for cell #1 and cell #3 since the target WTRU was able to collect measurements from 5 and 2 WTRUs from cell #1 and cell #3, respectively.

[0230] In examples, the target WTRU may determine the number of WTRUs in an area (e.g., cell, a collection of cells) based on one or more of (e.g., any combination of) the following.

[0231] In examples, the target WTRU may determine whether the WTRU belongs to an area based on a ground truth or location estimate (e.g., determined by the WTRU or target WTRU) associated with the WTRU. For example, if the ground truth is located within the area, the target WTRU may consider the WTRU to be located within the cell.

[0232] In examples, the target WTRU may determine whether the WTRU belongs to an area based on the location of TRPs from which the WTRU received PRS and made measurements (e.g., CIR, POP, DP, timing, phase) from. If the WTRU makes measurements from TRPs in a cell, the target WTRU may consider that the WTRU is associated with the cell.

[0233] The WTRU may determine the ground truth(s) or WTRU location estimate(s) to use for training based on a criterion (e.g., consistency, ground truth quality indicator).

[0234] In examples, the network may introduce restrictions on the area from which training data is derived. For example, the WTRU may receive an indication from the network to use forwarded measurementsand / or ground truths from an indicated area or cell. The indicated area or cell may be expressed in the form of area ID and / or cell I D(s).

[0235] A WTRU may be configured to determine the validity of a dataset.

[0236] In examples, the WTRU may determine the validity of a dataset ID based on an ID broadcast from the network. The WTRU may determine the validity of a dataset ID based on the broadcasted dataset ID from the network. For example, if the WTRU has a dataset ID#1 and the WTRU receives a broadcast message from the network that the dataset I D#1 is valid within the area where the WTRU can receive the broadcast message, the WTRU may determine that the dataset I D#1 is valid and uses the dataset for training the AIML model. The inference (e.g. , location estimate) generated by the trained Al ML model may also be valid within the area where the WTRU can receive the broadcast message.

[0237] The WTRU may be configured to verify and / or validate that it has a valid Al model before activating the model for inference. Such validation may be based on ensuring that the validity condition associated with the Al model matches with a validity indication from the network for Al operation in the cell and / or logical area. In a solution the validity indication may be a broadcast in system information. In examples, the validity indication may be broadcast in existing broadcast messages (e.g., master information block (MIB), system information block 1 (SIB1), SIB2, or the like). In examples, a new system information block may be defined e.g., SIB-AI may carry the validity indication for any Al model operation. In examples, use case specific system information blocks may be defined (e.g., SI B-AI-POS may validity indication specific for positioning features). The validity indication may comprise one or more of: a logical ID (e.g., a dataset ID, a vendor ID, an MNO (Mobile Network Operator) ID, an MCC (Mobile Country Code), an MNC (Mobile Network Code) or the likes); a range of logical IDs; a version number; a timestamp information; an area information (e.g., RAN area, Tracking area, or the likes); etc.

[0238] In examples, the WTRU may determine to activate the AIML model at the WTRU if the validity indication matches with the ID associated with the AIML model (e.g., if the dataset ID associated with the AIML model at the WTRU matches with the broadcasted dataset ID).

[0239] The WTRU may deactivate an Al model if the validity indication from the network doesn’t match the Al model or ID associated with the AIML model currently active at the WTRU. The WTRU may be configured to disable Al operation and return to non-AI operation if the validity indication from the network doesn’t match with any Al model in the WTRU.

[0240] In examples, the WTRU may be configured to apply a dataset acquisition procedure from the network. For example, the WTRU may trigger the dataset acquisition procedure upon one or more of thefollowing conditions: upon power on, upon cell-reselection, return from out of coverage, upon reconfiguration with sync completion, upon entering a cell from another cell that does not support Al operation, upon entering an area different from an area associated with the latest received validity indication, upon determining that validity indication from the network doesn’t match with any Al model in the WTRU, upon receiving an indication that the system information associated with validation indication has changed, upon receiving a positioning request from higher layers (e.g., via RRC or LPP message), or whenever the WTRU determines that it doesn’t have valid version of stored SIB associated with the validity indication.

[0241] When the dataset acquisition procedure is triggered, the WTRU may trigger lower layers to initiate a random access procedure if there is no UL grant available. In one solution the WTRU may transmit a dedicated preamble preconfigured for dataset acquisition. In another solution, if a UL grant is available or received, the WTRU may transmit an RRC message to request for dataset acquisition. As a response the WTRU may receive the dataset via one or more of the following: a higher layer message, an RRC message, a user plane PDU, and / or a broadcast transmission etc.

[0242] In examples, when the dataset acquisition is triggered, the WTRU may determine to transmit a request for measurement forwarding from the LMF.

[0243] If the WTRU receives a broadcast message containing a dataset ID which the WTRU does not have, the WTRU may determine to request the dataset from the network. The WTRU may receive the dataset in the form of assistance information or measurement forwarding from the network, for example.

[0244] A WTRU may be configured to determine the validity of an AIML model.

[0245] In examples, the WTRU may determine that the AIML model is valid (e.g., in terms of the area or time) based on the timing information (e.g., timestamp) and / or area (e.g., cell) the inference and / or input (e.g., measurements) of the AIML model is associated with.

[0246] Validity conditions for an AIML model are discussed herein.

[0247] As illustrated in the following non-exhaustive examples, the WTRU may determine time or area validity for an AIML model.

[0248] In examples, the WTRU may determine that the time validity condition for the AIML model can be expressed in terms of the duration with respect to the reference time (e.g., 24 hours starting at the reception timing of the validity condition for the AIML model from the network, 24 hours staring from the timestamp of the input to the AIML model). In examples, the reference time may be absolute time (e.g., Jan. 2nd, 2025, 5PM).

[0249] In examples, area validity for an Al M L model may be expressed in terms of validity area (e. g. , cell ID, a collection of cell IDs).

[0250] In examples, validity conditions may be combined. For example, the WTRU may determine a validity condition by combining area and time validity. For example, the WTRU may determine that the Al ML model is valid for cell #1 from Jan. 2nd, 2025, 5PM for 24 hours.

[0251] Timestamps for measurements are discussed herein.

[0252] In examples, the WTRU may determine to use measurements (e.g., CIR, PDP, DP, RSTD, RSCPD, RSRPP, RSRP) as an input for the AIML model. The WTRU may make measurements based on the PRSs received from TRPs, for example. The measurements may be made by PRUs and / or other WTRUs, which may be forwarded by the LMF. Each measurement or a set of measurements (e.g., comprising measurements corresponding to different PRS resource IDs, PRS resource set IDs, TRP IDs) may be associated with a (e.g., unique) timestamp. The WTRU may determine a timestamp for the input (e.g., a set of measurements) for an AIML model based on one or more of (e.g., any combination of) the following criteria.

[0253] In examples, the WTRU may determine a timestamp for the input for an AIML model based on the average value of the timestamps associated with each measurement for the input for the AIML model. For example, as an input for an AIML model, the WTRU may determine a PDP for each channel between the WTRU and 16 TRPs and each PDP estimate may be associated with a timestamp. The WTRU may determine the average value of the 16 timestamps as the timestamp for the input for an AIML model.

[0254] In examples, the WTRU may determine a timestamp for the input for an AIML model based on the minimum or maximum value of the timestamps associated with each measurement for the input for the AIML model. For example, as an input for an AIML model, the WTRU may determine a PDP for each channel between the WTRU and 16 TRPs and each PDP estimate may be associated with a timestamp. The WTRU may determine the earliest or latest value of the 16 timestamps as the timestamp for the input for an AIML model.

[0255] In examples, the WTRU may determine a timestamp for the input for an AIML model based on an indicated timestamp from the network.

[0256] In examples, the WTRU may determine a timestamp for the input for an AIML model based a reference among the input. For example, the WTRU may receive a configuration indicating which TRP, PRS resource ID, and / or PRS resource set ID to use as the reference to determine the timestamp for the input. For example, as an input for an AIML model, the WTRU may determine a PDP for each channelbetween the WTRU and 16 TRPs. The WTRU may receive an indication from the network to use the timestamp for TRP#5 as the reference timestamp. The WTRU may determine to associate the timestamp for the measurement made from PRSs transmitted from TRP#5.

[0257] The validity of a model may be determined based on a timestamp for an inference which is determined based on the associated measurements.

[0258] For example, the WTRU may determine that the AIML model is valid for 24 hours starting at January 2nd 2PM in 2025. If the timestamp for the input for the AIML model is January 4th 3PM in 2025 and the WTRU uses the measurement to obtain the inference (e.g., location estimate generated by the AIML model) from the AIML model, the WTRU may determine to associate “January 4th 3PM in 2025” with the inference. Based on the inference or associated with the inference, the WTRU may determine that the inference is expired with respect to validity time of the AIML model. The WTRU may not use the AIML model for AIML based positioning and the WTRU may report the outcome (e.g., AIML model is expired).

[0259] In examples, the WTRU may compare the timestamp associated with the input to the AIML model and expiry time of the AIML model. If the timestamp associated with the input is earlier than the expiry time of the AIML model, the WTRU may determine to use the AIML for AIML based positioning. If the timestamp associated with the input is later than the expiry time of the AIML model, the WTRU may determine to report that the AIML model is expired or use the fallback positioning methods (e.g., RAT dependent positioning method) if it is configured to do so by the network. In the examples described herein, the expiry time, time validity or time validity condition may be used interchangeably. For example, if the WTRU determines that the timestamp associated with input (e.g., measurements) to the AIML model does not satisfy the time validity condition of the AIML mode, the WTRU may determine that the AIML model is expired. The WTRU may determine to report that the AIML model is expired or use the fallback positioning methods (e.g., RAT dependent positioning method) if configured by the network.

[0260] In examples, the WTRU may determine the positioning initiation time which is the time the WTRU determined to use the AIML model (e.g., when the WTRU receives a request from the network to perform AIML based positioning). By comparing the positioning initiation time and the model validity time (e.g., AIML model is valid for 24 hours starting at January 2nd 2PM in 2025), the WTRU may determine the validity of the AIML model. For example, if the initiation time is later than the expiry time of the AIML model, the WTRU may determine not to use the AIML model for AIML based positioning. In examples, if the initiation time is earlier than the expiry time of the AIML model, the WTRU may determine to use the AIML model for AIML based positioning.

[0261] The validity of an AIML model may be determined based on the associated area validity condition.

[0262] In examples, the WTRU may determine the AIML model is valid by comparing an area associated with the input to the AIML model and a validity area. For example, if the input to the AIML model is derived from measurements made in an area that is outside of the validity area associated with the AIML model, the WTRU may determine that the inference generated by the AIML model is not valid. In examples, if at least one of the inputs (e.g., measurements) is made outside of the validity area associated with the AIML model, the WTRU may determine that the inference generated by the AIML model is not valid. If the WTRU determines that the inference generated by the AIML model is not valid, the WTRU may determine not to perform AIML based positioning using the AIML model. The WTRU may report an error (e.g., a cause an indication that the AIML model is not valid) to the network.

[0263] A WTRU may be configured to request to use an AIML model.

[0264] In examples, the WTRU may determine to transmit a request or message to the network, asking whether the WTRU can use a dataset for training or use an AIML model trained based on the dataset. The WTRU may indicate, in the request, information about dataset used to train the AIML model.

[0265] For example, the WTRU may indicate, in the request, the validity condition(s) associated with the model to the network. The WTRU may send a request to the network to use the AIML model based on the associated validity condition(s). In examples, the WTRU may send a request if a validity condition associated with the AIML model is not satisfied. For example, the WTRU may send a request to use the AIML model if the associated time validity condition associated with the AIML model is expired and / or area validity condition associated with the AIML model is not valid. In examples, the WTRU may send information related to the validity condition for the AIML model to the network on every occasion the WTRU determines to use AIML based positioning, or when the WTRU receives a request to perform AIML based positioning.

[0266] In examples, the WTRU may include a dataset ID in the message or request where the dataset ID may be associated with a set of measurements and associated ground truth(s) or location estimate(s), and / or timestamps associated with the measurements or ground truth(s). The dataset ID may be used by the network to determine time or area validity of the AIML model trained with the indicated dataset ID.

[0267] Priority may be used in determining area and / or time validity conditions.

[0268] In examples, the WTRU may determine a priority between area and time validity conditions. For example, the WTRU may be configured with a rule that the WTRU should determine the first validity condition. Based on the first validity condition, the WTRU may determine the second validity condition. Forexample, the WTRU may determine the time validity condition first. Based on the time validity, the WTRU may select measurements and / or ground truth(s) that satisfy the time validity condition. Based on the selected measurements and / or ground truth(s) the WTRU can determine area validity condition.

[0269] In examples, the WTRU may receive an indication of which validity condition to determine first. For example, the WTRU may receive an indication or configuration from the network indicating to determine the area validation condition first. Based on the determined area validity condition, the WTRU may determine time validity condition(s).

[0270] A WTRU may be configured with fallback mechanisms for positioning.

[0271] In examples, if the Al M L model at the WTRU satisfies validity conditions (e.g., both time and validity conditions), the WTRU may perform AIML based positioning. In examples, if the AIML model does not satisfy the time and / or area validity conditions, the WTRU may report an error to the network. In examples, if the AIML model does not satisfy the time and / or area validity conditions, the WTRU may report an error and cause (e.g., invalid AIML model) to the network. If the WTRU is configured with a fallback positioning method (e.g., a RAT dependent positioning method or a RAT independent positioning method), the WTRU may determine to use the fallback positioning method if the AIML model does not satisfy the validity condition.

[0272] A WTRU may be configured with a PRS configuration.

[0273] The WTRU may be configured with a set of measurement time windows and / or associated configurations (e.g., periodicity, duration of a gap) by the network.

[0274] The WTRU may receive an association rule between area and time validation condition (e.g., a configured threshold) and / or a priority of determination between time and area validity.

[0275] The WTRU may determine that the AIML model is valid for the area (e.g., cell, zone in a cell) if the number of WTRUs from which measurements and corresponding ground truths are collected is above the configured threshold.

[0276] In examples, the WTRU may determine area validity based on the geographical distribution or density of WTRUs in the area (e.g., cell(s), zone(s)). For example, the WTRU may be configured with a validity condition in the form of density (e.g., 1 WTRU per 10 square meters, 5 WTRUs per 20 square meters).

[0277] In examples, the WTRU may determine whether to use WTRUs measurements based on consistency among measurements (e.g., if two measurements are made by the target and second WTRU where both WTRUs are the reduced capability WTRU, if two measurements are made using the same PRSconfiguration, if two measurements are associated with the same PRS resource ID, and / or if two measurements are made by the same WTRU type, such as WTRUs in the same category).

[0278] An AIML model may be valid for a duration (e.g., 24 hours) if the timespan and periodicity of collected measurements and corresponding ground truth are above the configured threshold (e.g., the model is valid for 24 hours if the measurements made over 48 hours at 1 hour intervals). If the measurements are made by more than one WTRUs, the timespan may be based on the shortest timespan and the periodicity may be based on the longest periodicity.

[0279] The WTRU may receive an activation command for one of the measurement time windows in the list from the network. The activation command (e.g., MAC-CE) may contain a timestamp (e.g., absolute time), and each measurement time window in the list can be associated with an ID.

[0280] The WTRU may make measurements on the received PRS during the activated measurement time window.

[0281] The WTRU may receive a deactivation command for the measurement time window and determine the duration of the measurement.

[0282] The WTRU may receive forwarded measurements and / or associated ground truths from the network. A timestamp (e.g., absolute time) and / or a measurement time window ID may be associated with the measurements and / or ground truth.

[0283] The WTRU may select which measurements to use for training and train AIML model using the selected measurements.

[0284] The WTRU may receive a priority for time and area validity determination (e.g., the priority may indicate that time validity is determined first and then area validity is determined second).

[0285] The WTRU may determine time validity for the AIML model based on the received association rule (e.g., effective measurement duration determined based on measurement duration, start and / or end time of the measurement period).

[0286] The WTRU may determine an area validity for the AIML model based on the number of WTRUs per area and / or the received associated rule. Additionally, or alternatively, the WTRU may determine area validity for the AIML model based on the effective measurement duration (e.g., the chosen WTRUs to determine the effective measurement duration).

[0287] The WTRU may receive a request to report the determined validity condition. The WTRU may report the determined validity condition to the network (e.g., LMF). The WTRU may receive a request for AIML based positioning.

[0288] Scheduled training time and determination of time validity are discussed herein.

[0289] Training data from the network may not align with the WTRU’s training schedule (e.g., if the WTRU wants to train on Jan 4, 2024, the WTRU may obtain training data acquired by the network in 2022). The WTRU may request for the measurements that are made during a specific time interval and / or area (e.g., cell ID).

[0290] A WTRU may be configured to include a requested area or timing of measurements in a request for forwarding measurements.

[0291] In examples, the target WTRU may determine to make a request to the network (e.g., LMF) to forward measurements and / or associated ground truths made or determined by other WTRUs or PRUs. In the request the WTRU may include one more of (e.g., any combination of) the following.

[0292] In examples, the target WTRU may indicate, in the request, a time interval or window (e.g., expressed in terms of absolute time, SFN) during which PRU / WTRU measurements should be made and / or ground truths for the PRU / WTRU should be determined. The time interval may be a future time interval, so training data is fresh when the target WTRU trains the Al ML model. For example, a time interval can be expressed as the start and end time of Jan. 2nd 4PM EST, 2025 and Jan. 3rd 4PM EST, 2025, respectively.

[0293] In examples, the target WTRU may request for measurements made during a specific time interval or window, where a window is expressed in terms of start and / or end time or duration. The time interval or start and / or end time of the window may be the past or future compared to the time the target WTRU sends a request or the time when the network receives the request from the target WTRU. In examples, the WTRU may send a request for the minimum periodicity of measurements made by other PRU or WTRU. The network may forward measurements with a shorter periodicity than the requested periodicity.

[0294] In examples, the target WTRU may indicate, in the request, a list of cells within which the PRU / WTRU measurements should be made and / or ground truths for the PRU / WTRU should be determined. For example, the WTRU may include a list of cell IDs and / or area IDs in the request. The WTRU may receive, from the network, a list of cell IDs or area IDs from which the WTRU can include the cell ID or area ID in the request.

[0295] An example of the signal exchange is illustrated in FIG. 10 at 1000. The target WTRU may send a request to the network (e.g., LMF). The request may include the desired time interval and area for the forwarded measurements and / or ground truth. The target WTRU may receive measurements and / or ground truth(s) made or determined by other WTRUs. Based on the received measurements and / ormeasurements available at the target WTRU, the target WTRU may train AIML model(s) at the target WTRU. Based on the determined or selected measurements and / or ground truth(s), the target WTRU may send a request for a validation condition by including information about the determined or selected measurements and / or ground truth(s) (e.g., effective measurement duration described herein, cell IDs). Based on the request, the target WTRU may receive time and / or area validity condition(s) from the network.

[0296] A WTRU may be configured to respond to a network request for information associated with AIML model (s) at the WTRU.

[0297] In examples, the WTRU may receive a request from the network to report information, identification information, and / or association information about the AIML model(s) (e.g., model association information) trained or to be trained at the WTRU. Examples of association information about the AIML model can be found below. Association information can include any combination of the examples below.

[0298] The association information may include parameter(s) in PRS configuration (e.g., PRS ID, cell ID, TRP ID, frequency information such as frequency layer ID, ARFCN, bandwidth, center frequency, subcarrier spacing, numerology, CP length).

[0299] The association information may include a group of parameters of DL RS (e.g., PRS) configurations (e.g., a set of PRS resource IDs, a set of TRPs, a set of PRS resource sets).

[0300] The association information may include parameter(s) in SRS or SRSp configuration (e.g., SRS sequence ID).

[0301] The association information may include a cell ID.

[0302] The association information may include an area, which may be defined by one or more cell IDs. Area may be associated with an ID, for example, an area ID.

[0303] The association information may include zone ID, where a zone may be an area within a cell.

[0304] The association information may include one or more than one parameters. For example, an AIML model may be associated with more than one TRPs or cell IDs, indicating that the AIML model can be used with the measurements made on the associated TRPs or cell IDs.

[0305] The association information may include an ID related to RS or signals (e.g., CSI-RS ID, DM-RS ID, SSB ID).

[0306] The association information may include input information and / or type thereof.

[0307] The association information may include output information and / or type thereof.

[0308] The association information may include a model ID.

[0309] The association information may include model version information.

[0310] The association information may include model format information and / or type thereof.

[0311] The association information may include AI / ML capability (e.g., AI / ML positioning, AI / ML beam management). AI / ML capabilities may be defined at finer granularities (e.g., AI / ML direct positioning, AI / ML assisted positioning, AI / ML spatial domain beam prediction, AI / ML temporal domain beam prediction, etc.).

[0312] The association information may include vendor information (e.g., vendor ID).

[0313] The association information may include applicable scenario and / or configuration information (e.g., frequency range, antenna configuration, site information, cell ID, etc. in which AI / ML model is applicable for inference, based for example on matching with the training scenario).

[0314] The association information may include computational complexity (e.g., FLOPS, level of pre- / post- processing that may be needed before deploying the model and / or before using the model for inference).

[0315] The association information may include complexity, for example, a number of real-value model parameters, a number of real-value operations for the model, a number and / or ID representing model complexity in terms of any of the aforementioned parameters.

[0316] The association information may include size, for example, fixed sizes associated to some models (e.g., <5 MB, < 50 MB, < 100 MB, etc.).

[0317] The association information may include a performance metric, e.g., accuracy, bias, variance and / or a number / ID associated with any thereof.

[0318] The association information may include functionality, sub-functionality, use case, and / or sub use case. In examples, the association information may indicate., what (sub) functionality and / or (sub) use cases are applicable for a specific model, e.g., CSI / BM / positioning.

[0319] The association information may include an indication of what types are applicable to a specific model. For example, the association information may include an indication that a model is a WTRU-sided model, WTRU-part of a two-sided model (e.g., encoder at WTRU, decoder at gNB for CSI compression use case).

[0320] The association information may include a model monitoring method.

[0321] In examples, the WTRU may receive a request to report associated information about the model(s) trained or to be trained at the WTRU. Based on the request, the WTRU may indicate to the network that an AIML model associated with cell#1 was trained with the measurements made by the WTRU and forwarded by the network. In examples, the WTRU may report, to the network, an ID associated with one or more PRS configurations (e.g., PRS resource IDs, TRP IDs) with which the WTRU made measurements and theWTRU may associate the PRS configuration ID to the model trained with the measurements made with the PRS configurations.

[0322] In examples, the WTRU may receive a request to report model ID(s) of model(s) trained or to be trained at the WTRU. Based on the request, the WTRU may determine to report the model ID. In examples, the WTRU may determine to associate the PRS configuration ID with the model ID and report the PRS configuration ID associated with the AIML model.

[0323] A WTRU may be configured to determine the AIML input based on forwarded measurements and / or ground truth(s).

[0324] In examples, the target WTRU may receive, from the network, forwarded measurements. The WTRU may determine the time interval of training data used to train the AIML model and / or a list of cells which training data is associated with. The WTRU may determine the measurements and / or ground truth(s) to use for training based on the examples of criteria described herein.

[0325] In examples, if the WTRU receives a request from the network, the WTRU may report a start and / or end time of duration associated with the training data to the network. In examples, the WTRU may report the area (e.g., a list of cell IDs) the training data is associated with.

[0326] In response to the WTRU report, the WTRU may receive time and / or area validity conditions from the network. Examples of the time and / or area validity conditions are described herein.

[0327] A WTRU may receive a request from the network to generate a location estimate based on the forwarded measurements.

[0328] In examples, a target WTRU may receive a request to send, to the network, details related to the AIML model at the target WTRU (e.g., number of inputs, type of inputs, number of neurons per layer, number of layers, validity conditions). Such a request from the network may be sent to the WTRU if the WTRU has an AIML model that can generate the WTRU location estimate based on measurements. In examples, the target WTRU may receive a request from the network to generate a location estimate using the AIML model at the WTRU, based on the forwarded measurements from the network.

[0329] If the target WTRU accepts the request (e.g., sends a message to the network accepting the request), the target WTRU may receive forwarded measurements, made by another WTRU, from the network. Based on the forwarded measurements, the target WTRU may determine the location estimate using the AIML model at the WTRU. The target WTRU may receive a configuration associated with the delivery of forwarded measurements. The configuration may include parameters such as a start and / or endtime of measurement forwarding, a duration of measurement forwarding, and / or a periodicity of measurement forwarding.

[0330] In examples, the WTRU may receive one or more than one set of forwarded measurements (e.g., one set of measurements may comprise PDPs, timing measurements made by the second WTRU) from the network. One set of measurements may be comprised in one instance of assistance information received by the network. For periodic delivery of forwarded measurements, the WTRU may collect more than one instance of measurements. For example, the WTRU may receive M instances of measurements forwarded by the network. For each instance, the WTRU may determine one location estimate.

[0331] The target WTRU may receive an indication from the network to generate more than one estimate (e.g., N estimates) of the WTRU location and report one or more (e.g., all) of N instances or average of N instances of location estimate. In examples, the target WTRU may indicate to the network whether the reported location estimate is based on one or more of (e.g., any combination of) the following.

[0332] In examples, the WTRU may indicate to the network that the determined location estimate is based on one instance of measurements. The WTRU may indicate the timestamp or configuration associated with the measurements.

[0333] In examples, the WTRU may indicate to the network that the determined location estimate is based on more than one instances of measurements. The WTRU may indicate the timestamps or configurations associated with (e.g., each instance of) the measurements.

[0334] In examples, the WTRU may indicate to the network that the determined location estimate is based on processed (e.g., averaged) measurements.

[0335] A WTRU may be configured to support performance reporting.

[0336] In examples, a WTRU may be configured to report the training performance during or at the end of training an AIML model. In examples, after training is complete, the WTRU may send an indication of the outcome of training (e.g., a performance metric or error metric) to the network. Examples of the performance metric or error metric of training and / or associated information can include one or more of (e.g., any combination of) the following: a Mean Absolute Error (MAE); a Mean Squared Error (MSE); a Root Mean Squared Error (RMSE); an X percentile (%) CDF Error, where X can be in the range of 0 to 100; a Variance or standard deviation of the error; and / or a Number of samples.

[0337] In examples, an error in the error metric may be defined as a difference between the inference generated by the AIML model and ground truth. For example, the MSE, a = cr, may be defined as a =- xt| where x and x are inference and the ground truth for the ithsample, respectively.

[0338] For training, MSE as the loss function may be used. Examples of other training metrics may include MSE, 2D-distance, MAE, and CDF (90%), e.g., probability that 90% of instances MSE performance is below a value, or CDF (80%) error values.

[0339] In examples, the WTRU may receive a configuration to report the error metric periodically at the configured periodicity. In examples, the WTRU may report the error metric at the end the training the AIML model. In examples, the WTRU may report the error metric in a semi-persistent manner (e.g., within a time window). For example, the WTRU may receive an indication from the network to initiate periodic reporting. The WTRU may terminate the periodic reporting if the WTRU receives an indication to terminate the periodic reporting. In examples, the WTRU may terminate periodic reporting once the timer associated with the periodic reporting expires. In examples, the WTRU may receive a configuration for a time window (e.g., indicated by the start time, end time, and / or duration) during which the WTRU is expected to report the error metric periodically.

[0340] In examples, the WTRU may receive an indication from the network to stop training the AIML model at the WTRU. The network may determine to send such an indication if the error metric reported by the WTRU reaches a satisfactory performance level. The WTRU may determine to stop training the AIML model if the provisioning of assistance information which contains forwarded measurements is terminated by the network.

[0341] In examples, the WTRU may include identification information of the model the error metric is associated with. For example, the WTRU may include a model ID or associated information (e.g., cell ID the model is associated with). Examples of identification information and associated information are described herein.

[0342] Exemplary embodiments are described herein.

[0343] The WTRU may send a request for PRU / WTRU measurement forwarding to the network (e.g., LMF). The request may include one or more of (e.g., any combination of) the following: a time interval, and / or a list of cells.

[0344] The time interval (e.g., expressed in terms of absolute time) may indicate a time during which PRU / WTRU measurements should be made and / or ground truths for the PRU / WTRU should be determined. The time interval may be a future time interval, so training data is fresh when the WTRU trains the AIML model.

[0345] The list of cells may indicate cells within which PRU / WTRU measurements should be made and / or ground truths for the PRU / WTRU should be determined.

[0346] The WTRU may receive WTRU / PRU measurements from the network (e.g., LMF).

[0347] The WTRU may report to the network (e.g., LMF) one or more of (e.g., any combination of) the following: a time interval of training data used to train the AIML model; and / or a list of cells to which training data is associated with.

[0348] In response for the report, the WTRU may receive time and / or area validation conditions from the network (e.g., LMF).

[0349] The WTRU may receive a configuration for AIML based positioning.

[0350] The WTRU may use the AIML model for positioning while one or more (e.g., all) validity conditions are satisfied.

[0351] If one of the validity conditions is not satisfied, the WTRU may send an indication to the network that AIML based positioning is terminated. This indication may include the cause of the stoppage.

[0352] Examples of exchanges between the network and a WTRU is illustrated in FIG. 11 at 1100. At 1102, the target WTRU may send a request for measurements made by other WTRUs and their and ground truth(s) made or determined (e.g., between Jan. 2nd2PM and 4PM EST from cell #1, #2 and #3). At 1104, the WTRU may receive one or more samples (e.g., measurement instances, a collection of measurements) from the network. In the example, the WTRU receives 5000 measurements made between Jan. 2nd 2PM and 4PM EST from cell #1. The WTRU also receives 3000 samples of measurements from the network which are made between Jan. 2nd 3PM and 4PM EST from cell #2. At 1106, the WTRU may report to the network that the WTRU used, for training an AIML model at the WTRU, one or more samples and / or associated ground truths. In the example shown, the WTRU reports that it used 3000 samples of measurements and associated ground truth(s) made or determined between Jan. 2nd 2PM and 3PM EST from cell #1, and 2000 samples of measurements and associated ground truth(s) made or determined between Jan. 2nd 3PM and 4PM EST from cell #1. At 1108, the WTRU may receive a validity condition from the network indicating that the trained AIML model at the WTRU is valid for an area and / or time. In the example, the WTRU receives a validity condition indicating that the trained AIML model is valid for cell #1 and the model is valid for 24 hours.

[0353] Using the methods described herein, the WTRU can determine validity conditions for the AIML model trained at the WTRU. Based on the determined validity condition reported by the WTRU, the network can determine an optimal positioning configuration for the WTRU, improving accuracy for positioning, providing stability in positioning operations and reducing latency for positioning.

Claims

CLAIMS:

1. A wireless transmit / receive unit (WTRU) comprising: a processor, wherein the processor is configured to: receive a configuration for artificial intelligence or machine learning (AIML) based positioning, wherein the configuration indicates an association rule for determining AIML model validity, wherein the association rule comprises a time validity condition of an AIML model or an area validity condition of the AIML model; measure a plurality of positioning reference signals (PRSs) in accordance with the configuration for AIML based positioning; determine a validity for the AIML model based on at least the association rule; and send a report indicating the validity of the AIML model.

2. The WTRU of claim 1 , wherein the processor is further configured to: train the AIML model based on at least the plurality of PRSs measured; receive an indication of a priority between the time validity condition and the area validity condition; and determine that the time validity condition should be determined before or after the area validity condition based on the priority.

3. The WTRU of claim 1 , wherein the processor is configured to send the report indicating the validity of the AIML model to a location management function (LMF).

4. The WTRU of claim 1 , wherein the processor is configured to receive an activation command associated with the AIML model.

5. The WTRU of claim 4, wherein the processor is configured to receive the activation command in a medium access control (MAC) control element (CE).

6. The WTRU of claim 4, wherein the activation command comprises a timestamp, wherein the timestamp indicates a time for activating the AIML model.

7. The WTRU of claim 1 , wherein the area validity condition is based on a determination that a number of WTRUs in an area associated with the plurality of PRSs is above a threshold number or a determination that a number of WTRUs per unit area in an area associated with the plurality of PRSs is above a threshold.

8. The WTRU of claim 1 , wherein the time validity condition comprises an indication of a time period during which the AIML model is valid.

9. The WTRU of claim 1 , wherein the processor is further configured to evaluate the area condition based on a cell identity associated with the WTRU.

10. The WTRU of claim 1 , wherein the processor is further configured to: evaluate the time validity condition based on an absolute time or a relative time.

11. A method to be performed by a wireless transmit / receive unit (WTRU), the method comprising: receiving a configuration for artificial intelligence or machine learning (AIML) based positioning, wherein the configuration indicates an association rule for determining AIML model validity, wherein the association rule comprises a time validity condition of an AIML model or an area validity condition of the AIML model; measuring a plurality of positioning reference signals (PRSs) in accordance with the configuration for AIML based positioning; determining a validity for the AIML model based on at least the association rule; and sending a report indicating the validity of the AIML model.

12. The method of claim 11 , further comprising: training an AIML model based on at least the plurality of PRSs measured; receiving an indication of a priority between the time validity condition and the area validity condition; and determining that the time validity condition should be determined before or after the area validity condition based on the priority.

13. The method of claim 11, further comprising: sending the report indicating the validity of the AIML model to a location management function (LMF).

14. The method of claim 11 , further comprising: receiving an activation command associated with the AIML model.

15. The method of claim 14, further comprising receiving the activation command in a medium access control (MAC) control element (CE).

16. The method of claim 14, wherein the activation command comprises a timestamp, wherein the timestamp indicates a time for activating the AIML model.

17. The method of claim 11, wherein the area validity condition is based on a determination that a number of WTRUs in an area associated with the plurality of PRSs is above a threshold number or a determination that a density of WTRUs per unit area in the area associated with the plurality of PRSs is above a threshold density.

18. The method of claim 11, wherein the time validity condition comprises an indication of a time period during which the AIML model is valid.

19. The method of claim 11, further comprising: evaluating the area condition based on a cell identity associated with the WTRU.

20. The method of claim 19, further comprising: evaluating the time validity condition based on an absolute time or a relative time.

Images