Joint compression of multiple channel state information prediction instances

Abstract

A WTRU may receive configuration information, for example from a network. The configuration information may be associated with a rate of change threshold associated with one or more channel state information (CSI) predictions. The WTRU may determine a plurality of CSI measurements, for example based on CSI reference signals (CSI-RSs). The WTRU may determine a plurality of CSI predictions, for example based on the plurality of CSI measurements. The WTRU may determine a rate of change associated with the plurality of CSI predictions. The WTRU may determine a CSI compression model based on the rate of change associated with the plurality of CSI predictions. The WTRU may generate jointly compressed CSI, for example using the CSI compression model and / or based on the plurality of CSI predictions. The WTRU may send an indication of the jointly compressed CSI, for example to the network.

Description

JOINT COMPRESSION OF MULTIPLE CHANNEL STATE INFORMATIONPREDICTION INSTANCESCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional Application No. 63 / 627,249 filed on January 31, 2024, the entire contents of which are incorporated herein by reference.BACKGROUND

[0002] Channel state information (CSI) prediction and CSI compression may utilize enablers for artificial intelligence (Al) / machine learning (ML)-based enhanced CSI measurement and reporting. CSI prediction may be performed by a wireless transmit / receive unit (WTRU), which may predict future CSI based on historical measured CSI.SUMMARY

[0003] A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on inclusion and / or omission of CSI predictions. The WTRU may receive CSI-reference signal (RS), measure the current channel state, predict multiple future CSI instances, determine a subset of CSI prediction instances based on the configurations and a criteria (e.g., the consecutive differences of prediction), determine an inclusion indicator, and / or report the inclusion indicator and / or a subset of multiple CSI predictions.

[0004] A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on CSI prediction and / or compression model selection. The WTRU may receive CSI-RS, measure the current channel state, predict multiple future CSI instances, determine the CSI compression model based on the configurations and criteria (e.g., based on the rate of change of predicted CSI), jointly compress all CSI predictions using the determined model, and / or report(e.g., jointly) compressed CSI predictions and / or model information.

[0005] A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on determining a CSI prediction subset. The WTRU may receive CSI-RS, measure the current channel state, predict multiple future CSI instances, determine a subset of the CSI prediction instances to use as input to a configured model, jointly compress the determined subset of CSI predictions using the configured model, and / or report (e.g., jointly)compressed CSI predictions and / or identifiers of CSI prediction instances used in the compression.

[0006] A WTRU may receive configuration information, for example from a network. The configuration information may be associated with one or more CSI predictions. The WTRU may determine one or more CSI predictions, for example based on the configuration information. The WTRU may determine whether to include the one or more CSI predictions in a subset of CSI predictions, for example to be reported. The WTRU may transmit one or more of an indication of the subset of CSI predictions and / or an inclusion indicator associated with one or more CSI predictions, for example to the network.

[0007] The WTRU may determine whether to include the one or more CSI predictions in the subset of CSI predictions based on a value associated with a difference between the one or more determined CSI predictions and one or more previous CSIs. The WTRU may compress one or more values of the subset of CSI predictions, for example to obtain compressed CSI predictions. The WTRU may determine whether to include the one or more CSI predictions in the subset of CSI predictions by determining a difference associated with consecutive compressed CSI predictions. The WTRU may determine whether to include the one or more CSI predictions in the subset of CSI predictions by determining to include and / or omit one or more CSI predictions from the subset of CSI predictions, for example based on a comparison of consecutive CSI predictions.

[0008] The one or more CSI predictions in the subset of CSI predictions may include a minimum value of CSI predictions to be included in the subset of CSI predictions. The WTRU may determine to update one or more of the indication of the subset of CSI predictions and / or the inclusion indicator, for example based on the minimum value of CSI predictions to be included in the subset of CSI predictions. The WTRU may transmit one or more of a first included CSI prediction and / or an indication of a difference of consecutive included CSI predictions, for example to the network. The WTRU may transmit the indication of the subset of CSI predictions and the inclusion indicator (e.g., to the network), for example by transmitting the indication of the subset of CSI predictions after the inclusion indicator.

[0009] A WTRU may receive configuration information, for example from a network. The configuration information may be associated with one or more CSI predictions. The WTRU may determine one or more CSI predictions, for example based on the configuration information. The WTRU may compress one or more values of the one or more CSI predictions, for example to obtain one or more compressed CSI predictions. The WTRU may transmit the one or more compressed CSI predictions, for example to the network.

[0010] The WTRU may determine one or more parameters associated with the one or more CSI predictions. The WTRU may determine a CSI compression model, for example based on the one or more parameters associated with the one or more CSI predictions. The WTRU may compress the one or more values of the one or more CSI predictions to obtain the one or more compressed CSI predictions by compressing the one or more values of the one or more CSI predictions, for example with the determined CSI compression model. The one or more parameters may include one or more of a rate of change between CSI predictions, an average squared generalized cosine similarity (SGCS) between CSI predictions, and / or a payload size.

[0011] The WTRU may transmit the determined one or more parameters associated with the one or more CSI predictions, for example to the network. The WTRU may determine a CSI compression model based on the one or more parameters after transmitting the determined one or more parameters associated with the one or more CSI predictions, for example to the network. The WTRU may determine a subset of the one or more CSI predictions for input to the determined model. The WTRU may transmit an indication of one or more indices associated with the subset of the one or more CSI predictions, for example to the network. The WTRU may transmit model information to the network.

[0012] A WTRU may receive configuration information, for example from a network. The configuration information may be associated with a rate of change threshold associated with one or more channel state information (CSI) predictions. The WTRU may determine a plurality of CSI measurements, for example based on CSI reference signals (CSI-RSs). The WTRU may determine a plurality of CSI predictions, for example based on the plurality of CSI measurements. The WTRU may determine a rate of change associated with the plurality of CSI predictions. The WTRU may determine a CSI compression model based on the rate of change associated with the plurality of CSI predictions. The WTRU may generate jointly compressed CSI, for example using the CSI compression model and / or based on the plurality of CSI predictions. The WTRU may send an indication of the jointly compressed CSI, for example to the network.

[0013] The WTRU may determine a payload size of the CSI compression model, for example based on the rate of change. The WTRU may determine the CSI compression model based on the payload size. The WTRU may send, for example to the network, one or more of a model identifier associated with the CSI compression model, a payload size associated with the CSI compression model, and / or one or more parameters associated to the plurality of CSI predictions.

[0014] The WTRU may determine an average squared generalized cosine similarity (SGSC), for example between consecutive CSI predictions of the plurality of CSI predictions. The CSI compression model may be determined based on the average SGSC between consecutive CSI predictions of the plurality of CSI predictions. The configuration information may include a threshold. The threshold may be associated with the rate of change. The WTRU may determine a subset of CSI predictions of the plurality of CSI predictions, for example based on the threshold. The subset of CSI predictions may include a first number and / or subset of CSI predictions if the rate of change associated with the plurality of CSI predictions is less than the threshold. The subset of CSI predictions may include a second number and / or subset of CSI predictions if the rate of change associated with the plurality of CSI predictions is greater than or equal to the threshold.

[0015] The configuration information may be associated with inclusion and / or omission of one or more CSI predictions. The configuration information may include an indication of a number of CSI predictions. The CSI compression model may be an artificial intelligence (Al)Zmachine learning (ML) model, for example determined based on the indication of the number of CSI predictions. The configuration information may include an indication of the AI / ML model. The AI / ML model may be used to generate the jointly compressed CSI.BRIEF DESCRIPTION OF THE DRAWINGS

[0016] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0017] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0018] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0019] FIG. 1 D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1A according to an embodiment.

[0020] FIG. 2 shows an example of codebook-based precoding with feedback information.

[0021] FIG. 3 shows an example AI / ML framework for CSI feedback with CSI compression.

[0022] FIG. 4 shows an example of multiple CSI prediction framework.

[0023] FIG. 5 shows an example of model selection based on the CSI predictions and / or joint compression.

[0024] FIG. 6 shows an example of joint compression of a determined subset of multiple predicted CSI instances.DETAILED DESCRIPTION

[0025] 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.

[0026] As shown in FIG. 1A, 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-Fi 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.

[0027] 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 Internet 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.

[0028] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in 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.

[0029] 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).

[0030] 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), whichmay 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).

[0031] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE- Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0032] 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).

[0033] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., a eNB and a gNB).

[0034] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e. , Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0035] 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 cellularbased 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 connectionto the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in 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.

[0042] 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.

[0043] 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.

[0044] 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).

[0045] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0046] 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 location-determination method while remaining consistent with an embodiment.

[0047] 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 138may 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.

[0048] 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)).

[0049] FIG. 1C is a system diagram illustrating the RAN 104 and the ON 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0050] 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.

[0051] 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.

[0052] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] Although the WTRU is described in FIGS. 1A-1D 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.

[0058] In representative embodiments, the other network 112 may be a WLAN.

[0059] 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 respectivedestinations. 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.

[0060] When using the 802.11ac 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 STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0061] 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.

[0062] 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).

[0063] 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 802.11af and 802.11 ah relative to those used in 802.11n, and 802.11ac. 802.11af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support 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).

[0064] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11 ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11ah, 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.

[0065] 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 802.11ah is 6 MHz to 26 MHz depending on the country code.

[0066] FIG. 1 D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0067] 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 withthe 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).

[0068] 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 wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0069] 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 gN Bs 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.

[0070] 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. 1 D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] In view of Figures 1A-1 D, and the corresponding description of Figures 1A-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.

[0077] 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 implemented / deployed as part of a wired and / or wireless communication network. The emulation device may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0078] 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 communicationnetwork. 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.

[0079] Systems and methods disclosed provide solutions for the efficient reporting of multiple channel state information (CSI) prediction instances, for example within a single report. CSI may be reported, for example by a WTRU. FIG. 2 shows an example of codebook-based precoding 200 with feedback information. A transmitter 202 may include a precoding matrix 204. Input signals (e.g., Xi, Xwt) may be input into the precoding matrix 204, which for example may include a weight W = Pi. Output signals (e.g., Zi, ZN from the precoding matrix 204 may be input into a MIMO channel 206. The MIMO channel 206 may output signals (e.g., y1 , yN1) based on the input signals and / or may transmit the output signals (e.g., yi , YNY) to a receiver 208. The receiver may include a machine learning (ML) algorithm and / or may perform a minimum mean square error (MMSE) process, for example on the output signals (e.g., y1 , yN1) from the MIMO channel 206. The receiver 208 may output signals (e.g., X;, Xwt) based on the output signals (e.g., y1 , yN1) from the MIMO channel 206. Additionally, or alternatively, the receiver 208 may output feedback, for example to the transmitter 202. The feedback information may include a precoding matrix index (PMI). The feedback information (e.g., PMI) may include a feedback codeword index.

[0080] A codebook may include a set of precoding vectors / matrices, for example for a (e.g., each) rank and number of antenna ports. A (e.g., each) precoding vector / matrix may include an index, for example such that a receiver may inform preferred precoding vector / matrix index to a transmitter. Codebook-based precoding may have performance degradation due to a finite number of precoding vector / matrix, for example as compared with non-codebook-based precoding. An advantage of a codebook-based precoding may include lower control signaling / feedback overhead.

[0081] There may be artificial intelligence (Al) / machine learning (ML) based CSI feedback. An autoencoder (AE) may be used, for example for CSI compression for AI / ML based CSI feedback. Systems and methods may include two sides, which for example may include an encoder and decoder. FIG. 3 shows an example AI / ML framework 300 for CSI feedback with CSI compression. Estimated CSI may be compressed at a WTRU 302 side. The WTRU side may include the encoder 304. The estimated CSI feedback 306 may be sent to a network (NW)308 side (e.g., a gNB). The network 308 side may include the decoder 310. The estimated CSI feedback 306 may (e.g., then) be decompressed, for example at the network 308 (e.g., gNB). An advantage of AI / ML based CSI compression may include improved performance, for example compared to legacy CSI feedback using a similar payload size. A disadvantage of AI / ML based CSI feedback may include a compression error that, for example may occasionally lead to a (e.g., significant) mismatch between a precoder computed at the WTRU 302 and a decompressed precoder at NW 308, X and X.

[0082] FIG. 4 shows an example of multiple CSI prediction framework 400. AI / ML based feedback may be used for CSI prediction. A WTRU may predict one or more instances of future CSI (e.g., channel matrices H(t + 1), ..., H(t + P)), for example by using the current and / or historical (e.g., previous) CSI measurements H(t — N), ..., H(t). CSI prediction may reduce CSI reporting overhead and / or reduce the number of downlink CSI-RS. The WTRU may perform CSI predictions.

[0083] Systems and methods may report multiple CSI prediction instances. A CSI prediction model may predict more than one future CSI depending on the trained model. A WTRU may report all predicted future CSI in a (e.g., single) report. Predicted CSI instances may show correlation, for example when a CSI prediction model predicts more than one future CSI. For example, predicted CSI instances may show correlation among consecutive predicted CSI instances. Systems and methods to leverage the correlation between consecutive CSI prediction instances may be defined to reduce the feedback overhead and / or increase reporting efficiency.

[0084] Systems and methods may include model selection and / or joint compression, for example of multiple predicted CSI instances. A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on CSI prediction and / or compression model selection. Additionally, or alternatively, the WTRU may receive CSI-RS, measure the current channel state, predict multiple future CSI instances, determine the CSI compression model, jointly compress (e.g., all) CSI predictions using the determined model, and / or report jointly compressed CSI predictions and / or model information. The WTRU may determine the CSI compression model based on the configurations and / or criteria. For example, determining the CSI compression model may be based on the rate of change of predicted CSI.

[0085] The WTRU (e.g., capable of CSI prediction) may be configured with one or more of CSI prediction for a certain window length (e.g., for a certain number of slots and / or a number of predictions), one or more thresholds for rate of change of CSI prediction, and / or one or more thresholds on average squared generalized cosine similarity (SGCS). The WTRU may receiveCSI-RS, determine CSI based on received CSI-RS, and / or predict one or more CSI, for example for the configured window. The WTRU may determine one or more parameters associated with the one or more predicted CSI. For example, the one or more parameters may include rate of change and / or average SGCS between consecutive CSI predictions. The WTRU may determine the rate of change of predicted CSI. The WTRU may compute the sum of the absolute differences between consecutive predicted CSI instances. The WTRU may determine the average of SGCS between consecutive CSI predictions.

[0086] The WTRU may determine the CSI compression model based on and / or as a function of one or more of a determined payload size of CSI compression model that takes (e.g., all) CSI predictions as input (e.g., WTRU may determine the compression model), a rate of change of predicted CSI, and / or a function of the average of SGCS between consecutive CSI predictions. The WTRU may determine payload size (e.g., the latent dimension) of CSI compression model that takes (e.g., all) CSI predictions as input (e.g., WTRU may determine the compression model). The WTRU may select a model based on the rate of change of predicted CSI. The WTRU may determine the payload size (e.g., the latent dimension) based on the rate of change (e.g., a lower rate of change may lead to lower overhead). The WTRU may be configured with multiple thresholds on the rate of change, for example to determine the model. The WTRU may select a model based on a function of the average of SGCS between consecutive CSI predictions. The WTRU may be configured with multiple thresholds on the average SGCS, for example to determine the model. The WTRU may report the determined one or more parameters associated with the one or more predicted CSI. The WTRU may (e.g., then) select an indicated CSI compression model, for example based on an indication from the NW.

[0087] The WTRU may activate the determined and / or indicated model for CSI compression. The determined CSI compression model may include an input size. The input size may be fixed (e.g., predetermined). The WTRU may use predicted (e.g., all predicted) CSI based on the configured window length as input. The WTRU may compress multiple predicted CSI jointly, for example using the determined model. The WTRU may report, for example to a network, the jointly compressed CSI predictions. Additionally, or alternatively, the WTRU may report one or more of model identifier, payload size, determined one or more parameters associated with the one or more predicted CSI, for example if the WTRU is configured to determine the model.

[0088] Systems and methods may include joint compression of a determined subset of multiple predicted CSI instances. A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) for determining a CSI prediction subset. Additionally, or alternatively, the WTRU may receive CSI-RS, measure the current channelstate, predict multiple future CSI instances, determine a subset of the CSI prediction instances to use as input to a configured model, jointly compress the determined subset of CSI predictions using the configured model, and / or report jointly compressed CSI predictions and / or identifiers of CSI prediction instances used in the compression.

[0089] The WTRU (e.g., capable of CSI prediction) may be configured with one or more of CSI prediction for a certain window length (e.g., for a certain number of slots), payload size and / or model ID, and / or one or more thresholds for rate of change of CSI prediction. The WTRU may receive CSI-RS, determine CSI based on received CSI-RS, and / or predict multiple CSI for the configured window.

[0090] The WTRU may determine a subset of multiple predicted CSI, for example to use as input to the model. The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model, for example based on one or more of the window length, a threshold rate of change, and / or model. For example, given a configured window length of 8, if the rate of change in CSI prediction instances is below the configured threshold and / or the configured model supports 4 inputs, then the WTRU may select 4 CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or use the down-selected CSI prediction instances as the input to model. In another example, if the rate of change in CSI prediction instances is above a threshold, then the WTRU may (e.g., only) report for a subset of the CSI prediction window. Additionally, or alternatively the WTRU may select 4 CSI prediction instances within the determined subset of CSI prediction window (e.g., 1st,2nd, 3rd, 4th), for example if the rate of change in CSI prediction instances is above a threshold. Additionally, or alternatively the WTRU may use the down- selected CSI prediction instances as the input to model, for example if the rate of change in CSI prediction instances is above a threshold.

[0091] The WTRU may determine the CSI prediction instances to be used as input to the model based on the estimated reconstruction quality at the NW. The WTRU may use a proxy decoder and / or proxy SGCS estimator to measure the estimated reconstruction quality. The WTRU may select the number and / or subset of CSI predictions instances that gives the highest reconstruction quality. The WTRU may report information on the indices of CSI prediction instances determined as input to the model and / or may jointly compressed CSI predictions.

[0092] CSI as herein may refer to any measurement and / or computation performed by the WTRU regarding a channel between WTRU and the NW. CSI may additionally, or alternatively, refer to one or more of channel matrix, representation of a channel matrix, and / or processed channel matrix. CSI prediction as herein may refer to the predicting future CSI, for example based on the historical measured CSI. Additionally, or alternatively, CSI prediction as hereinmay refer to using an analytical or AI / ML-based model. Multiple CSI prediction as herein may refer to a prediction model that is capable of prediction more than one future CSI predictions, for example using historical measured CSI. CSI prediction group as herein may refer to the multiple CSI predictions, for example obtained at the output of the CSI prediction model. CSI compression as herein may refer to the compression of CSI, for example using a compression model such as autoencoder based model.

[0093] Joint CSI compression as herein may refer to the compression of more than one CSI using a single model, for example simultaneously. Inclusion indicator as herein may refer to the indicator information reported from the WTRU, for example to the NW. The inclusion indicator may provide information on (e.g., which) CSI instances included in the report. The inclusion indicator may include one or more of the indices, slot numbers, time stamps, and / or etc. of the CSI predictions included in the report.

[0094] Systems and methods herein may address overhead in reporting of multiple CSI predictions. Systems and methods herein may reduce the uplink control channel overhead, for example by selective inclusion of multiple CSI predictions in a CSI prediction report. Systems and methods herein may include a CSI prediction module that, for example takes the historical measured CSI as input and / or may output multiple CSI prediction instances (e.g., as in FIG. 4). The number input CSIs and / or the number of predicted future CSIs may be configured by the NW. The WTRU may indicate the available configurations of the CSI prediction module, for example within a capability signaling message. Each configuration of the CSI prediction module may correspond to a different model trained for the given number of input and output.

[0095] A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on inclusion and / or omission of CSI predictions. The WTRU may receive CSI-RS, measure the current channel state, predict multiple future CSI instances, determine a subset of CSI prediction instances based on the configurations and a criteria (e.g., the consecutive differences of prediction), determine an inclusion indicator, and / or report the inclusion indicator and / or a subset of multiple CSI predictions. The WTRU (e.g., capable of CSI prediction) may be configured with one or more of (e.g., multiple) CSI predictions for a window length, CSI predictions for a number of slots, CSI predictions for a number of CSI reporting instances,, the number of historical CSI predictions to be used as input to the model, a model ID, one or more thresholds to determine the inclusion and omission of CSI predictions, a maximum number of consecutive omissions, a minimum number of inclusions, and / or the mode of operation of CSI prediction feedback. The WTRU may receive CSI-RS, determine CSI based on received CSI-RS, and / or predict multiple CSI (e.g., P) for the configured window.

[0096] The WTRU may determine omission and / or inclusion of reporting for CSI predictions, for example in one of the modes of operation (e.g., mode-a). The WTRU may determine a subset of CSI predictions, for example by computing the difference of predicted CSI with the previous predicted CSIs. The WTRU may omit the predicted CSI instance in the CSI report and / or indicate the omission (e.g., 0, in the inclusion indicator), for example if the difference is below a threshold. The WTRU may include the predicted CSI instance in the CSI report and / or indicate the inclusion (e.g., 1 , in the inclusion indicator), for example if the difference is above a threshold. The inclusion indicator may be 11011101 , where 1s indicate inclusion and 0s indicate omission, for example if the WTRU is configured to feedback 8 future CSI predictions. The WTRU may include (e.g., does not omit) the corresponding CSI prediction, for example if the number of consecutive omissions would become larger than (e.g., exceeds) a configured threshold.

[0097] The WTRU may compress one or more values for the included predicted CSI instances, (e.g., the determined subset of CSI predictions), for example in an example mode of operation (e.g., mode-b). The WTRU may compress each predicted CSI instance in the subset (e.g., using an autoencoder), for example if the WTRU is configured to compress the CSI predictions.

[0098] The WTRU may compress a (e.g., each) predicted CSI instance and / or (e.g., then) compute the difference of the consecutive compressed CSI instances to decide on inclusion, for example in another example mode of operation (e.g., mode-c). The WTRU may apply omission among CSI prediction groups. For example an inclusion indicator of 01110011, may mean the first CSI prediction instance is omitted. The WTRU may omit the first CSI prediction instance due to a similarity to the last CSI prediction of the previous group.

[0099] The WTRU may (e.g., further) update the inclusion indicator and / or the subset of CSI predictions, for example based on the configured minimum number of inclusions. The WTRU may feedback the inclusion flag and / or the (e.g., determined) subset of predicted CSI instances. The WTRU may report the first included CSI prediction and / or the differences of consecutive included CSI predictions. The WTRU may report predicted multiple CSI in two phases. For example in a first phase, the WTRU may report the inclusion indicator and / or (e.g., then) receive an uplink grant to report the CSI predictions. For example, the uplink grant may indicate resources to report the CSI predictions. In a second phase for example, the WTRU may report the included multiple CSI predictions (e.g., the determined subset of CSI predictions).

[0100] Systems and methods may include model selection and / or joint compression of multiple predicted CSI instances. A WTRU may be configured for model selection and / or joint compression. A WTRU may be configured for AI / ML based CSI prediction and compression. AWTRU may support one or more one-sided AI / ML model for CSI prediction and / or multiple two- sided AI / ML models for CSI compression. The WTRU may be pre-configured and / or may be (e.g., explicitly) configured with CSI prediction parameters. The WTRU may be configured with CSI prediction for a specific window length (e.g., for a certain number of slots), and / or a set of thresholds used for rate of change of CSI prediction. The WTRU may additionally, or alternatively, be configured with thresholds on average SGCS performance of the CSI prediction AI / ML model, for example for performing model selection of CSI compression.

[0101] The WTRU may be configured with multiple rates of change of the predicted CSI. For example the multiple rates of change may include different ranges. The WTRU may use the different ranges to determine a lookup table. A (e.g., each) range and / or interval may be mapped to an (e.g., specific) AI / ML model, for example for CSI compression. The WTRU may perform model selection of the most appropriate AI / ML model for CSI compression for performance optimization, for example based on one or more thresholds of rate of change. An (e.g., each) interval of pre-configured thresholds of rate of change may be associated with a subset of the supported AI / ML models for CSI compression. The WTRU may additionally, or alternatively, select one AI / ML model, for example based on the average SGCS performance.

[0102] The WTRU may compute the sum of the absolute differences between consecutive predicted CSI instances, for example for the determination of the rate of change. The WTRU may compute the correlation between different predicted CSI instances. A correlation close to 1 may indicate that the rate of change is small. A small correlation (e.g., close to 0) may indicate a large rate of change.

[0103] The WTRU may be configured with multiple thresholds on average SGCS performance of CSI prediction. The WTRU may use the thresholds for maintaining SGCS, for example within a specific performance requirement. The WTRU may use the average SGCS performance between consecutive predicted CSI instances. The WTRU may average the SGCS performance over a certain window with a specific size (e.g., over a specific number of consecutive predicted CSI instances). The WTRU may receive the configuration from a NW dynamically via DCI, for example after CSI compression model download / activation and / or fine-tuning. The WTRU may receive the configuration via MAC control element (CE) and / or radio resource control (RRC).

[0104] A WTRU may determine the model for the compression of multiple predicted CSI instances. The WTRU may generate one or more CSI predicted samples. The WTRU may be configured to determine one or more parameters associated with CSI feedback operation, for example including joint compression of multiple predicted CSI.

[0105] The WTRU may be configured to generate multiple predicted CSI based on a preconfigured prediction window and / or the number of predicted samples. The prediction window may indicate the maximum prediction time in the future (e.g., measured in seconds). The number of predicted samples may indicate the number of CSI samples, which may be equally-spaced for example, to predict within the configured prediction window. The WTRU may be configured with the number of predicted samples and / or the time interval(s) between each pair of predicted sample. As herein, the term sequence of predicted CSI samples may be used interchangeably with predicted CSI sequence and / or predicted CSI samples, for example to indicate the prediction of multiple CSI samples in the future.

[0106] A WTRU may determine and / or select a compression model, for example based on payload size. The WTRU may be configured to jointly compress the predicted CSI sequence and / or may report the compressed CSI as part of the CSI feedback report, for example as in FIG. 5. FIG. 5 shows an example of model selection 500 based on the CSI predictions and / or joint compression. The WTRU may predict CSI at 502. At 504 the WTRU may determine the AI / ML compression model needed to compress the predicted CSI sequence, for example based on a rate of change of predicted CSI. At 506 the WTRU may compress the CSI predictions using an encoder-based compression model, for example an autoencoder-based compression model.

[0107] As herein, the terms AI / ML compression model, AI / ML model, and / or autoencoder (AE) model may be used interchangeably, for example to indicate the AI / ML model used to compress the predicted CSI sequence. The WTRU may determine the compression model based on the needed payload size, for example one or more latent dimension. Each AI / ML model may include a specific bottleneck dimension. For example, the WTRU may determine the latent dimension based on the long-term correlation measured between the first and last predicted CSI sample in the predicted CSI sequence. Ht+1,... , Ht+Nmay denote the sequence of P predicted CSI samples at time instant t. The long-term correlation, 0<pL< 1, between the first and last predicted CSI sample may be expressed as:where htmay represent the vectorized version of the channel matrix / tensor Ht. The WTRU may determine the latent dimension based on a predefined mapping between the long-term correlation and the latent dimension. For example, higher long-term correlation may imply a lower latent dimension. Lower long-term correlation may imply a higher latent dimension. The WTRU may determine the AI / ML model based on the number of predicted CSI samples P.

[0108] A WTRU may determine and / or select a compression model based on one or more measurements. The one or more measurements may include a rate of change of predicted CSI and / or an average SGCS between consecutive CSI. The WTRU may be configured to select and / or determine the compression model based on one or more of a rate of change of predicted CSI (RoCP) and / or an average SGCS between consecutive CSI predictions. RoCP may indicate how the predicted channels are varying across time. For example, given a sequence of P predicted CSI samples Ht+1,... , Ht+P, the rate of change of predicted CSI may compute (e.g., may be used to compute) the sum of differences between every pair of consecutive predicted CSI samples normalized by the number of pairs. For example, this may be mathematically expressed as:where ||. || denotes the Frobenius norm.

[0109] The WTRU may determine the compression model as a function of the RoCP. For example, the WTRU may compare the measured RoCP with one or more configured threshold(s). Each threshold may map to a (e.g., particular) AI / ML model. Lower RoCP may imply an AI / ML model with smaller bottleneck, for example since predicted samples are closer / correlated to each other while higher RoCP requires a model with higher bottleneck for efficient compression.

[0110] The WTRU may determine and / or select a compression model based on the average SGCS between consecutive CSI predictions. The average SGCS between consecutive CSI predictions may indicate the level of correlation between every pair of consecutive CSI samples normalized by the number of pairs. For example:where h indicates the vectorized channel sample.

[0111] The average SGCS may be measured in the eigenvector domain, for example wherein the principal eigenvector of the channels is used (e.g., instead of the full CSI). The WTRU may select the compression model by comparing the measured average SGCS with one or more configured thresholds. AI / ML models with large latent size may be associated with lower SGCSthreshold(s). AI / ML models with small latent size may be associated with higher SGCS threshold(s).

[0112] A WTRU may determine and / or select a compression model based on one or more channel conditions. The WTRU may be configured to determine and / or select the AI / ML model based on one or more channel conditions. The one or more channel conditions may include one or more of Doppler frequency, WTRU speed, and / or channel coherence time. For example, the WTRU may select the model based on a predefined mapping between the AI / ML compression models and / or one or more WTRU speed threshold. Mapping may be between the AI / ML model and channel coherence time.

[0113] Systems and methods may include reporting of a selected model and / or compressed multiple predicted CSI instances. A WTRU may report the determined parameters used for CSI compression model selection, for example including one or more of the rate of change and / or the average SCGS calculated from different predicted CSI instances. The WTRU may additionally, or alternatively, report the model identifiers / IDs associated with one or more selected models. The WTRU may report a set of model identifiers, for example along with one or more determined payload sizes. The WTRU may report (e.g., parameters), for example the set of model identifiers, as assistance information to the NW for performing CSI compression model selection. The WTRU may report the compressed multiple CSI predictions, which for example may be compressed based on the determined compression model. The compressed CSI prediction report may include a jointly compressed representation of all CSI predictions.

[0114] The WTRU may send a report via UCI over PUCCH and / or PUSCH, for example. The channel may be selected based on the report payload. The WTRU may select a channel based on a configuration, for example received from NW. A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) on CSI prediction and / or compression model selection. The WTRU may receive CSI-RS, measure the current channel state, predict multiple future CSI instances, determine the CSI compression model based on the configurations and criteria (e.g., based on the rate of change of predicted CSI), jointly compress (e.g., all) CSI predictions using the determined model, and / or report (e.g., jointly) compressed CSI predictions and / or model information.

[0115] The WTRU (e.g., capable of CSI prediction) may be configured with one or more of CSI prediction for a certain window length (e.g., for a certain number of slots, number of predictions), one or more thresholds for rate of change of CSI prediction, and / or one or more thresholds on average SGCS. The WTRU may receive CSI-RS, determine CSI based on received CSI-RS, and / or predict one or more CSI for the configured window. The WTRU may determine one ormore parameters (e.g., rate of change or average SGCS between consecutive CSI predictions) associated with the one or more predicted CSI. For example, the WTRU may determine the rate of change of predicted CSI. The WTRU may compute the sum of the absolute differences between consecutive predicted CSI instances. The WTRU may determine the average of SGCS between consecutive CSI predictions.

[0116] The WTRU may determine the CSI compression model based on and / or as a function of a payload size and / or one or more parameters associated with one or more predicted CSI. The WTRU may determine the payload size (e.g., the latent dimension), for example of a CSI compression model that takes (e.g., all) CSI predictions as input (e.g., WTRU to determine the compression model). The WTRU may select a model based on the rate of change of predicted CSI. The WTRU may determine the payload size (e.g., the latent dimension) based on the rate of change. A lower rate of change may lead to a lower overhead. The WTRU may be configured with multiple thresholds on the rate of change to determine the model. The WTRU may select a model based on (e.g., a function of) the average of SGCS between consecutive CSI predictions. The WTRU may be configured with multiple thresholds on the average SGCS to determine the model. The WTRU may report the determined one or more parameters associated with the one or more predicted CSI. The WTRU may (e.g., then) select an indicated CSI compression model, for example based on an indication from the NW.

[0117] The WTRU may activate the determined and / or indicated model for CSI compression. The determined CSI compression model may include a fixed input size (e.g., all predicted CSI based on the configured window length are used as inputs together). The WTRU may compress multiple predicted CSI, for example jointly, using the determined model. The WTRU may report the jointly compressed CSI predictions. The WTRU may additionally, or alternatively, report one or more of a model identifier, a payload size, and / or the determined one or more parameters associated with the one or more predicted CSI.

[0118] Systems and methods may include joint compression of a determine subset of multiple predicted CSI instances. A WTRU may be configured for subset determination. The WTRU (e.g., capable of CSI prediction / estimation / compression) may be configured with one or more of CSI prediction for a certain window length (e.g., for a certain number of slots), the payload size (or the model ID), and / or one or more thresholds for rate of change of CSI prediction. For example, the WTRU may be configured with CSI estimation, prediction, and / or compression for a window (e.g., certain number of slots and / or certain time period measured in milliseconds). The WTRU may be configured with one or more payload size(s) (e.g., the latent dimension) of the input to the CSI compression model. The WTRU may be configured with (e.g., a few)options for payload sizes for different input to the AI / ML model. For example, each payload size option may be associated with one AI / ML model (e.g., that the WTRU may have been preconfigured with and / or may have downloaded from the gNB).

[0119] The WTRU may be preconfigured with one or more AI / ML models for CSI estimation / prediction / compression. The WTRU may additionally, or alternatively, receive AI / ML models (e.g., from the network) and / or update its list of models accordingly. For example, a (e g., each) AI / ML model (e.g., preconfigured and / or downloaded from the network) may be associated with one or more of a (e.g., different) window length, payload size, and / or threshold for rate of change of CSI prediction. The WTRU may receive (e.g., from the network) one or more model ID(s) associated with one or more AI / ML models at the WTRU for CSI estimation / prediction / compression. The WTRU may receive the model with its associated model ID and / or (e.g., any) additional configuration from the network (e.g., associated window length, thresholds etc.), for example if the model has been downloaded from the network. The WTRU may send the model ID(s) associated with the AI / ML models (e.g., model IDs that may have been allocated by the model vendor and / or WTRU vendor), for example if the WTRU may have been preconfigured with the one or more AI / ML models. The WTRU may send the model ID(s) to the network.

[0120] The WTRU may receive one or more thresholds Tj, , for example for the rate of change of CSI prediction. The threshold may impact WTRU behavior, for example if the threshold is exceeded. For example if a rate of change of CSI prediction < Ti, the WTRU may (e.g., only) report on a subset of predicted CSI instances. A threshold may alternatively, or additionally, correspond to one or more CSI measurement values (e.g., if CQI < corresponding preconfigured threshold Tj). The WTRU may report on (e.g., all) the predicted CSI instances, for example instead of a subset thereof.

[0121] The WTRU may receive one or more thresholds from the network. The one or more thresholds may correspond to channel quality measurement metrics (e.g., thresholds corresponding to CQI) and / or radio channel conditions (e.g., thresholds corresponding to RSRP, L1-RSRP, SNR, SI NR, and / or etc.) which, for example if exceeded / crossed may impact the WTRU behavior. For example, a WTRU may determine to use all CSI prediction instances as input to the model versus a subset thereof and the size / number of entries in the subset thereof. The WTRU may receive (e.g., from the network) configuration information as herein and / or related assistance information, for example via dedicated signaling (e.g., RRC signaling, MAC CE, DCI) and / or broadcast in system information.

[0122] A WTRU may determine a subset of multiple predicted CSI instances and / or may compress the subset. The WTRU may receive CSI-RS, determine CSI based on received CSI- RS, and / or predict multiple CSI, for example for a configured window. The WTRU may determine a subset of multiple predicted CSI to use as input to the model, for example as depicted in FIG. 6. FIG. 6 shows an example of joint compression 600 of a determined subset of multiple predicted CSI instances. The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model, for example based on one or more of the window length, one or more thresholds on rate of change, and a model. The WTRU may predict CSI at 602. At 604 the WTRU may determine inputs, for example based on a rate of change (e.g., of predicted CSI) and / or estimated SGCS. At 606 the WTRU may down-select one or more CSI predictions. At 608 the WTRU may compress the CSI predictions using an encoderbased compression model, for example a fixed encoder compression model.

[0123] For example, given a configured window length of 8, if the rate of change in CSI prediction instances is below the configured threshold and / or the configured model supports 4 inputs, the WTRU may select 4 CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or use the down-selected CSI prediction instances as input to model. In another example, if the rate of change in CSI prediction instances is above a threshold, (e.g., then) the WTRU may (e.g., only) report for a subset of the CSI prediction window and / or select 4 CSI prediction instances within the determined subset of CSI prediction window (e.g., 1st,2nd, 3rd, 4th) and / or use the down- selected CSI prediction instances as the input to model. The WTRU may determine the CSI prediction instances to be used as input to the model based on the estimated reconstruction quality, for example at the NW. The WTRU may use a proxy decoder and / or proxy SGCS estimator to measure the estimated reconstruction quality. The WTRU may select the number and / or subset of CSI predictions instances that gives the highest reconstruction quality.

[0124] The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model based on the channel quality measurements (e.g., CQI, PMI, and / or Rl). For example if the measured CQI is better than a preconfigured threshold, (e.g., then) the WTRU may select (e.g., a few) CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or use the down-selected CSI prediction instances as the input to model. The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model based on the change in channel quality measurements (e.g., CQI, PMI, and / or Rl differential between consecutive measurements). For example if there is a sudden drop in CQI, the WTRU may use (e.g., start using) the predicted CSI instances (e.g., all predicted CSI instances) as input to the model. For example if there is an increase in CQI between two consecutive measurements, theWTRU may determine to select (e.g., a few) CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or use the down-selected CSI prediction instances as the input to model. There may be additional or alternative granularities. For example if CQI further increases, the WTRU may determine to further down select (e.g., a few) CSI prediction instances (e.g., 1st, 5th) in the following prediction window as input to the model.

[0125] The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model based on the radio conditions (e.g., L1 and / or L3 RSRP, interference, channel coherence time, channel coherence bandwidth, and / or etc.). For example if the measured RSRP is above a preconfigured threshold, the WTRU may select (e.g., a few) CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or use the down-selected CSI prediction instances as the input to model. If for example the radio conditions are poor (e.g., at cell edge) and / or during handover with reference to the source cell for example, the WTRU may not down select and / or may (e.g., instead) use (e.g., all) the CSI prediction instances.

[0126] The WTRU may send an indication to the network for example following determination of the subset of predicted CSI instances to use as input to the model. The indication may indicate indices of CSI prediction instances determined as input to the model. The network may use the indication to achieve encoder-decoder synchronization. The indication may be sent in one or more of RRC, MAC CE, and / or UCI. The indication may include a bitmap, for example to indicate selected instances. The WTRU may send the indication (e.g., a bitmap) periodically to the NW. The WTRU may send the indication (e.g., bitmap) on request from the network. The WTRU may send the indication (e.g., bitmap) initially and / or (e.g., only) send an (e.g., another) indication if there is a change in the determination.

[0127] The network may determine (e.g., assume that) the configuration remains unchanged, for example until the WTRU sends an updated bitmap. The WTRU may send, an indication of (e.g., information on) the duration of time when the WTRU expects to keep input the same subset of CSI instances to the model, for example alongside the bitmap. The information on the duration of time may include one or more of a length of time, a number of slots, a number of occurrences of the prediction window, and / or etc.

[0128] The WTRU may send (e.g., to the network) information for multiple windows. The information may be for future windows. The CSI instances input to the model may vary from one window to another. The WTRU may determine to input a higher number of CSI instances to the model than during normal operation, for example if the WTRU is undergoing handover. For example, the WTRU may be moving through an area of sparse coverage (e.g., cell edge) for thenext two time windows during which, for example the WTRU may input all the CSI instances into the model.

[0129] The WTRU may down select a smaller subset of CSI instances to input into the model, for example once the coverage conditions improve (e.g., in the third window). The WTRU may receive (e.g., from the network) an indication to increase the number of CSI instances input to the model (e.g., either input all the CSI instances or input a larger subset), for example if the model performance and / or output is poor (e.g., below a threshold and / or criteria). The WTRU may receive one or more indications from the network. The one or more indications may include information associated with how and / or when to determine the subset of CSI instances to use as input to the model. The network may determine the subset of CSI instances and / or the determination may be indicated to the WTRU.

[0130] Systems and methods may include reporting of information on the determined subset and / or the compressed subset. A WTRU may be configured with a window for which, for example the WTRU may provide measurement reports (e.g., CSI measurement reports). The measurement reports may be determined based on predicted measurement values. The WTRU may be configured and / or may determine a set of time instances P (e.g., within the configured window) for which, for example the WTRU may determine expected and / or predicted measurement values. The WTRU may report a compressed measurement report that. The compressed measurement report may provide information related to the measurement values applicable to the set of time instances P and / or a subset of P.

[0131] A WTRU may use a subset of the P predicted measurement values (e.g., subset of size M, where M<P) to determine and / or generate a compressed measurement report, for example as described herein. The subset of M measurement values may be compressed and / or may provide information related to (e.g., all) P predicted measurement values. The subset M of measurement values may be compressed and / or may provide information related to a subset of the P time instances (e.g., subset of size P’, where P’<P). For example when the rate of change of CSI, determined from the P predicted measurement values, is less than threshold, the compressed measurement report (e.g., obtained from M measurement values) may provide information (e.g., predicted measurement values) related to the P time instances. In another example when the rate of change of CSI, determined from the P predicted measurement values, is greater than a threshold, the compressed measurement report (e.g., obtained from M measurement values) may provide information (e.g., predicted measurement values) related to P’ time instances.

[0132] The WTRU may determine and / or may be configured with one or more of values of M and / or P’, an identity of the M predicted measurement values, and / or an identity of the P’ time instances. The determination of the identity of the M predicted measurement values may be based on a metric obtained from one or more of the predicted P measurement values. The determination of the identity of the P’ time instances may be based on a metric obtained from one or more of the predicted P measurement values and / or on the identity of the M predicted measurement values.

[0133] The WTRU may send (e.g., feedback) a compressed measurement report, for example to the gNB. The WTRU may additionally, or alternatively, provide feedback information based on one or more of a value of M, selected / configured M predicted measurement values, a value of P’, selected / determined / configured P’ time instances, a metric type used to determine any of M or P’ and / or subset of predicted measurement values comprising M and / or subset of time instances comprising P’, and / or a metric value used to determine any of M or P’. The WTRU may provide the feedback information along with the compressed measurement report. The WTRU may feedback the compressed measurement report and / or may additionally, or alternatively, feedback one or more of a value M, an identity of M predicted measurements, a Value P’, an identity of P’ instances, a metric used to determine value of M or P’, a value of the metric used to determine the value of M or P’ and / or subset of predicted measurement values comprising M or subset of time instances comprising P’, a request to change the value of P and / or M and / or P’, a request to change the subset of M measurement values used to generate the compressed report and / or the subset of P’ time instances for which the compressed report provides information, and / or a request to transmit a second measurement report associated with the window.

[0134] The WTRU may send a value M. For example, the WTRU may indicate the number of predicted measurement values used to generate the compressed measurement report. The WTRU may send an identity of M predicted measurements. The WTRU may indicate the identity of one or more of the M predicted measurements, for example used to generate the compressed measurement report. Additionally, or alternatively, the WTRU may indicate the identity of one or more of the P-M predicted measurements not used to generate the compressed measurement report. The WTRU may send a value P’. For example, the WTRU may indicate the number of time instances for which the compressed measurement report provides information (e.g., predicted measurement values). The WTRU may send an identity of P’ time instances. For example, the WTRU may indicate the identity of the P’ time instances for which the compressed measurement report provides information (e.g., predicted measurementvalues). The WTRU may indicate the identity of the P-P’ time instances for which the compressed measurement report does not provide information (e.g., predicted measurement values) .

[0135] The WTRU may send a metric, for example used to determine a value of M or P’ and / or a subset of predicted measurement values comprising M and / or subset of time instances comprising P’. For example, the WTRU may indicate the metric used to determine either subset (e g., subset of measurement values to generate the compressed report and / or subset of time instances for which the report provides information). The metric may include one or more of the rate of measurement change, SGCS, prediction reliability, maximum and / or minimum measurement value, difference between max and min measurement value, and / or compression rate.

[0136] The metric may be based on a set of predicted measurements within the current window and / or for a previous window. The WTRU may send a value of the metric used to determine the value of M or P’ and / or subset of predicted measurement values comprising M or subset of time instances comprising P’. The WTRU may send a request to change the value of P and / or M and / or P’. The WTRU may determine that a compressed measurement report may (e.g., only) be valid for a set of time instances P’, for example where P’<P. The WTRU may request a change of P for subsequent compressed measurement reports. The values of M and / or P’ may be configured by the gNB. The WTRU may request a change in the values of M and / or P’ (e.g., an increase or a decrease in values).

[0137] The WTRU may send a request to change the subset of M measurement values used to generate the compressed report and / or the subset of P’ time instances for which the compressed report provides information. The WTRU may send a request to transmit a second measurement report associated with the window. For example, the second measurement report may provide information related to at least one of the P-P’ time instances, for example for which a first measurement report does not provide information. For example, a first measurement report may provide information for the first P’ time instances of the window. The WTRU may request resources to transmit a second measurement report to provide information for the last P-P’ time instances of the window.

[0138] A WTRU may monitor for and / or receive an indication to transmit a measurement report (e.g., a compressed measurement report), for example generated using a specific set of M measurement values. The WTRU may monitor for and / or receive an indication to transmit a measurement report (e.g., a compressed measurement report) applicable to a (e.g., specific)set of time instances. A WTRU may monitor for and / or receive an indication to transmit a measurement report (e.g., a compressed measurement report).

[0139] The measurement report may be applicable to one or more of a subsequent window, a previous window, and / or an ongoing / current window. For example, the WTRU may receive an indication to transmit a measurement report applicable to a specific set of time instances of a window for which the WTRU has previously transmitted a feedback report, and / or of a window for which the WTRU has not yet transmitted a feedback report. The received indication may (e.g., explicitly) indicate the set of time instances for which the report is applicable. The received indication may (e.g., implicitly) indicate the set of time instances for which the report is applicable (e.g., for all time instances for which a previous report was not applicable).

[0140] A WTRU (e.g., capable of CSI prediction) may receive configuration information (e.g., one or more configurations) for determining a CSI prediction subset. The WTRU may receive CSI-RS. The WTRU may measure the current channel state. The WTRU may predict multiple future CSI instances. The WTRU may determine a subset of the CSI prediction instances to use as input to a configured model. The WTRU may jointly compress the determined subset of CSI predictions, for example using the configured model. The WTRU may report (e.g., jointly) compressed CSI predictions and / or identifiers of CSI prediction instances used in the compression. The WTRU (e.g., capable of CSI prediction) may be configured with one or more of CSI prediction for a certain window length (e.g., for a certain number of slots), the payload size (or the model ID), and / or one or more thresholds for rate of change of CSI prediction.

[0141] The WTRU may receive CSI-RS, determine CSI based on received CSI-RS, and / or predict multiple CSI for the configured window. The WTRU may determine a subset of multiple predicted CSI, for example to use as input to the model. The WTRU may determine the number and / or subset of predicted CSI instances to use as input to the model, for example based on one or more of the window length, one or more thresholds on rate of change, and / or a model. For example given a configured window length of 8, if the rate of change in CSI prediction instances is below the configured threshold and / or the configured model supports 4 inputs, (e.g., then) the WTRU may select 4 CSI prediction instances (e.g., 1st, 3rd, 5th,7th) and / or may use the down-selected CSI prediction instances as the input to model. In another example if the rate of change in CSI prediction instances is above a threshold, (e.g., then) the WTRU may (e.g., only) report for a subset of the CSI prediction window and / or select 4 CSI prediction instances within the determined subset of CSI prediction window (e.g., 1st,2nd, 3rd, 4th) and / or use the down-selected CSI prediction instances as the input to model.

[0142] The WTRU may determine the CSI prediction instances to be used as input to the model based on the estimated reconstruction quality at the NW. The WTRU may use a proxy decoder and / or proxy SGCS estimator to measure the estimated reconstruction quality. The WTRU may select the number and / or subset of CSI predictions instances, for example that results in (e.g., gives) the highest reconstruction quality. The WTRU may report information on the indices of CSI prediction instances determined as input to the model and / or (e.g., jointly) compressed CSI predictions.

Claims

CLAIMS:

1. A method implemented by a wireless transmit / receive unit (WTRU), the method comprising: receiving configuration information from a network, the configuration information associated with a rate of change threshold associated with one or more channel state information (CSI) predictions; determining a plurality of CSI measurements based on CSI reference signals (CSI-RSs); determining a plurality of CSI predictions based on the plurality of CSI measurements; determining a rate of change associated with the plurality of CSI predictions; determining a CSI compression model based on the rate of change associated with the plurality of CSI predictions; generating jointly compressed CSI using the CSI compression model and based on the plurality of CSI predictions; and sending, to the network an indication of jointly compressed CSI.

2. The method of claim 1 , further comprising: determining a payload size of the CSI compression model based on the rate of change; and determining the CSI compression model based on the payload size.

3. The method of claim 1 , further comprising: sending, to the network, one or more of a model identifier associated with the CSI compression model, a payload size associated with the CSI compression model, or one or more parameters associated to the plurality of CSI predictions.

4. The method of claim 1 , further comprising determining an average squared generalized cosine similarity (SGSC) between consecutive CSI predictions of the plurality of CSI predictions.

5. The method of claim 4, wherein the CSI compression model is determined based on the average SGSC between consecutive CSI predictions of the plurality of CSI predictions.

6. The method of claim 1 , wherein the configuration information further comprises a threshold associated with the rate of change associated with the plurality of CSI predictions, and wherein the method further comprises determining a subset of CSI predictions of the plurality of CSI predictions based on the threshold.

7. The method of claim 6, wherein the subset of CSI predictions comprises a first number of CSI predictions if the rate of change associated with the plurality of CSI predictions is less than the threshold, and wherein the subset of CSI predictions comprises a second number of CSI predictions if the rate of change associated with the plurality of CSI predictions is greater than or equal to the threshold.

8. The method of claim 1 , wherein the configuration information comprises an indication of a number of CSI predictions.

9. The method of claim 8, wherein the CSI compression model is an artificial intelligence (Al) / machine learning (ML) model determined based on the indication of the number of CSI predictions, wherein the AI / ML model is used generate the jointly compressed CSI.

10. The method of claim 1, wherein the configuration information further comprises an indication of an (Al) / machine learning (ML) model, wherein the CSI compression model comprises the AI / ML model, and wherein the AI / ML model is used to generate the jointly compressed CSI.

11. A wireless transmit / receive unit (WTRU) comprising: a processor, the processor configured to: receive configuration information from a network, the configuration information associated with a rate of change threshold associated with one or more channel state information (CSI) predictions; determine a plurality of CSI measurements based on CSI reference signals (CSI- RSs); determine a plurality of CSI predictions based on the plurality of CSI measurements; determine a rate of change associated with the plurality of CSI predictions;determine a CSI compression model based on the rate of change associated with the plurality of CSI predictions; generate jointly compressed CSI using the CSI compression model and based on the plurality of CSI predictions; and send, to the network an indication of jointly compressed CSI.

12. The WTRU of claim 11 , wherein the processor is further configured to: determine a payload size of the CSI compression model based on the rate of change; and determine the CSI compression model based on the payload size.

13. The WTRU of claim 11 , wherein the processor is further configured to: send, to the network, one or more of a model identifier associated with the CSI compression model, a payload size associated with the CSI compression model, or one or more parameters associated to the plurality of CSI predictions.

14. The WTRU of claim 11 , wherein the processor is further configured to determine an average squared generalized cosine similarity (SGSC) between consecutive CSI predictions of the plurality of CSI predictions.

15. The WTRU of claim 14, wherein the CSI compression model is determined based on the average SGSC between consecutive CSI predictions of the plurality of CSI predictions.

16. The WTRU of claim 11 , wherein the configuration information further comprises a threshold associated with the rate of change associated with the plurality of CSI predictions, and wherein the processor is further configured to determine a subset of CSI predictions of the plurality of CSI predictions based on the threshold.

17. The WTRU of claim 16, wherein the subset of CSI predictions comprises a first number of CSI predictions if the rate of change associated with the plurality of CSI predictions is less than the threshold, and wherein the subset of CSI predictions comprises a second number of CSI predictions if the rate of change associated with the plurality of CSI predictions is greater than or equal to the threshold.

18. The WTRU of claim 11 , wherein the configuration information comprises an indication of a number of CSI predictions.

19. The WTRU of claim 18, wherein the CSI compression model is an artificial intelligence (Al) / machine learning (ML) model determined based on the indication of the number of CSI predictions, wherein the AI / ML model is used to generate the jointly compressed CSI.

20. The WTRU of claim 11 , wherein the configuration information further comprises an indication of an (Al) / machine learning (ML) model, wherein the CSI compression model comprises the AI / ML model, and wherein the AI / ML model is used to generate the jointly compressed CSI.

Images