Method and apparatus for reducing CSI feedback overhead using compression

Abstract

The present disclosure relates to a method and apparatus for reporting channel state information (CSI) feedback in a wireless telecommunications network. In one example, a method implemented in a wireless transmit / receive unit (WTRU) may include receiving configuration information indicating a channel rank threshold, determining a channel rank associated with a channel measurement value, selecting a type of CSI compression based on the channel rank and the channel rank threshold, and transmitting information indicating the CSI and the selected CSI compression type, the CSI associated with the channel measurement value and compressed using the selected CSI compression type.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 392,734, filed with the U.S. Patent and Trademark Office on July 27, 2022, the entire contents of which are incorporated herein by reference as if fully set forth below in their entirety, and for all applicable purposes.

[0002] FIELD OF THE INVENTION FIELD OF THE DISCLOSURE The present disclosure relates generally to wireless and / or wireline communication networks. For example, one or more embodiments disclosed herein relate to methods and apparatus for channel state information (CSI) reporting in wireless telecommunications networks. Summary of the Invention

[0003] One or more embodiments disclosed herein relate to a method and apparatus for CSI feedback overhead reduction using eigenvector compression for wireless communications. For example, a wireless transmit / receive unit (WTRU) capable of full-channel CSI compression and eigenvector-based CSI compression may select a CSI compression type. The WTRU measures a channel and determines a rank. If the determined rank is less than a configured channel rank threshold, the WTRU selects EV-based compression, which may reduce CSI feedback overhead.

[0004] In one embodiment, a method implemented by a WTRU for wireless communication includes receiving, from a network entity, configuration information indicating a channel rank threshold and determining a channel rank associated with a channel measurement. The method further includes selecting a type of CSI compression based on the determined channel rank and the channel rank threshold and transmitting, to the network entity, CSI and information indicating the selected CSI compression type, the CSI associated with the channel measurement and compressed using the selected CSI compression type. In some cases, the configuration information includes an indication for enabling selection of a type of CSI compression from a set of CSI compression types, the set of CSI compression types including full-channel-based compression and eigenvector (EV)-based compression.

[0005] In one embodiment, a WTRU for wireless communication, comprising circuitry including a transmitter, a receiver, a processor, and a memory, is configured to receive, from a network entity, configuration information indicating a channel rank threshold, determine a channel rank associated with a channel measurement, select a type of channel state information (CSI) compression based on the determined channel rank and the channel rank threshold, and transmit, to the network entity, the CSI and information indicating the selected CSI compression type, the CSI associated with the channel measurement and compressed using the selected CSI compression type. In some cases, the configuration information includes instructions for enabling selection of a CSI compression type from a set of CSI compression types, the set of CSI compression types including full-channel-based compression and eigenvector (EV)-based compression. [Brief explanation of the drawings]

[0006] A more detailed understanding can be had from the following detailed description, given by way of example in conjunction with the drawings that accompany this specification. The figures in such drawings, like the detailed description, are illustrative. Therefore, the figures and detailed description should not be considered limiting, as other equally effective embodiments are possible and likely to be so. Moreover, like reference numerals ("ref") within the figures ("FIG") indicate like elements. [Figure 1A] 1 is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented. [Figure 1B] 1B is a system diagram illustrating an exemplary wireless transmit / receive unit (WTRU) that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1C] 1B is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communication system shown in FIG. 1A, in accordance with one or more embodiments. [Figure 1D] 1B is a system diagram illustrating a further exemplary RAN and a further exemplary CN that may be used within the communication system shown in FIG. 1A, according to one or more embodiments. [Figure 2] A diagram showing an example of configuration for CSI reporting settings, resource settings, and links. [Figure 3] FIG. 1 illustrates codebook-based precoding with feedback information. [Figure 4] FIG. 1 is a block diagram illustrating a zero-padding technique in accordance with one or more embodiments. [Figure 5] FIG. 10 illustrates an autoencoder input for zero padding for rank-1 and rank-2 transmissions, in accordance with one or more embodiments. [Figure 6] 1 is a flow diagram illustrating a method for selecting between eigenvector compression and full channel compression in accordance with one or more embodiments. [Figure 7] FIG. 1 illustrates an exemplary network configuration for MU-MIMO. [Figure 8] 1 is a flow diagram illustrating a process for selecting between eigenvector compression and full channel compression for MU-MIMO in accordance with one or more embodiments. [Figure 9] FIG. 1 is a block diagram illustrating bursting-based compression in accordance with one or more embodiments. [Figure 10] FIG. 1 illustrates an eigenvector bursting technique in accordance with one or more embodiments. [Figure 11] 1 is a flow diagram illustrating a process for selecting between bursting eigenvector-based compression and bursting full-channel-based compression in accordance with one or more embodiments. [Figure 12] 1 is a flow diagram illustrating a process for selecting between bursting eigenvector-based compression and bursting full-channel-based compression for MU-MIMO compression, in accordance with one or more embodiments. [Figure 13] FIG. 1 is a block diagram illustrating a process for post-processing of CSI feedback in the latent domain, in accordance with one or more embodiments. [Figure 14] FIG. 2 is a block diagram illustrating a process for adaptive quantization post-processing of CSI feedback in accordance with one or more embodiments. [Figure 15] FIG. 1 is a block diagram illustrating an example of a CSI feedback procedure using CSI compression type selection and indication, in accordance with one or more embodiments. [Figure 16] 10 is a flowchart illustrating an example of a CSI feedback procedure using a selected CSI compression type, in accordance with one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0007] Introduction In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments and / or examples disclosed herein. It will be understood, however, that such embodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to obscure the following description. Furthermore, embodiments and examples not specifically described herein may be practiced in place of, or in combination with, embodiments and other examples explicitly, implicitly, and / or inherently described, disclosed, or otherwise provided herein (collectively "provided").

[0008] Although various embodiments are described and / or claimed herein in which apparatus, systems, devices, etc. and / or any elements thereof perform operations, processes, algorithms, functions, etc. and / or any portions thereof, it should be understood that any embodiment described and / or claimed herein assumes that any apparatus, system, device, etc. and / or any elements thereof are configured to perform any operation, process, algorithm, function, etc. and / or any portion thereof.

[0009] Examples of communication systems The methods, apparatus, and systems provided herein are well suited for communications involving both wired and wireless networks. Wired networks are well known. An overview of various types of wireless devices and infrastructure is provided with respect to Figures 1A-1D, and various elements of the networks may utilize, perform, be arranged, and / or be adapted and / or configured in accordance with the methods, apparatus, and systems provided herein.

[0010] 1A is a diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. Communication system 100 may be a multiple-access system that provides content, such as voice, data, video, messaging, broadcasts, etc., to multiple wireless users. Communication system 100 may enable multiple wireless users to access such content through sharing of system resources, including wireless bandwidth. For example, the communication system 100 may 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), etc.

[0011] 1A, communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RANs 104 / 113, CNs 106 / 115, public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, although it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a "station" and / or "STA," may be configured to transmit and / or receive wireless signals and may include user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a mobile phone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (loT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, a medical device and application (e.g., for remote surgery), an industrial device and application (e.g., a robot and / or other wireless device operating in an industrial and / or automated processing chain context), a consumer electronics device, a device operating on a commercial wireless network and / or an industrial wireless network, etc. Any of the WTRUs 102a, 102b, 102c, and 102d may be referred to interchangeably as a UE.

[0012] The communications system 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communications networks, such as the CN 106 / 115, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node B, an eNodeB, a Home Node B, a Home eNodeB, a gNB, an NR Node B, a site controller, an access point (AP), a wireless router, etc. Although the base stations 114a, 114b are each depicted as a single element, it will be understood that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0013] 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 base station 114b may be configured to transmit and / or receive radio signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide wireless service coverage for a particular geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In one embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers per sector of the cell, for example, using beamforming to transmit and / or receive signals in desired spatial directions.

[0014] 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).

[0015] More specifically, as noted above, the communications system 100 may be a multiple-access system, but may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base stations 114a of the RANs 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communications protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and / or High-Speed Uplink Packet Access (HSUPA).

[0016] In one 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-Advanced, LTE-A) and / or LTE-Advanced Pro (LTE-Advanced Pro, LTE-A Pro).

[0017] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR radio access, which may establish the air interface 116 using New Radio (NR).

[0018] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may jointly implement LTE radio access and NR radio access, e.g., using dual connectivity (DC) principles. Thus, the air interface utilized by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to and from multiple types of base stations (e.g., eNBs and gNBs).

[0019] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement a wireless technology such as IEEE 802.11 (i.e., Wireless Fidelity, WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access, WiMAX), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), or the like.

[0020] 1A may be, for example, a wireless router, a Home NodeB, a Home eNodeB, or an access point and may utilize any suitable RAT to facilitate wireless connectivity in a local area such as a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, etc. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may establish a picocell or a femtocell using a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.). As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not need to access the Internet 110 through the CN 106 / 115.

[0021] The RAN 104 / 113 may communicate with the CN 106 / 115, which may be any type of network configured to provide voice, data, application, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have various quality of service (QoS) requirements, such as different throughput, latency, error tolerance, reliability, data throughput, mobility, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions such as user authentication. Although not shown in FIG. 1A , it will be understood that the RAN 104 / 113 and / or the CN 106 / 115 may communicate directly or indirectly with other RANs employing 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 utilize NR radio technology, the CN 106 / 115 may also communicate with another RAN (not shown) employing GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0022] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network providing plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices, which use common communication protocols such as the transmission control protocol (TCP), the user datagram protocol (UDP), and / or the internet protocol (IP) of the TCP / IP Internet protocol suite. The network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the network 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 113 or a different RAT.

[0023] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links.) For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with a base station 114a, which may employ a cellular-based wireless technology, and a base station 114b, which may employ an IEEE 802.2 wireless technology.

[0024] 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, the WTRU 102 may include, among other things, a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138. It will be understood that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0025] The processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0026] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In one embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR signals, UV signals, 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 signals and light signals. It will be understood that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0027] 1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0028] The transceiver 120 may be configured to modulate signals transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers to enable the WTRU 102 to communicate via multiple RATs, such as, for example, NR and IEEE 802.11.

[0029] The processor 118 of the WTRU 102 may be coupled to and may receive user-entered data from a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. Additionally, the processor 118 may access information from and store data in any type of suitable memory, such as non-removable memory 130 and / or removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, etc. In other embodiments, the processor 118 may access information from and store data in memory that is not physically located on the WTRU 102, such as on a server or home computer (not shown).

[0030] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to other components in the WTRU 102. The power source 134 may be any suitable device for providing power to the WTRU 102. For example, the power source 134 may include one or more dry batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0031] The processor 118 may also be coupled to a GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or instead of, information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0032] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, etc. The peripheral device 138 may include one or more sensors, which may be one or more of a gyroscope, an accelerometer, a Hall effect sensor, a magnetometer, a direction sensor, a proximity sensor, a temperature sensor, a time sensor, a geolocation sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0033] The WTRU 102 may include a full-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with a particular subframe for both the uplink (e.g., for transmission) and downlink (e.g., for reception)) may be parallel and / or simultaneous. The full-duplex radio may include an interference management unit 139 to reduce and or substantially eliminate self-interference either through hardware (e.g., chokes) or signal processing via a processor (e.g., via a separate processor (not shown) or processor 118). In one embodiment, the WTRU 102 may include a half-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with a particular subframe for either the uplink (e.g., for transmission) or downlink (e.g., for reception)) may be parallel and / or simultaneous.

[0034] 1C is a system diagram illustrating the RAN 104 and the CN 106, according to one embodiment. As noted above, the RAN 104 may employ E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0035] The RAN 104 may include eNodeBs 160a, 160b, and 160c, although it will be understood that the RAN 104 may include any number of eNodeBs while remaining consistent with an embodiment. The eNodeBs 160a, 160b, and 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In an embodiment, the eNodeBs 160a, 160b, and 160c may implement MIMO technology. Thus, the eNodeB 160a may, for example, use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0036] Each of the eNodeBs 160a, 160b, 160c may be associated with a particular cell (not shown) and configured to handle radio resource management decisions, handover decisions, scheduling of users in the uplink (UL) and / or downlink (DL), etc. As shown in FIG. 1C, the eNodeBs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0037] 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. Although each of the foregoing elements is depicted as part of the CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0038] The MME 162 may be connected to each of the eNodeBs 162a, 162b, 162c in the RAN 104 via an S1 interface and may function as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, activating / deactivating bearers, selecting a particular serving gateway during initial attach of the WTRUs 102a, 102b, 102c, etc. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies such as GSM and / or WCDMA.

[0039] The SGW 164 may be connected to each of the eNodeBs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to and from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during inter-eNodeB handovers, triggering paging when DL data is available to the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0040] The SGW 164 may be connected to a PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0041] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional landline communications devices. For example, the CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. Additionally, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0042] Although the WTRU is illustrated in FIGS. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments, such a terminal may use a wired communication interface (e.g., temporarily or permanently) with the communication network.

[0043] In a representative embodiment, the other network 112 may be a WLAN.

[0044] A WLAN in infrastructure Basic Service Set (BSS) mode may have an access point (AP) of the BSS and one or more stations (STAs) associated with the AP. The AP may have access to or interface with a Distribution System (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating from outside the BSS to a STA may arrive through the AP and be delivered to the STA. Traffic originating from a STA to a destination outside the BSS may be sent to the AP to be delivered to the respective destination. Traffic between STAs within a BSS may be sent, for example, through the AP, where the source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent between (e.g., directly between) a source STA and a destination STA using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (e.g., all of the STAs) may communicate directly with each other. The IBSS mode of communication may be referred to herein as an "ad hoc" communication mode.

[0045] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, an AP may transmit beacons on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., a 20 MHz wide bandwidth) or a width that is dynamically set via signaling. The primary channel may be the operating channel of the BSS, but may also be used by STAs to establish a connection with the AP. In certain representative embodiments, for example, in an 802.11 system, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented. With CSMA / CA, STAs (e.g., all STAs), including the AP, may sense the primary channel. If a particular STA senses / detects and / or determines that the primary channel is busy, the particular STA may back off. One STA (e.g., only one station) may transmit in a given BSS at any given time.

[0046] High Throughput (HT) STAs may use 40 MHz wide channels for communication, which may be formed, for example, through a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels.

[0047] A Very High Throughput (VHT) STA may support channels with widths of 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz. A 40 MHz and / or 80 MHz channel may be formed by combining multiple contiguous 20 MHz channels. A 160 MHz channel may be formed by combining eight contiguous 20 MHz channels or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, after channel encoding, the data may pass through a segment parser that may separate the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time-domain processing may be performed separately on each stream. The streams may be mapped to two 80 MHz channels, and the data may be transmitted by the transmitting STA. At the receiver of the receiving STA, the operations described above for the 80+80 configuration may be reversed, and the combined data may be sent to Medium Access Control (MAC).

[0048] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah compared to those used in 802.11n and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, while 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to representative embodiments, 802.11ah may support meter-type control / machine-type communications, such as MTC devices, within a macro coverage area. MTC devices may have limited capabilities, including, for example, support for (e.g., only support for) certain specific and / or limited bandwidths. MTC devices may include batteries with above-threshold battery life (e.g., to maintain very long battery life).

[0049] WLAN systems that can support multiple channels and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel that can be designated as a primary channel. The primary channel can have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be configured and / or limited by the STAs among all STAs operating in the BSS that support the minimum bandwidth operating mode. In an 802.11ah embodiment, the primary channel can be 1 MHz wide for STAs (e.g., MTC-type devices) that support (e.g., only) the 1 MHz mode, even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) configuration can depend on the status of the primary channel. For example, if the primary channel is busy due to a STA (that only supports 1 MHz operating mode) transmitting to the AP, the entire available frequency band may be considered busy, even though most of the frequency band may remain idle and be available for use.

[0050] In the United States, the available frequency band that can be used by 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz depending on the country code.

[0051] 1D is a system diagram illustrating the RAN 113 and the CN 115, according to one embodiment. As noted above, the RAN 113 may use NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also communicate with the CN 115.

[0052] The RAN 113 may include gNBs 180a, 180b, and 180c, although it will be understood that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, and 180c may implement MIMO technology. For example, the gNBs 180a and 180b may utilize beamforming to transmit and / or receive signals to and / or from the gNBs 180a, 180b, and 180c. Thus, the gNB 180a may transmit and / or receive wireless signals to and / or from the WTRU 102a, for example, using multiple antennas. In one embodiment, the gNBs 180a, 180b, and 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 one embodiment, the gNBs 180a, 180b, and 180c may implement Coordinated Multi-Point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNBs 180a and 180b (and / or 180c).

[0053] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of different or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0054] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without accessing another RAN (e.g., eNodeBs 160a, 160b, 160c, etc.). In a standalone configuration, the WTRUs 102a, 102b, 102c may utilize one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in unlicensed bands. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate with and connect to gNBs 180a, 180b, 180c while also communicating with and connecting to another RAN, such as eNodeBs 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNodeBs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNodeBs 160a, 160b, 160c may act as mobility anchors for the WTRUs 102a, 102b, 102c, and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0055] 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 uplink (UL) and / or downlink (DL), support for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, etc. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with each other via an Xn interface.

[0056] 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 is depicted as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0057] 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 function as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, supporting network slicing (e.g., handling different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. Network slicing may be used by the AMF 182a, 182b to customize the CN support of the WTRUs 102a, 102b, 102c based on the type of service utilizing the 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, etc. The AMFa 82a, 182b 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.

[0058] The SMFs 183a and 183b may be connected to the AMFs 182a and 182b in the CN 115 via an N11 interface. The SMFs 183a and 183b may also be connected to the UPFs 184a and 184b in the CN 115 via an N4 interface. The SMFs 183a and 183b may select and control the UPFs 184a and 184b and configure the routing of traffic through the UPFs 184a and 184b. The SMFs 183a and 183b may perform other functions such as managing and assigning UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0059] The UPFs 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 UPFs 184, 184b may perform other functions such as routing and forwarding packets, enforcing user plane policy, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, etc.

[0060] The CN 115 may facilitate communication with other networks. For example, the CN 115 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts 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 other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b through the UPFs 184a, 184b via an N3 interface to the UPFs 184a, 184b and an N6 interface between the UPFs 184a, 184b and the DNs 185a, 185b.

[0061] 1A-1D and the corresponding description thereof, one or more or all of the functions described herein with respect to one or more of the WTRUs 102a-d, base stations 114a-b, eNodeBs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other devices described herein may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more or all of the functions described herein. For example, the emulation devices may be used to test other devices and / or simulate network and / or WTRU functions.

[0062] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or an operator network environment. For example, one or more emulation devices may perform one or more or all functions while fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices in the communication network. One or more emulation devices may perform one or more or all functions while temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation devices may be directly coupled to another device for testing purposes and / or may perform testing using terrestrial wireless communication.

[0063] One or more emulation devices may perform one or more functions, inclusive, while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in test scenarios in a test lab and / or in an undeployed (e.g., test) wired and / or wireless communication network to implement testing of one or more components. One or more emulation devices may be test equipment. Direct RF coupling and / or wireless communication via RF circuitry (which may include, e.g., one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0064] Channel State Information (CSI) Reporting Channel state information (CSI), which may include at least one of a channel quality index (CQI), a rank indicator (RI), a precoding matrix index (PMI), an L1 channel measurement (e.g., a reference signal received power (RSRP) such as L1-RSRP, or SINR), a CSI-reference signal (CSI-RS) resource indicator (CRI), an SS / PBCH block resource indicator (SSBRI), a tier indicator (LI), and / or any other measurement quantity measured by the WTRU from a configured reference signal (e.g., a CSI-RS or SS / PBCH block or any other reference signal).

[0065] CSI Reporting Framework The WTRU may be configured to report CSI through an uplink control channel on the physical uplink control channel (PUCCH) or per gNB request on an uplink (UL) PUSCH grant. Depending on the configuration, the CSI-RS can cover the entire bandwidth of the bandwidth portion (BWP) or just a portion of it. Within the CSI-RS bandwidth, the CSI-RS can be configured in each physical resource block (PRB) or every other PRB. In the time domain, the CSI-RS resources can be configured either periodic, semi-persistent, or aperiodic. Semi-persistent CSI-RS is similar to periodic CSI-RS, except that the resources can be (de)activated by the MAC CE, and the WTRU reports the associated measurements only when the resources are activated. In the case of aperiodic CSI-RS, the WTRU is triggered to report the measured CSI-RS on the PUSCH by a request in the downlink control information (DCI). Periodic reports are carried on the PUCCH, while semi-persistent reports can be carried on either the PUCCH or the Physical Uplink Shared Channel (PUSCH).

[0066] The reported CSI may be used by the scheduler when allocating optimal resource blocks, possibly based on the time-frequency selectivity of the channel, when determining precoding matrices, when determining beams, when determining transmission modes, and when selecting a preferred modulation and coding scheme (MCS). The reliability, accuracy, and timeliness of WTRU CSI reporting may be important to meet Ultra-Reliable Low-Latency Communications (URLLC) service requirements.

[0067] The WTRU may be configured with a CSI measurement configuration, which may include one or more CSI reporting configurations, resource configurations, and / or links between one or more CSI reporting configurations and one or more resource configurations. Figure 2 shows example configurations for CSI reporting configurations, resource configurations, and links.

[0068] In the CSI measurement configuration, one or more of the following configuration parameters may be provided: N≧1 CSI reporting configuration, M≧1 resource configuration, and / or a CSI measurement configuration linking the N CSI reporting configurations with the M resource configurations.

[0069] A CSI reporting configuration that includes at least one of the following: Time domain behavior: e.g., aperiodic, periodic, or semi-persistent; Frequency granularity for at least the precoding matrix indicator (PMI) and the channel quality indicator (CQI); CSI report type (e.g., PMI, CQI, Rank Indicator (RI), CSI Resource Indicator (CRI), etc.), and / or If PMI is reported, the PMI type (Type I or II) and codebook configuration.

[0070] A resource configuration that contains at least one of the following: Time domain behavior: aperiodic, periodic, or semi-persistent, RS type (e.g., for channel measurements or interference measurements), and / or Each resource set is K sS≧1 resource sets, each of which may contain resources.

[0071] A CSI measurement configuration including at least one of the following: 1) one CSI reporting configuration, 2) one resource configuration, and / or 3) in the case of CQI, a reference transmission scheme configuration.

[0072] For CSI reporting for component carriers, one or more of the following frequency granularities may be supported: wideband CSI, partial-band CSI, and / or sub-band CSI.

[0073] Codebook-based Precoding Figure 3 shows the basic concept of codebook-based precoding with feedback information, which may include PMI, which may be referred to as a codeword index in a codebook as shown in Figure 3.

[0074] As shown in Figure 3, the codebook includes a set of precoding vectors / matrices for each rank and the number of antenna ports, and each precoding vector / matrix has its own index so that the receiver can inform the transmitter of a preferred precoding vector / matrix index. Codebook-based precoding may have performance degradation compared to non-codebook-based precoding due to its finite number of precoding vectors / matrices. On the other hand, the main advantage of codebook-based precoding is its smaller control signaling / feedback overhead.

[0075] Table 1 shows an example of a codebook for 2Tx.

[0076] [Table 1]

[0077] CSI Processing Standards The CSI processing unit (CPU) may be referred to as the minimum CSI processing unit, and a WTRU may support one or more CPUs (e.g., N CPUs). A WTRU with N CPUs may estimate N CSI feedback calculations in parallel, where N may be the capability of the WTRU. If the WTRU is requested to estimate more than N CSI feedbacks simultaneously, the WTRU may only perform the N highest priority CSI feedbacks and the rest may not be estimated.

[0078] The start and end of the CPU may be determined based on the CSI reporting type (e.g., aperiodic, periodic, semi-persistent) as follows:

[0079] For example, in the case of aperiodic CSI reporting, the CPU starts to be occupied from the first orthogonal frequency division multiplexing (OFDM) symbol after the physical downlink control channel (PDCCH) trigger and remains occupied until the last OFDM symbol of the PUSCH carrying the CSI report.

[0080] In another example, for periodic and semi-persistent CSI reporting, the CPU is occupied starting from the first OFDM symbol of one or more associated measurement resources (not earlier than the CSI reference resource) and continuing until the last OFDM symbol of the CSI report.

[0081] The number of CPUs occupied may vary based on the CSI measurement type (e.g., beam-based or non-beam-based), for example, as follows: Non-beam related reports ●K in the CSI-RS resource set for channel measurements s If there are K CSI-RS resources, s CPUs ● Beam-related reports (e.g., "cri-RSRP", "ssb-Index-RSRP", or "none") One CPU, regardless of the number of CSI-RS resources in the CSI-RS resource set for channel measurements "none" is used for P3 beam management operations or non-periodic Tracking Reference Signal (TRS) transmissions In the case of aperiodic CSI reporting using a single CSI-RS resource, one CPU is occupied. ●K of CSI report s For CSI-RS resources, the WTRU needs to perform CSI measurements for each CSI-RS resource, so s CPUs will be occupied.

[0082] Number of free CPUs (N u ) is the number of CPUs required for CSI reporting (N r ), the following WTRU behavior may be implemented: For example, the WTRU may drop Nr-Nu CSI reporting instances based on priority for uplink control information (UCI) on the PUSCH without data / HARQ (hybrid automatic repeat request). In another example, the WTRU may report dummy information in Nr-Nu CSI reporting instances based on priority to avoid rate-matching processing for the PUSCH.

[0083] Artificial intelligence (AI) Artificial intelligence can be broadly defined as behavior exhibited by machines that can, for example, sense, reason, adapt, and act in ways that mimic cognitive functions.

[0084] Machine Learning (ML) General principles of ML Machine learning may refer to algorithms that solve problems based on learning through experience (“data”) without being explicitly programmed (“constructing a set of rules”). Machine learning may be considered a subset of artificial intelligence (AI). Various machine learning paradigms may be envisioned based on the nature of the data or feedback available to the learning algorithm. For example, supervised learning techniques may involve learning a function that maps inputs to outputs based on labeled training examples, where each training example may be a pair consisting of an input and a corresponding output. Meanwhile, unsupervised learning techniques may involve detecting patterns in data that do not have existing labels. In yet another example, reinforcement learning techniques may involve performing a sequence of actions in an environment to maximize a cumulative reward.

[0085] In some solutions, machine learning algorithms can be applied using a combination or interpolation of any of the above-mentioned techniques. For example, semi-supervised learning techniques can use a combination of a small amount of labeled data and a large amount of unlabeled data during training. In this regard, semi-supervised learning is positioned between unsupervised learning (no labeled training data) and supervised learning (only labeled training data).

[0086] Deep Learning (DL) Deep learning refers to a class of machine learning algorithms that employ artificial neural networks (specifically, deep neural networks) loosely inspired by biological systems. DNNs are a special class of machine learning models inspired by the human brain, in which inputs are linearly transformed and passed multiple times through nonlinear activation functions. DNNs typically contain multiple layers, each containing a linear transformation and a given nonlinear activation function. DNNs can be trained using training data via a backpropagation algorithm. Recently, DNNs have shown state-of-the-art performance in various domains, such as speech, vision, and natural language, and for various machine learning settings, including supervised, unsupervised, and semi-supervised.

[0087] AI / ML-based methods / processes may refer to achieving behavior and / or adapting to requirements through data-driven learning without explicit configuration of a sequence of action steps. Such methods may enable learning complex behaviors that may be difficult to specify and / or implement using traditional methods.

[0088] CSI overhead For downlink scheduling and link adaptation purposes for both single-user (SU)-MIMO and multi-user (MU)-MIMO, accurate knowledge of the channel is required. This is achieved by using DL CSI reference signals (CSI-RS) to enable channel estimation at the WTRU and feeding back estimated CSI (e.g., implicit CSI: CQI, PMI, RI, LI) in the WTRU CSI report. However, because NR supports a large number of antenna ports, there is significant overhead associated with CSI feedback reporting. The overhead is particularly large for CSI Type II codebooks (e.g., Rel-15 CSI Type II, Rel-16 / 17 Type II / eType II CSI codebooks).

[0089] This overhead is expected to increase further as system bandwidth and the number of antennas increase in B5G massive MIMO systems.

[0090] In some examples, AI / ML-based compression reduces CSI feedback overhead. However, typical approaches compress the full channel matrix. Further overhead reduction can be achieved by compressing the eigenvectors instead.

[0091] For AI / ML-based eigenvector compression, new or improved methods may be desirable to support scenarios where the channel rank is greater than 1. Additionally, for eigenvector-based compression, new or improved methods may be needed to support MU-MIMO.

[0092] In some current implementations, there is significant overhead associated with CSI feedback reporting, and the overhead is expected to further increase in current and future wireless communication networks (e.g., 5G Advanced or 6G networks) as system bandwidth and the number of antennas increase. CSI compression (e.g., AI / ML-based CSI compression) can reduce the CSI feedback overhead. However, current implementations tend to compress the full channel matrix. In some examples described herein, further overhead reduction can be achieved by compressing one or more eigenvectors (EVs).

[0093] Therefore, new or improved methods and procedures are desired to address 1) reducing CSI feedback overhead by compressing channel eigenvectors, 2) supporting different channel ranks using eigenvector compression, 3) supporting MU-MIMO configurations using eigenvector compression, 4) determining and selecting a CSI compression type (compression of the channel matrix or eigenvectors), 5) post-processing the compressed CSI, 6) indicating the determined CSI compression type to the network, and / or 7) reporting the compressed CSI feedback to the network.

[0094] Typical steps to configure the WTRU AI / ML-based CSI compression capabilities In one example, the WTRU may support AI / ML-based CSI compression using one or more autoencoders (AEs). Different types of AI / ML models (e.g., AEs) may be used for CSI compression. For example, a dedicated (or separate) model may be constructed and trained using a training data set consisting of the full channel response matrix H. This model may be used to compress the full channel matrix H. Another dedicated (or separate) model may be trained using the eigenvectors (EVs) of the channel response, and this model may be used to compress the channel eigenvectors. A generalized model may be constructed and trained to compress either the full channel matrix H or the channel eigenvectors (EVs).

[0095] The WTRU may report its AI / ML-based CSI compression capability to the network (e.g., gNB) and / or may report the configured CSI compression model. Parameters describing the WTRU CSI compression model may include one or more of the following:

[0096] CSI compression types may include: 1) full channel (H) - the WTRU compresses the full channel matrix estimate; and / or 2) eigenvector (EV) - the WTRU compresses the eigenvectors (e.g., one or more eigenvectors, including all) of the channel estimate.

[0097] AI / ML CSI compression model types may include: 1) separate (or dedicated), whereby full-channel matrix compression and eigenvector compression employ separate ML models (e.g., dedicated full-channel or dedicated EV), and / or 2) generalized, whereby full-channel matrix compression and eigenvector compression may use the same ML model.

[0098] The maximum channel rank supported in the AE model input, R m .

[0099] Stacking or formatting type at the autoencoder's input: Zero-padding (ZP): The WTRU may be configured with a (fixed-size) generalized model that supports the full channel H as input (in this case R m =N r ), or the WTRU may be configured with a single model that supports the maximum number of eigenvectors (corresponding to a full-rank channel). In these examples, the data at the ML (e.g., AE) model input is adjusted so that the actual channel rank is equal to the maximum channel rank R supported at the model input. m If it is smaller than , it may be zero padded. Bursting: The WTRU may be configured with a dedicated model for EV compression with a fixed input size, and if the model compresses one eigenvector at a time, the WTRU may format the data in the ML (e.g., AE) model input to compress each eigenvector separately. For example, if the actual channel rank is 1, the WTRU compresses a single eigenvector (associated with the largest eigenvalue), and if the actual channel rank is 2, the WTRU compresses two eigenvectors (e.g., may run the ML encoder model twice). AI / ML model ID, which may include input size, stacking or formatting information for model input (ZP or bursting), output size, other model parameters (e.g., number of layers), and / or training dataset information.

[0100] AI / ML-based CSI compression configuration A WTRU capable of AI / ML-based CSI compression may be configured to report compressed CSI. The configuration may include: AI / ML CSI compression model type: distinct (full channel matrix H and / or channel eigenvectors EV) and / or generalized ●Single user (SU) or multi-user (MU) configuration ●Channel rank threshold CSI feedback type: The WTRU may be configured to report the following: the compressed channel matrix H, or Compressed eigenvectors The type of post-processing to be applied at the output of the ML encoder.

[0101] A representative procedure for eigenvector (EV)-based CSI compression using zero-padding The WTRU may be configured to generate an ML-based CSI feedback report. In one solution, the AI / ML model may be an autoencoder to compress either the channel matrix or the principal eigenvector in the case of single-layer transmission or the dominant eigenvector in the case of multi-layer transmission. Eigenvector-based compression is expected to provide more efficient compression capabilities in contrast to full-matrix compression approaches, especially when the number of layers is smaller than the channel rank. On the other hand, because AE models generally handle a fixed input size, handling the multiple layer / rank case with the eigenvector approach requires the use of multiple models (one for each rank), a technique that significantly increases the computational and memory load on the WTRU. To overcome this issue, a single autoencoder model may be trained to handle the multiple layer / rank case by including a zero-padding step before using the model.

[0102] A high-level block diagram of the proposed zero-padding technique is shown in Figure 4. As shown, CSI-RS is received by the WTRU, and the WTRU performs channel estimation on the CSI-RS. Singular value decomposition (SVD) is performed on the channel estimates. After SVD, zero-padding is performed before the autoencoder process. The compressed CSI feedback information is then transmitted to the network.

[0103] The WTRU may derive the zero-padded eigenvector stack based on the maximum number of layers supported by the AE model. The WTRU may be configured to derive the nth principal eigenvector of the estimated channel matrix in the nth subband, for n=1,...,Nsub. The AE model may be configured to derive the nth principal eigenvector of the estimated channel matrix in the nth subband, for n=1,...,Nsub. m Supports eigenvector compression up to R m ≦N r The AE model is then recalculated using the zero-padding technique described next. m Any number of layers can be handled:

[0104] WTRU, R m When configured to report CSI feedback for layers, the WTRU first calculates the channel matrix

[0105]

number

[0106]

number

[0107]

number

[0108]

number

[0109]

number

[0110]

number

[0111]

number

[0112]

number

[0113]

number

[0114]

number

[0115]

number

[0116] In the case of single-layer transmission,

[0117]

number

[0118]

number

[0119]

number

[0120]

number

[0121] The same AE model can be trained to output codewords of a size that depends on how sparse the input is. For example, in R m For feedback containing layers, the model has a maximum code work size of

[0122]

number

[0123]

number

[0124]

number

[0125] The WTRU may decide whether to use full channel compression or eigenvector compression based on the estimated rank, the number of computational resources, and / or the UCI allocation. In an embodiment, the WTRU may be configured to select between compressing and reporting the full channel matrix or compressing and reporting the associated eigenvectors depending on the estimated rank. Eigenvector compression techniques can potentially achieve higher compression than full-matrix compression, but require performing a singular value decomposition (SVD) on each channel matrix across all subbands, which is computationally more demanding than the full-matrix approach.

[0126] In an embodiment, the WTRU (1) determines the available computational resources (number of CPUs N r ), (2) the number of allocated bits for CSI reporting (i.e., UCI) on either the PUCCH or the PUSCH, or (3) the number of pre-configured layers for CSI reporting (i.e., rank). For example, R m N r If the input samples associated with both techniques are chosen to be equal to , then both the eigenvector compression technique with zero padding and the full channel compression technique have the same dimension N t ×N r N subSince the eigenvectors have the same AE model, the WTRU may use the same AE model. The WTRU may select either full-channel compression or eigenvector compression based on the estimated rank. For example, if the estimated rank R is equal to or less than some pre-configured threshold, eigenvector compression may be selected since it potentially achieves higher compression performance compared to the full-channel matrix case. The WTRU may be configured to select between compressing the full-channel matrix or compressing the eigenvectors based on a pre-configured threshold or an estimated rank indicator. The decision whether to compress the full-channel matrix or the eigenvectors may alternatively or additionally be based on available computational resources. For example, if the number of computational resources is limited or below some threshold, it may be beneficial to use the full-channel matrix approach since an SVD step is not required, regardless of the estimated rank (or possibly in combination with consideration of the estimated rank).

[0127] Alternatively, instead of using one generalized model that can handle both channel samples and zero-padded eigenvector samples, the WTRU can choose between two AE models, one optimized for full channel-based compression and one optimized for eigenvector compression, as shown in FIG. 6.

[0128] 6 is a flowchart illustrating one example embodiment of a process for compressing CSI. In step 601, the channel matrix H is measured. In step 603, the WTRU determines whether it is configured to compress the full channel matrix or the eigenvectors. For example, the WTRU may be pre-configured by the gNB to (1) compress the full channel matrix, (2) compress the eigenvectors, or (3) select either compressing the full channel matrix or compressing the eigenvectors based on certain conditions, such as an estimated rank.

[0129] If the WTRU is configured to compress the full channel matrix, flow proceeds from step 603 to step 615. As described above, the WTRU may be configured with two Ai / ML models for compression: a generalized model (Model #1) that may be well suited to compressing both the channel eigenvectors and the full channel matrix, and a separate model (Model #2) that is best adapted for compressing the full channel matrix. Thus, in step 615, the WTRU determines which model to use for compressing the full channel matrix. In particular, if the WTRU is provisioned with a separate model for full channel matrix compression, it uses that model (Model #2) in step 617. Otherwise, it uses the generalized model (Model #1) in step 613.

[0130] If, on the other hand, in step 603, the WTRU is configured to compress the eigenvectors (or at least consider compressing the eigenvectors based on conditions such as the estimated channel rank), then flow proceeds instead from step 603 to step 605. In step 605, the WTRU checks whether it is configured with a rank threshold to consider when deciding whether to compress the eigenvectors or the full channel matrix. If so, flow proceeds from step 605 to step 607 to make that determination. If the estimated rank indicator is above the preconfigured threshold, then flow proceeds from step 607 to step 615 to perform model selection as described above. On the other hand, if the estimated rank is not above the threshold, then flow proceeds from step 607 to step 609, where the WTRU begins obtaining eigenvectors for all subbands using an SVD process. Next, in step 611, the WTRU builds an eigenvector stack. Then, in step 613, the WTRU compresses the eigenvectors using model #1.

[0131] The WTRU may recommend whether to use a channel matrix or eigenvector compression technique based on reference signal measurements (eg, RSSI, RSRQ, RSRP, SINR) in a MU-MIMO setup or based on the MU-MIMO configuration. Alternatively or additionally, the WTRU may be configured to use either a channel matrix compression technique or an eigenvector compression technique based on reference signal measurements. SVD-based precoding is not optimal for the MU case, and perhaps compressing full channel matrices from different WTRUs is more appropriate for MU-MIMO. Therefore, in the MU-MIMO case, the WTRU may be configured to compress the full channel matrix and feed it back to the gNB, so that the gNB can design a precoder based on full channel matrix information from all of the co-scheduled WTRUs. However, in the MU-MIMO case (as shown in FIG. 7), there is still a chance that SVD precoding may result in acceptable performance (e.g., for inter-cell interference cases, when co-scheduled WTRUs are far from each other). The WTRU may use some reference signal measurements to recommend whether it is beneficial to compress the eigenvectors or channel matrix. For example, the WTRU may use a signal-to-interference-and-noise (SINR) measurement and compare it to a pre-configured threshold.

[0132] FIG. 8 is a flow chart illustrating an embodiment in which a WTRU determines whether to use overall channel compression or eigenvector compression based on whether the WTRU is configured for MU-MIMO.

[0133] As shown, a channel matrix H is obtained via measurements at 801. Then, at 803, the WTRU determines whether it is configured for MU-MIMO.

[0134] If the WTRU is configured for MU-MIMO, it will compress the full channel matrix; if not configured for MU-MIMO, it will compress the eigenvectors. Thus, if not configured for MU-MIMO, flow proceeds from step 803 to step 805, where the WTRU begins obtaining eigenvectors for all subbands using an SVD process. Then, in step 807, it builds an eigenvector stack and, in 809, inputs the eigenvectors into autoencoder model #1.

[0135] On the other hand, if at 803 the WTRU determines that it is configured for MU-MIMO, then flow proceeds instead to step 811, where the WTRU checks whether it is configured with a separate model for MU-MIMO (Model #2). If so, then flow proceeds from step 811 to 813, where Model #2 is used. If not, then flow proceeds from step 811 to step 809, where Generalized Model #1 is used.

[0136] If a generalized model is used, flow proceeds from 1213 to step 1209 where the channel burst is input to a generalized autoencoder (trained on all eigenvectors and the H burst).

[0137] On the other hand, if a separate model is used, flow instead proceeds from step 1213 to step 1215, where the channel bursts are input to a separate autoencoder (trained only on the H burst).

[0138] The WTRU may transmit a CSI report containing the compressed eigenvectors with padded zero dimensions or containing the compressed channel matrix. The WTRU may be configured to report either the compressed channel matrix or the compressed eigenvectors as part of the CSI report. The WTRU may also be configured to report a recommendation between the two approaches in the case of multi-user or single-user, or single-layer or multi-layer, or any combination thereof (which the gNB may or may not choose to follow for future CSI feedback reporting). In the case of eigenvector compression with zero padding, the WTRU may be configured to explicitly indicate the number of padded zeros for meaningful reconstruction at the gNB side. In another option, the number of padded zeros can be implicitly known from the rank indicator and the maximum number of layers supported by the AE model.

[0139] A representative procedure for eigenvector (EV)-based CSI compression using bursting The WTRU may be configured with AI / ML-based bursting, in which case the autoencoder may compress either the channel matrix burst or the eigenvector burst in the case of a single-layer transmission, or the dominant eigenvector in the case of a multi-layer transmission. In this regard, the EV / H burst may be compressed into a fixed-size block (i.e., N t ×N sub The AE is defined as a mapping of EV / H to a number of blocks, each of which is input to the encoder separately. Fixing the size of the input burst to the AE allows the AE model to handle a fixed input size when dealing with multiple layers / ranks for both the channel bursting and eigenvector bursting approaches, as shown in the high-level block diagram in Figure 9.

[0140] The WTRU may perform measurements on the acquired channel and then use those measurements (i.e., based on the estimated rank from the measurements) to select either a channel matrix burst or an eigenvector burst to use as input to the autoencoder. Alternatively or additionally, the WTRU may determine the type of input based on any one or more of: (1) available computational resources; (2) the number of allocated bits for CSI reporting on either the PUCCH or the PUSCH; and (3) the number of preconfigured layers for CSI reporting. For example, the WTRU may be configured to check the rank of the channel and can select either a channel matrix or an eigenvector based on a particular threshold. In addition, the WTRU may be configured to select to use a channel matrix burst or an eigenvector burst in a multi-user scenario.

[0141] In one embodiment, a WTRU may be configured with channel matrix bursting as follows: A WTRU may be configured with channel matrix bursting, and N sub channels are input to the bursting block. sub n sub-bands r The th row vector is mapped to a single block, (N t ×N sub ) of the channel matrix in all subbands. r repeated for row vectors, thus (N t ×N sub ) with a total size of N r bursts are generated. For example, if some N sub channels

[0142]

number

[0143]

number

[0144]

number

[0145]

number

[0146] All N r bursts are fed into the autoencoder to generate N r The compressed bursts are generated and sent as part of the CSI feedback. Thus, the channel matrix is fed back to the gNB. The WTRU may be configured to input each channel matrix burst into a parallel autoencoder.

[0147] In one embodiment, the WTRU may be configured with EV bursting as follows: If the WTRU is configured with eigenvector bursting, the SVD decomposition is sub This is performed for all N channels. sub eigenvectors (i.e., the principal eigenvectors in the case of single-layer transmission or the dominant eigenvectors in the case of multi-layer transmission) are fed to the bursting block, and all N sub n subband eigenvectors t The th column vector is mapped to a single block, (N t ×N sub ) size block. The same operation is performed for all R m Repeated for row vectors, R m denotes the maximum rank defined by the WTRU (e.g.,

[0148]

number

[0149] For example, N sub The EV of the channel in a sub-band can be expressed as:

[0150]

number

[0151]

number

[0152]

number

[0153] All R m bursts are fed into the autoencoder to generate R m compressed bursts are generated and sent as part of the CSI feedback. The WTRU may be configured to input each eigenvector burst into a parallel autoencoder.

[0154] In one embodiment, the WTRU may be configured with eigenvector bursting based on a particular rank R as follows:

[0155] For example, the WTRU may be configured to perform eigenvector bursting using a particular R (i.e., N sub (After SVD decomposition is performed on all channels) subeigenvectors are fed to the bursting block, and all N sub The first R column vectors of the subband eigenvectors are mapped to R blocks, each of which is (N t ×N sub ) size.

[0156] In one example, when R=1, the first eigenvectors of all subbands are expressed as a single (N t ×N sub ) where one eigenvector burst is input to an autoencoder that outputs a single compressed burst out1 of size M.

[0157] When R=2, the first eigenvector in all subbands is a single (N t ×N sub ) size EV1, and then the second eigenvectors in all subbands are mapped to another (N t ×N sub ) into a block EV2 of size M. Now, both eigenvector bursts are input to an autoencoder, which outputs two compressed bursts out1 and out2 of size M.

[0158] When R=3, the first eigenvector in all subbands is a single (N t ×N sub ) and the second eigenvector in every subband is mapped to another (N t ×N sub ) block EV2, and the third eigenvector in every subband is mapped to another (N t ×N sub ) where all eigenvector bursts are input to an autoencoder that outputs three compressed bursts out1, out2 and out3, each of size M.

[0159] All R m bursts are fed into the autoencoder to generate R m compressed bursts are generated and sent as part of the CSI feedback.

[0160] The WTRU may be configured to input each of the R eigenvector bursts into a parallel autoencoder.

[0161] In another embodiment, the WTRU may choose to use eigenvector bursting or channel bursting based on some measurements of the channel. For example, the WTRU determines the rank of the channel matrix and chooses to use eigenvector compression or full channel compression based on the rank. For example, if the WTRU measures a low rank channel, it may choose to use eigenvector bursting (e.g., the WTRU uses the principal eigenvector when R=1). On the other hand, if the WTRU measures a high rank, it may choose to use the full channel matrix. For example, if the channel matrix is full rank (R=N r ), the WTRU may choose to compress the channel matrix since the output of the autoencoder will be the same in either case. Furthermore, the WTRU may determine whether the channel is low-rank or high-rank based on a certain threshold.

[0162] The WTRU may be configured to compress the channel matrix burst or the eigenvector burst. Furthermore, the WTRU may be configured to consider compressing the eigenvector burst or to always compress the channel matrix burst. In this case, assuming the WTRU is configured to consider using eigenvectors, the WTRU may be configured to consider using a threshold or not.

[0163] A detailed process flow chart is shown in Figure 11. As shown, in 1101, a channel matrix H is obtained through measurement. Then, in 1103, N sub Given a set of channels, the WTRU determines whether to burst the channel matrix or eigenvectors in all subbands. For example, the WTRU may be pre-configured by the gNB to (1) compress the full channel matrix, (2) compress the eigenvectors, or (3) choose between compressing the full channel matrix or compressing the eigenvectors based on certain conditions, such as an estimated rank.

[0164] If the WTRU determines that it is configured to report eigenvectors, flow proceeds to step 1105. In step 1105, the WTRU determines whether it is further configured with an estimated rank threshold that should be considered before deciding to report eigenvectors. If the WTRU is not configured with such a threshold, flow proceeds directly to step 1109, where the WTRU begins to obtain eigenvectors for all subbands using an SVD process. Then, in step 1111, an eigenvector burst is created and, in 1113, the eigenvectors are input to an autoencoder.

[0165] On the other hand, if at 1105 the WTRU determines that it is configured with an estimated rank threshold, then the flow proceeds instead from 1105 to 1107, where the WTRU compares the estimated rank of the channel to a threshold. The threshold may be predefined or configured by the gNB. If the rank is greater than the threshold, then the flow exits the EV leg of the flow at step 1115 and proceeds to the full channel leg of the flow, as described further below. On the other hand, if at step 1107 it is determined that the rank < threshold, then the flow instead proceeds from step 1107 to steps 1109, 1111, and 1113 as described above, i.e., obtaining eigenvectors for all subbands (step 1109), then creating eigenvector bursts (step 1111), and providing them to the autoencoder (step 1113).

[0166] Returning to step 1103, if the WTRU initially determines that it is configured to burst the full channel matrix H rather than EV, flow instead proceeds from step 1103 to step 115, and the WTRU selects N r eigenvectors and H-bursts (including channel matrix information). Next, in step 1117, the WTRU checks which model to use based on its particular configuration. If the generalized model is selected, the channel bursts are input to a generalized autoencoder (trained on all eigenvectors and the H-burst), as shown at 1113. On the other hand, if the WTRU chooses to use a separate model, flow instead proceeds from step 1117 to step 1119, where the channel bursts are input to a separate autoencoder (trained on only the H-burst).

[0167] In one embodiment, AI / ML-based CSI feedback may be used to enable MU-MIMO transmission. The selection of CSI feedback for one WTRU depends on feedback from all simultaneously scheduled devices. Therefore, to conclude a suitable CSI feedback type in a MU-MIMO scenario, the network requires complete knowledge of the channels experienced by all scheduled devices. For example, if the scheduled devices experience high correlation, the network may configure the WTRU to report H-bursts. On the other hand, if the scheduled devices experience independent channels, the WTRU may be configured to transmit eigenvector bursts. Note that transmitting channel matrices rather than eigenvectors comes at the cost of higher signaling overhead.

[0168] 12 is a flowchart illustrating channel condition reporting for MU-MIMO transmissions according to one example embodiment. The WTRU may be configured to use either H-bursts or eigenvector bursts.

[0169] As shown, a channel matrix H is obtained via measurements at 1201. The WTRU then determines at 1203 whether it is configured to compress the channel matrix H or the eigenvectors EV for MU-MIMO for transmission to the network.

[0170] If the WTRU is configured to compress and transmit the eigenvectors, flow proceeds from step 1203 to step 1205, where the WTRU begins obtaining the eigenvectors for all subbands using an SVD process, then creates an eigenvector burst in step 1207, and inputs the eigenvectors to an autoencoder in 1209.

[0171] On the other hand, if in 1203 the WTRU decides to compress and transmit the channel matrix, then in step 1211 the WTRU r bursts and then checks in step 1213 which model to use based on the particular configuration.

[0172] If a generalized model is used, flow proceeds from 1213 to step 1209 where the channel burst is input to a generalized autoencoder (trained on all eigenvectors and the H burst).

[0173] On the other hand, if a separate model is used, flow instead proceeds from step 1213 to step 1215, where the channel bursts are input to a separate autoencoder (trained only on the H burst).

[0174] Representative steps for post-processing compressed CSI In particular embodiments, the WTRU may post-process the stack / burst of compressed eigenvectors / H at the output of the AE. The WTRU may perform measurements on the compressed H / eigenvector output in the latent domain to further reduce the dimensionality of the feedback.

[0175] For example, a WTRU may be configured with one or more post-processing types, which are applied in the potential domain as shown in Figure 13. Each post-processing type may be defined using an index. For each post-processing type, the WTRU configuration may be associated with a set of parameters, and some parameters may be used in one or more post-processing types. As shown in Figure 13, if post-processing is present in the WTRU, corresponding inverse processing is required on the network side.

[0176] Post-processing may be performed for each input type (i.e., zero-padding or bursting of H / eigenvectors), and parameters may be configured for each post-processing type. Additionally, the WTRU may be configured with one or more parameter updates based on the post-processing type.

[0177] The WTRU may be configured with a set of parameters for use with one or more post-processing types, which may include at least one of the following: Compressed channel / eigenvector (e.g., single output of an autoencoder) correlation threshold. This parameter may be associated with a post-processing type that involves latent domain post-processing. The WTRU may determine the correlation using a compressed channel / eigenvector correlation of the same output. Compressed channel / eigenvector burst correlation threshold (eg, correlation between compressed outputs of multiple outputs). The WTRU may compare the compressed channel / eigenvector burst correlation value to a particular threshold. Compressed channel / eigenvector burst correlation threshold over the time domain (e.g., correlation between compressed outputs of multiple outputs). The WTRU may compare the correlation value of the zero padding or burst of compressed channel / eigenvectors with a certain threshold in the time domain (output of compressed eigenvectors / H in different time slots).

[0178] Quantizer information for adaptive quantization. This parameter may be associated with a post-processing type that uses sparsity information of the input zero-padded eigenvectors. Depending on the sparsity level of the input zero-padded eigenvectors, the WTRU may switch between different quantizers. For example, a low-resolution quantizer may be used with input eigenvector stacks of high sparsity, and a high-resolution quantizer may be used with input eigenvector stacks of low sparsity.

[0179] Adaptive Quantization: The WTRU may be configured with adaptive quantization at the output based on the sparsity of the eigenvector / H input, as shown in FIG. 14. In one solution, the WTRU may perform measurements on the input to the autoencoder and, for example, check the sparsity of the input when using zero-padded eigenvectors / H to determine which quantizer to use. For example, the WTRU may support multiple quantizers (e.g., Q#1, ..., Q#K as in FIG. 14), each applicable to a specific set of measurements. For example, when the input to the autoencoder is very sparse (e.g., many zeros), a low-resolution quantizer may be used, but when the input to the autoencoder is less sparse (e.g., a high-rank zero-padded eigenvector stack), the WTRU may select a different quantizer with higher resolution. The WTRU may define each quantizer using an index, which can be reported to the network to apply an equivalent dequantization procedure.

[0180] Single Output Coupling: In an embodiment, the WTRU may be configured to perform post-processing on the compressed output of a single eigenvector / H. Here, the WTRU may perform measurements on the output of the autoencoder in the latent domain to reduce the dimensionality of the feedback. For example, the WTRU may check the correlation between coefficients of the compressed information, and a post-processor may average adjacent coefficients (e.g., before quantization) based on a certain threshold for correlation. For example, for a given output L of size M:

[0181]

number

[0182] The WTRU is a function of N adjacent coefficients, i.e., l m ,l m+1 ,...,l m+NThen, if the correlation level exceeds a certain threshold, the WTRU may combine (e.g., average) M adjacent coefficients. Thus, the size of the output of the post-processor is

[0183]

number

[0184] Multiple output combinations: The WTRU may be configured to perform post-processing on the compressed output of the multiple eigenvectors / H, where the WTRU uses the R of the autoencoder in the latent domain to reduce the dimensionality of the feedback. m Measurements may be performed on the outputs.

[0185] When using the bursting method, each N sub channels are represented by R at the output of the autoencoder. m (For example, R m =R or R m =N r ) eigenvectors or channel response H, each of size M. The WTRU may perform measurements on the outputs to identify similarities between multiple outputs. For example, for a given output of the encoder,

[0186]

number

[0187]

number

[0188]

number

[0189]

number

[0190]

number

[0191]

number

[0192]

number

[0193] Additionally, the WTRU may receive instructions to use post-processing over a set period of time and / or across multiple groups of sub-bands.

[0194] If the WTRU supports time-domain post-processing in the latent domain, the WTRU may perform measurements on the output of the autoencoder over a particular time period to reduce the dimensionality of the output over a time period.

[0195] In one example, the WTRU receives N compressed signals over a period of T. TThe outputs may be post-processed. The WTRU may perform measurements on the outputs (e.g., correlation between different outputs), and based on a certain threshold, the WTRU may, for example, average the outputs into a single output.

[0196] Representative Procedure for Reporting Compressed CSI The WTRU may be configured to report compressed CSI using a CSI compression type (or model, or model type) including full channel compression (H), or eigenvector compression (EV), or a combination of the two (e.g., multi-resolution EV / H) based on the estimated rank, and / or number of computational resources, and / or uplink feedback allocation.

[0197] In one embodiment, the WTRU may report compressed CSI using combined reporting (e.g., multi-resolution EV / H reporting) that includes a combination of full-channel-based compression and EV-based compression. For example, the WTRU may report compressed CSI using full-channel compression (H) for one or more wideband CSI reports and may report compressed CSI using eigenvector (EV) compression for one or more subband CSI reports. In another example, the WTRU may report compressed CSI using full-channel compression (H) for some subbands (e.g., when the rank exceeds a configured threshold) and may report compressed CSI using EV compression for other subbands of the allocated bandwidth. In some cases using EV compression, methods may include, but are not limited to, using zero padding and / or bursting.

[0198] The feedback and reporting procedure may be applicable to any AI / ML model solution for different compressed CSI model types, including AE methods, and post-processing solutions, including dimensionality reduction methods.

[0199] The AI / ML model may be configured by the network, predefined, or based on the WTRU's implementation. In some solutions, the WTRU may be configured to report the AI / ML model specifications, such as the neural network architecture and hyperparameters. In other solutions, the AI / ML model specifications may be implicitly inferred based on specific WTRU behavior.

[0200] The configuration of the CSI compression model for compressed CSI reporting may be based on an instruction from the gNB, for example, explicitly through RRC, MAC-CE, or PUCCH / DCI. The WTRU may autonomously indicate a new or modified compression model type to the gNB, either explicitly through uplink signaling or implicitly through a specific selection of UL resources, upon observing certain performance metrics on the downlink.

[0201] Two embodiments may be considered for the WTRU to determine or update the CSI compression model type for compressed CSI reporting: (i) semi-static operation, in which the WTRU determines the model type based on specific channel measurements, e.g., using EV for a low-rank channel, and reports to the gNB, which then configures an AI / ML model for EV; and (ii) dynamic operation, in which the WTRU determines the model and applies it to the compressed CSI feedback, and the gNB then determines the model to be used either through blind detection or specific header indication from the report.

[0202] The compressed CSI may be explicitly reported through PUCCH or PUSCH based on the configured time-domain behavior (aperiodic or periodic / semi-persistent), among other options. The compressed CSI may also be implicitly reported in some embodiments through a specific selection of UL resources (RACH, PUCCH, PUSCH, SRS, SpatialRelationInfo, etc.), e.g., for EVs with low rank.

[0203] The selection between H, EV, or EV / H may affect the reporting of other CSI quantities and / or any other measurements measured by the WTRU from the CSI-RS or SSB.

[0204] In some embodiments, the rank may be extracted implicitly from reporting compressed CSI, including implicitly from full channel compression (H), implicitly from EV bursts, or from post-processed feedback information for decompression, all of which may alleviate the need to report RI.

[0205] The CSI processing criteria may affect the reporting of compressed CSI. In some solutions, the WTRU may decide on either H, EV, or EV / H based on the number of CPUs and CSI computation requirements.

[0206] The WTRU may be configured to report compressed CSI, whether full channel compression (H), or eigenvector compression (EV), or a combination of the two (multi-resolution EV / H), based on the estimated rank, and / or the number of computational resources, and / or the uplink feedback allocation.

[0207] The configuration of the compressed CSI report may be based on a previous indication from the WTRU, either explicitly through uplink signaling or implicitly through a specific selection of UL resources.

[0208] The compressed CSI may be explicitly reported over PUCCH or PUSCH based on the configured time-domain behavior (aperiodic or periodic / semi-persistent). The AI / ML model may be configured by the network, predefined, or based on the WTRU implementation. In some embodiments, the WTRU may be configured to report the AI / ML model specifications, such as neural network architecture and hyperparameters. In other embodiments, the AI / ML model specifications may be implicitly estimated, for example, by the ZP method or bursting.

[0209] FIG. 15 is a block diagram illustrating an example of a CSI feedback procedure between a WTRU and a network (e.g., a gNB) using CSI compression type selection and indication, in accordance with one or more embodiments described above. In this example, the WTRU is capable of full-channel CSI compression and eigenvector-based CSI compression and may select one or more CSI compression types. For example, the WTRU performs channel measurements and determines a rank associated with the measured channel. If the determined rank is less than a configured channel rank threshold, the WTRU selects EV-based compression, which may reduce CSI feedback overhead. Otherwise, the WTRU selects full-channel compression. The WTRU may report the compressed CSI and / or the selected CSI compression type to the network (e.g., a gNB).

[0210] FIG. 16 shows an example of a CSI feedback procedure using a selected CSI compression type. In this example, a WTRU capable of eigenvector (EV) CSI compression can select a CSI compression type (full channel or EV-based). The WTRU is configured with a channel rank threshold for CSI compression type selection. For example, the WTRU may receive configuration information from a network entity indicating the channel rank threshold. The WTRU may determine a channel rank associated with a channel measurement. For example, the WTRU may measure a downlink channel and determine a rank associated with the measured channel.

[0211] In one example, the WTRU may select the type of CSI compression based on the determined channel rank and a channel rank threshold. In another example, the WTRU may select the type of CSI compression based on any of the estimated rank, the number of computational resources, and / or the uplink feedback allocation.

[0212] In some aspects, the type of CSI compression selected includes full-channel-based compression, eigenvector (EV)-based compression, or 3) a combination of full-channel-based compression and eigenvector (EV)-based compression.

[0213] In one example, the WTRU may select EV-based compression when the determined channel rank is less than a channel rank threshold, hi another example, the WTRU may select full-channel-based compression when the determined channel rank is greater than or equal to a channel rank threshold.

[0214] The WTRU may transmit to a network entity the CSI and information indicating the selected CSI compression type, where the CSI is associated with the channel measurements and has been compressed using the selected CSI compression type.

[0215] In some embodiments, the configuration information includes an instruction to enable selection of a type of CSI compression from a set of types of CSI compression, the set of types of CSI compression including full-channel-based compression and EV-based compression.

[0216] In some embodiments, full-channel-based compression includes compressing a full-channel matrix, which in one example is an estimated channel matrix.

[0217] In some embodiments, the EV-based compression includes compressing one or more channel eigenvectors, in one example, each of the one or more channel eigenvectors is a respective eigenvector of the channel estimate.

[0218] In some embodiments, the WTRU is configured to perform CSI compression using a selected type of CSI compression, i.e., full-channel-based compression, EV-based compression, or a combination of full-channel-based compression and EV-based compression.

[0219] In some embodiments, when performing CSI compression, the WTRU may compress the CSI via an artificial intelligence / machine learning (AI / ML) model.

[0220] Exemplary Procedure for Compressed CSI Reporting for MU-MIMO Network side information used as input for AI / ML models for CSI compression In an embodiment, the WTRU may be configured in one or more operating modes for compressed CSI reporting, where the compressed CSI may be the output of an AI / ML model (e.g., an autoencoder), and the WTRU may report the output of the AI / ML model as a CSI report on determined uplink resources.

[0221] The operation mode may be determined or identified based on whether the input of the AI / ML model for CSI compression includes auxiliary information from the gNB. For example, in a first operation mode, the input of the AI / ML model for CSI compression may be based on reference signal measurements (e.g., channel matrix: H, eigenvectors: EV), and in a second operation mode, the input of the AI / ML model for CSI compression may be based on auxiliary information provided by the gNB in addition to the reference signal measurements. The auxiliary information may be at least one of the following: 1) channel information (e.g., channel matrix, eigenvector, beam direction, location, PMI) of another WTRU that may be scheduled on the same time / frequency resources as this WTRU. For example, the WTRU may be provided with MIMO transmission scheme information (e.g., MU-MIMO transmission scheme) that may be used at the gNB. The MIMO transmission scheme information may determine the AI / ML model for CSI compression; 2) channel information of an interfering WTRU; 3) WTRU location information of the interfering WTRU; or 4) scheduling mode (e.g., SU-MIMO, MU-MIMO). 5) MU-MIMO transmission schemes (e.g., ZF-BF, nonlinear precoders), and / or 6) AI / ML models for CSI compression.

[0222] The operating mode may be determined or identified based on the CSI type of the AI / ML model input for CSI compression, where the CSI type may be at least one of channel information (e.g., channel matrix, eigenvector, PMI), beam information (e.g., beam direction, beam index), channel quality information (e.g., CQI, RSRP, Reference Signal Received Quality (RSRQ), RI, etc.), and / or channel information format (e.g., zero-padding-based eigenvector, bursting-based eigenvector, number of subbands, subband size).

[0223] The WTRU may indicate or report its ability to support one or more operating modes for CSI compression using an AI / ML model.

[0224] Hereinafter, the term auxiliary information may be used interchangeably with additional information, channel information of an interfering WTRU, co-channel information, co-channel information for MU-MIMO, interfering channel information, and interfering beam information.

[0225] One or more operating modes for CSI compression may be used, and the WTRU may determine the operating mode based on one or more of the following:

[0226] Availability of additional information provided (or indicated) by the gNB. For example, if the additional information is available as input for CSI compression, a first operation mode (e.g., the input of the AI / ML model includes the additional information) may be used. Otherwise, a second operation mode (e.g., the input AI / ML model is based on measurements only at the WTRU side) may be used.

[0227] A validity timer or validity time window for the additional information may be used. For example, the additional information provided by the gNB may be valid within a time period starting from the reception of the additional information. For example, if a WTRU receives additional information by the gNB in slot #n, the additional information may be valid until slot #n+K. From slot #n+K+1, the WTRU may consider the additional information invalid (i.e., unavailable or inapplicable). The value K may be determined based on one or more of the following: configuration from the gNB, WTRU mobility (e.g., WTRU speed), subcarrier spacing, and / or accuracy of the AI / ML model. The additional information may be provided by the gNB as part of the CSI reporting configuration via higher layer signaling (e.g., RRC, MAC-CE). Alternatively, the additional information may be provided by the gNB as part of aperiodic CSI reporting triggering information.

[0228] CSI reporting resource. For example, one or more CSI reporting resources may be configured, and the CSI reporting resource may be determined based on at least one of a CSI reporting timing, an indication in a triggering signal, and one or more preconfigured conditions. The WTRU may determine an operation mode based on the determined CSI reporting resource.

[0229] Network auxiliary information used to process input for AI / ML models for CSI compression In an embodiment, the WTRU may determine, estimate, and / or process inputs of the AI / ML model for CSI compression by using auxiliary information provided by the gNB. For example, when the auxiliary information is not available / applicable, the WTRU may determine a subset (or rank) of eigenvectors as inputs for the AI / ML model for CSI compression based on the order of the largest eigenvalue (e.g., when a single eigenvector is reported, determine the eigenvector with the largest eigenvalue, and when two eigenvectors are reported, determine the two eigenvectors with the first and second largest eigenvalues). On the other hand, when the auxiliary information is available / applicable, the WTRU may determine a subset of eigenvectors as inputs for the AI / ML model for CSI compression taking into account the auxiliary information (e.g., co-channel interference from another WTRU) that may maximize a metric (e.g., system throughput, sum capacity, etc.), where the metric may be determined by the WTRU, configured by the gNB, or predetermined.

[0230] The number of eigenvectors in the subset may be determined based on the rank determined by the WTRU, and the rank may be implicitly or explicitly reported along with the subset of eigenvectors.

[0231] The availability / applicability of the assistance information by the gNB may be determined based on the reception time of the assistance information or the duration of the received assistance information when the assistance information is used for CSI reporting and / or CSI compression.

[0232] conclusion While features and elements have been provided above in particular combinations, those skilled in the art will understand that each feature or element can be used alone or in any combination with other features and elements. The present disclosure is not limited in terms of the specific embodiments described herein; these embodiments are intended as illustrations of various aspects. It will be apparent to those skilled in the art that many modifications and variations may be made without departing from the spirit and scope of the invention. No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly stated as such. Functionally equivalent methods and apparatuses within the scope of the present disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing description. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is understood that the present disclosure is not limited to any particular method or system.

[0233] The foregoing embodiments are discussed with respect to the terminology and structure of infrared-enabled devices (i.e., infrared emitters and receivers) for simplicity, however, the discussed embodiments are not limited to these systems and may also be applied to other systems that use other forms of electromagnetic waves, or non-electromagnetic waves such as acoustic waves.

[0234] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the term “video” or “image” can mean either a snapshot, a single image, and / or multiple images displayed over time. As another example, when referred to herein, the term “user equipment” and its abbreviation “UE,” “remote,” and / or the term “head-mounted display” and its abbreviation “HMD” can mean or include (i) a wireless transmit and / or receive unit (WTRU), (ii) any of several embodiments of a WTRU, (iii) a wireless-enabled and / or wired-enabled (e.g., tetherable) device specifically configured to have some or all of the structure and functionality of a WTRU, (iii) a wireless-enabled and / or wired-enabled device configured to have less than all of the structure and functionality of a WTRU, or (iv) the like. Details of an exemplary WTRU, which may represent any WTRU listed herein, are provided herein with respect to FIGS. 1A-1D . As another example, various embodiments disclosed herein above and below are described as utilizing a head-mounted display. Those skilled in the art will recognize that devices other than head-mounted displays may be utilized and that some or all of the present disclosure and various disclosed embodiments may be modified accordingly without undue experimentation. Examples of such other devices may include drones or other devices configured to stream information to provide an adaptive reality experience.

[0235] Additionally, the methods provided herein may be implemented in a computer program, software, or firmware embodied in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random-access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, MME, EPC, AMF, or any host computer.

[0236] Modifications to the methods, apparatus, and systems provided above are possible without departing from the scope of the present invention. In view of the wide variety of possible embodiments, it should be understood that the illustrated embodiments are merely examples and should not be construed as limiting the scope of the following claims. For example, the embodiments provided herein include portable devices, which may include or be utilized with any suitable voltage source, such as a battery providing any suitable voltage.

[0237] Furthermore, in the above embodiments, it should be noted that processing platforms, computing systems, controllers, and other devices include processors. These devices may include at least one central processing unit ("Central Processing Unit (CPU)") and memory. In accordance with the practices of those skilled in the art of computer programming, references to acts and symbolic representations of operations or instructions may be performed by various CPUs and memories. Such acts and operations or instructions may be referred to as being "executed," "executed by a computer," or "executed by a CPU."

[0238] Those skilled in the art will understand that the operations and symbolically represented operations or instructions include the manipulation of electrical signals by a CPU. The electrical system represents data bits that may cause a resulting transformation or reduction of the electrical signals, and maintains the data bits in memory locations in a memory system, thereby reconfiguring or otherwise altering the operation of the CPU and the processing of other signals. The memory locations where the data bits are maintained are physical locations that have particular electrical, magnetic, optical, or organic properties that correspond to or represent the data bits. It should be understood that embodiments are not limited to the platforms or CPUs mentioned above, and that other platforms and CPUs may support the provided methods.

[0239] The data bits may also be maintained on computer-readable media, including magnetic disks, optical disks, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage system readable by a CPU. The computer-readable media may include computer-readable media that reside exclusively on a processing system, or that are distributed, cooperative, or interconnected among multiple interconnected processing systems, which may be local or remote to a processing system. It should be understood that embodiments are not limited to the memories mentioned above, and that other platforms and memories may support the provided methods.

[0240] In an example embodiment, any of the operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium, which may be executed by a processor of a mobile, a network element, and / or any other computing device.

[0241] There is little distinction between hardware and software implementations of aspects of a system. Whether to use hardware or software is generally (though not always, the choice between hardware and software can be important in certain contexts) a design choice that represents a trade-off between cost and efficiency. There may be various implementations (e.g., hardware, software, and / or firmware) in which the processes and / or systems and / or other techniques described herein may be effective, and the preferred implementation may vary depending on the context in which the processes and / or systems and / or other techniques are deployed. For example, if an implementer determines that speed and accuracy are paramount, the implementer may select a primarily hardware and / or firmware implementation. If flexibility is paramount, the implementer may select a primarily software implementation. Alternatively, the implementer may select some combination of hardware, software, and / or firmware.

[0242] The foregoing detailed description has illustrated various embodiments of devices and / or processes through the use of block diagrams, flowcharts, and / or examples. To the extent that such block diagrams, flowcharts, and / or examples include one or more functions and / or operations, it will be understood by those skilled in the art that each function and / or operation within such block diagrams, flowcharts, or examples can be individually and / or collectively implemented by a wide range of hardware, software, firmware, or substantially any combination thereof. In one embodiment, portions of the subject matter described herein can be implemented via application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), and / or other integrated forms. However, those skilled in the art will recognize that certain aspects of the embodiments disclosed herein may be equivalently implemented, in whole or in part, in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as substantially any combination thereof, and that designing circuitry and / or writing software and / or firmware code is within the skill of those skilled in the art in light of this disclosure. Additionally, those skilled in the art will understand that the subject matter mechanisms described herein may be distributed as program products in various forms, and that exemplary embodiments of the subject matter described herein apply regardless of the particular type of signal-bearing medium used to actually effect the distribution. Examples of signal bearing media include, but are not limited to, recordable media such as floppy disks, hard disk drives, CDs, DVDs, digital tape, computer memory, and transmission media such as digital and / or analog communications media (e.g., fiber optic cables, wave guides, wired communications links, wireless communications links, etc.).

[0243] Those skilled in the art will recognize that it is common in the art to describe devices and / or processes in the manner described herein and then use engineering techniques to integrate such described devices and / or processes into a data processing system. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system through a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system may generally include one or more of the following: a system unit housing; a video display device; memory, such as volatile and non-volatile memory; a processor, such as a microprocessor and a digital signal processor; computational entities, such as an operating system, drivers, a graphical user interface, and application programs; one or more interaction devices, such as a touchpad or screen; and / or a control system, including feedback loops and control motors (e.g., feedback for sensing position and / or velocity, control motors for moving and / or adjusting components and / or quantities). A typical data processing system may be implemented utilizing any suitable commercially available components, such as those typically found in data computing / communication systems and / or network computing / communication systems.

[0244] The subject matter described herein may illustrate different components contained within or connected to different other components. It should be understood that such depicted architectures are merely examples, and that in fact many other architectures that achieve the same functionality may be implemented. Conceptually, any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality may be achieved. Thus, any two components herein that combine to achieve a particular function may be considered to be “associated” with each other such that the desired functionality is achieved, regardless of the architecture or intervening components. Similarly, any two components so associated may be considered to be “operably connected” or “operably coupled” to each other to achieve the desired functionality, and any two components that can be associated in this way may be considered to be “operably couplable” with each other to achieve the desired functionality. Examples of operably couplable include, but are not limited to, components that are physically matable and / or physically interacting, and / or components that are wirelessly interacting and / or wirelessly interacting, and / or components that logically interact and / or logically interacting.

[0245] With respect to the use of virtually any plural and / or singular term herein, those skilled in the art may convert from plural to singular and / or from singular to plural as appropriate to the context and / or application. For purposes of clarity, various singular / plural permutations may be expressly set forth herein.

[0246] In general, those skilled in the art will understand that the terms used in this specification, and particularly in the appended claims (e.g., the body of the appended claims), are generally intended as "open" terms (e.g., the term "including" should be interpreted as "including, but not limited to," the term "having" should be interpreted as "having at least," and the term "including" should be interpreted as "including, but not limited to"). Furthermore, where a specific number of recitations of an introduced claim are intended, such intention will be explicitly set forth in the claim; in the absence of such recitation, those skilled in the art will understand that no such intention exists. For example, where only one item is intended, the term "single" or similar language may be used. To assist in understanding, the following appended claims and / or description of this specification may include the use of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed as meaning that the introduction of a claim recitation with the indefinite article "a" or "an" limits any particular claim that includes such an introduced claim recitation to embodiments that include only that one recitation, even if the same claim also includes the introductory phrase "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and / or "an" should be interpreted to mean "at least one" or "one or more"). The same applies to the use of definite articles used to introduce claim recitations. Additionally, those skilled in the art will recognize that even when a specific number of recitations of an introduced claim are explicitly recited, such recitation should be interpreted to mean at least the recited number (e.g., the simple recitation "two recitations" without any other modifiers means at least two recitations, or more than two recitations).Furthermore, when notation similar to "such as at least one of A, B, and C" is used, such structure is generally intended as a meaning that one of ordinary skill in the art would understand the notation (e.g., "a system having at least one of A, B, and C" includes, but is not limited to, systems having A only, B only, C only, A and B together, A and C together, B and C together, and / or A, B, and C together). When notation similar to "such as at least one of A, B, or C" is used, such structure is generally intended as a meaning that one of ordinary skill in the art would understand the notation (e.g., "a system having at least one of A, B, or C" includes, but is not limited to, systems having A only, B only, C only, A and B together, A and C together, B and C together, and / or A, B, and C together). Those skilled in the art will further appreciate that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the specification, claims, or drawings, should be understood to contemplate the possibility of including one of the terms, either of the terms, or both terms. For example, the phrase "A or B" should be understood to include the possibilities of "A" or "B" or "A and B." Furthermore, as used herein, the term "any of," followed by a list of items and / or a list of categories of items, is intended to include "any of," "any combination of," "any plurality of," and / or "any combination of" of the items and / or categories of items, individually or in combination with other items and / or other categories of items. Furthermore, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, the term "number" is intended to include any number, including zero. Also, as used herein, the term "multiple" is intended to be synonymous with "plurality."

[0247] Additionally, where features or aspects of the disclosure are described in terms of a Markush group, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual element or subgroup of elements of the Markush group.

[0248] As will be understood by those skilled in the art, for all purposes, including in terms of providing a written description, all ranges disclosed herein also encompass any possible subranges and combinations of subranges. Any recited range can be readily recognized as fully descriptive and allowing the same range to be broken down into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed herein may be readily broken down into a lower third, middle third, upper third, etc. As will also be understood by those skilled in the art, all terms such as "up to," "at least," "more than," and "less than" refer to ranges that are inclusive of the recited number and that can be further broken down into subranges as discussed above. Finally, as will be understood by those skilled in the art, ranges include each individual element. Thus, for example, a group having 1 to 3 cells refers to a group having 1, 2, or 3 cells. Similarly, a group having 1 to 5 cells refers to a group having 1, 2, 3, 4, or 5 cells, and so on.

[0249] Furthermore, the claims should not be read as limited to the provided order or to the provided elements unless specifically so stated. Additionally, the use of the term "means for" in any claim is intended to invoke 35 U.S.C. 112, paragraph 6, or means-plus-function claim format, and any claim without the term "means for" is not so intended.

[0250] Suitable processors include, by way of example, a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), an application specific standard product (ASSP), a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), and / or a state machine.

[0251] The WTRU may be used in conjunction with hardware and / or software implemented modules such as, for example, a Software Defined Radio (SDR), and may also be implemented in other components such as a camera, a video camera module, a video phone, a speaker phone, a vibration device, a speaker, a microphone, a television transceiver, a hands-free headset, a keyboard, a Bluetooth® module, a frequency modulation (FM) radio unit, a Near Field Communication (NFC) module, an LCD display unit, an organic light emitting diode (OLED) display unit, a digital music player, a media player, a video game player module, an internet browser, and / or a wireless local area network (WLAN) or ultra wide band (UWB) module.

[0252] Although various embodiments have been described with respect to a communications system, it is contemplated that the system may be implemented in software on a microprocessor / general purpose computer (not shown). In particular embodiments, one or more of the functions of the various components may be implemented in software controlling a general purpose computer.

[0253] Additionally, although the invention is illustrated and described herein with reference to specific embodiments, the invention is not intended to be limited to the details shown. Rather, various modifications of the details can be made within the scope of the claims and their equivalents and without departing from the invention.

Claims

1. 1. A method implemented in a wireless transmit / receive unit (WTRU) for wireless communication, comprising: receiving configuration information from a network entity indicating a channel rank threshold; determining a channel rank associated with the channel measurement; selecting a type of channel state information (CSI) compression based on 1) the determined channel rank and 2) the channel rank threshold; 1. A method implemented in a wireless transmit / receive unit for wireless communication, comprising: transmitting, to the network entity, CSI and information indicating the selected CSI compression type, the CSI being associated with the channel measurements and compressed using the selected CSI compression type.

2. 2. The method of claim 1, wherein the configuration information includes an indication to enable selection of the type of CSI compression from a set of types of CSI compression, the set of types of CSI compression including full-channel-based compression and eigenvector (EV)-based compression.

3. The method of claim 2 , wherein the full-channel-based compression comprises compressing a full-channel matrix.

4. The method of claim 3 , wherein the full channel matrix is an estimated channel matrix.

5. The method of claim 2 , wherein the EV-based compression comprises compressing one or more channel eigenvectors.

6. The method of claim 5 , wherein each of the one or more channel eigenvectors is a respective eigenvector of a channel estimate.

7. The method of claim 1 , further comprising: performing CSI compression using the selected type of CSI compression.

8. The method of claim 7 , wherein the performing the CSI compression comprises compressing the CSI via an artificial intelligence / machine learning (AI / ML) model.

9. 9. The method of claim 1, wherein the selected type of CSI compression comprises: 1) full-channel-based compression; 2) eigenvector (EV)-based compression; or 3) a combination of the full-channel-based compression and the eigenvector (EV)-based compression.

10. 10. The method of claim 1, wherein the selecting the type of CSI compression comprises selecting an eigenvector (EV)-based compression based on the determined channel rank being less than the channel rank threshold.

11. 11. The method of claim 1, wherein the selecting the type of CSI compression comprises selecting full channel-based compression based on the determined channel rank being greater than or equal to the channel rank threshold.

12. The method according to any one of claims 1 to 11, wherein the type of CSI compression is selected based on one of an estimated rank, a number of computational resources, and / or an uplink feedback allocation.

13. A wireless transmit / receive unit (WTRU) for wireless communication, comprising: a circuit including a transmitter, a receiver, a processor, and a memory; receiving configuration information from a network entity indicating a channel rank threshold; determining a channel rank associated with the channel measurements; selecting a type of channel state information (CSI) compression based on 1) the determined channel rank and 2) the channel rank threshold; and a WTRU configured to transmit, to the network entity, CSI and information indicating the selected type of CSI compression, the CSI being associated with the channel measurements and compressed using the selected type of CSI compression.

14. 14. The WTRU of claim 13, wherein the configuration information includes an indication to enable selection of the type of CSI compression from a set of types of CSI compression, the set of types of CSI compression including full-channel-based compression and eigenvector (EV)-based compression.

15. The WTRU of claim 14 , wherein the full-channel-based compression includes compressing a full-channel matrix.

16. The WTRU of claim 15, wherein the full channel matrix is an estimated channel matrix.

17. The WTRU of claim 15 , wherein the EV-based compression includes compressing one or more channel eigenvectors.

18. 20. The WTRU of claim 17, wherein each of the one or more channel eigenvectors is a respective eigenvector of a channel estimate.

19. The WTRU of any one of claims 13 to 18, wherein the WTRU is further configured to perform CSI compression using the selected CSI compression type.

20. The WTRU of any one of claims 13 to 19, wherein when the WTRU performs the CSI compression, the WTRU is further configured to compress the CSI via an artificial intelligence / machine learning (AI / ML) model.

21. 21. The WTRU of claim 13, wherein the selected type of CSI compression comprises: 1) full-channel-based compression; 2) eigenvector (EV)-based compression; or 3) a combination of the full-channel-based compression and the eigenvector (EV)-based compression.

22. The WTRU of any one of claims 13 to 21, wherein the WTRU is further configured to select eigenvector (EV)-based compression based on the determined channel rank being less than the channel rank threshold.

23. The WTRU of any one of claims 13 to 22, wherein the WTRU is further configured to select full channel-based compression based on the determined channel rank being greater than or equal to the channel rank threshold.

24. The WTRU of any one of claims 13 to 22, wherein the type of CSI compression is selected based on one of an estimated rank, a number of computational resources, and / or an uplink feedback allocation.

Images