Method for multi-trp linear coded csi compression

Abstract

One or more methods, devices, and / or systems can provide techniques for linear encoding channel state information (CSI) compression for multi-transmission / reception point (mTRP). This can provide improvements to wireless communication systems, for example, by improving resilience against transmission errors and mismatches, joint or separate compression of channel matrices from different TRPs, and / or fallback to legacy CSI reporting operations in mTRP CSI compression.

Description

[0001] Cross-references to related applications This application claims the benefit of U.S. Provisional Applications Nos. 63 / 592,483, 63 / 592,489 and 63 / 592,499, all of which were filed on October 23, 2023, the contents of which are incorporated herein by reference. Background Technology

[0002] In any given wireless communication system, it can be beneficial for all entities within the system to understand the signals transmitted within the system. One approach already used in conventional systems is to transmit channel state information reports relating to the characteristics of one or more specific types of signals. Summary of the Invention

[0003] One or more methods, apparatuses, and / or systems may provide techniques for linearly coded channel state information (CS) compression for one or more multiple transmit / receive points (mTRPs). This may provide improvements to wireless communication systems, such as by improving resilience against transmission errors and mismatches, joint or separate compression of channel matrices from different TRPs, and / or backoff to conventional CSI reporting operations in mTRP CSI compression. Attached Figure Description

[0004] A more detailed understanding can be obtained from the following description, given as an example in conjunction with the accompanying drawings, wherein similar reference numerals in the figures indicate similar elements, and wherein: Figure 1A This is a system diagram illustrating an example communication system in which one or more of the disclosed embodiments may be implemented; Figure 1B The illustration shows a device that can be used according to one embodiment. Figure 1A The diagram shows a system diagram of an example wireless transmit / receive unit (WTRU) used in a communication system. Figure 1C The illustration shows a device that can be used according to one embodiment. Figure 1A The diagram shows a system diagram of an example radio access network (RAN) and an example core network (CN) used in a communication system. Figure 1D The illustration shows a device that can be used according to one embodiment. Figure 1A The diagram shows a further example RAN and a further example CN used in the communication system. Figure 2 The illustration shows an example of codebook-based precoding that utilizes feedback information; Figure 3 The illustration shows an example of a CSI report for m-TRP; Figure 4The illustration shows an example of an AI / ML framework for CSI feedback; Figure 5 An example of a linear coding CSI compression mechanism for mTRP with a separate encoder / decoder (option -a) is illustrated; Figure 6 An example of a linear coding joint CSI compression mechanism for mTRP with a joint (e.g., a single) encoder / decoder (option-b) is illustrated. Figure 7 Examples of different compression types using an autoencoder are illustrated; and Figure 8 An example process according to one or more embodiments disclosed herein is illustrated. Detailed Implementation

[0005] As discussed in this article, one or more of the following terms may be abbreviated: ACK (Acknowledgement), AE (Autoencoder), BLER (Block Error Rate), BWP (Bandwidth Portion), CAP (Channel Access Priority), CAPC (Channel Access Priority Class), CCA (Careless Channel Assessment), CCE (Control Channel Element), CE (Control Element), CG (Configuration Grant or Cell Group), CP (Cyclic Prefix), CP-OFDM (Cyclic Prefix Dependent Classic OFDM), CQI (Channel Quality Indicator), CRC (Cyclic Redundancy Check), CSI (Channel State Information), CW (Contentment Window), CWS (Contentment Window Size), CO (Channel Occupancy), DAI (Downlink Assignment Index), DCI (Downlink Control Information), DFI (Downlink Feedback Information), DG (Dynamic Grant), DL (Downlink), DM-RS (Demodulation Reference Signal), DRB (Data Radio Bearer), eLAA (Enhanced Licensed Assisted Access), FeLAA (Further Enhanced Licensed Assisted Access), HARQ (Hybrid Automatic Repeat Request), LAA (Licensed Assisted Access), LBT (Listen Before Talk), LTE (from 3GPP LTE) R8 and above (Long Term Evolution), NACK (Negative Acknowledgment), MCS (Modulation and Coding Scheme), MIMO (Multiple-Input Multiple-Output), NR (New Radio), OFDM (Orthogonal Frequency Division Multiplexing), PHY (Physical Layer), PID (Procedure ID), PO (Paging Timing), PRACH (Physical Random Access Channel), PSS (Primary Synchronization Signal), RA (Random Access or Procedure), RACH (Random Access Channel), RAR (Random Access Response), RCU (Radio Access Network Central Unit), RF (Radio Front End), RLF (Radio Link Failure), RLM (Radio Link Monitoring), RNTI (Radio Network Identifier), RO (RACH Timing), RRC (Radio Resource Control), RRM (Radio Resource Management), RS (Reference Signal), RSRP (Reference Signal Received Power), RSSI (Received Signal Strength Indicator), SDU (Serving Data Unit), SGCS (Square Generalized Cosine Similarity), SRS (Sound Reference Signal), SS (Synchronization Signal), SSS (Secondary Synchronization Signal), SWG (Switching Gap in Self-Containing Subframe), SPS (Semi-Permanent Scheduling), SUL (Supplemental Uplink), TB (Transport Block), TBS (Transport Block Size), TRP (Transmit / Receive Point), TSC (Time-Sensitive Communications), TSN (Time-Sensitive Networking), UL (Uplink), URLLC (Ultra-Reliable and Low-Latency Communications), WBWP (Wideband Width Component), WLAN (Wireless Local Area Network and related technologies in the IEEE 802.xx domain).

[0006] Figure 1AThis diagram illustrates an example communication system 100 in which one or more of the disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content (such as voice, data, video, messaging, broadcasting, etc.) to multiple wireless users. The communication system 100 enables multiple wireless users to access such content by sharing system resources (including wireless bandwidth). For example, the communication system 100 may employ one or more channel access methods, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), Single Carrier FDMA (SC-FDMA), Zero-Tail Unique Word Discrete Fourier Transform Extended OFDM (ZT-UW-DFT-S-OFDM), Unique Word OFDM (UW-OFDM), Resource Block Filtered OFDM, Filter Bank Multicarrier (FBMC), etc.

[0007] like Figure 1A As shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104, a core network (CN) 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112. Although it will be appreciated, the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d can be any type of device configured to operate and / or communicate in a wireless environment. As an example, WTRUs 102a, 102b, 102c, and 102d (any of which may be referred to as a Station (STA)) may be configured to transmit and / or receive wireless signals and may include User Equipment (UE), mobile stations, fixed or mobile subscriber units, subscription-based units, pagers, cellular phones, personal digital assistants (PDAs), smartphones, laptops, netbooks, personal computers, wireless sensors, hotspots or Mi-Fi devices, Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in industrial and / or automated processing chain scenarios), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. Any of WTRUs 102a, 102b, 102c, and 102d may be interchangeably referred to as a UE.

[0008] The communication system 100 may also include base station 114a and / or base station 114b. Each of base stations 114a and 114b may be any type of device configured to wirelessly interface with at least one of WTRUs 102a, 102b, 102c, and 102d to facilitate access to one or more communication networks, such as CN 106, the Internet 110, and / or other networks 112. As an example, base stations 114a and 114b may be any of a base transceiver station (BTS), NodeB, eNodeB (eNB), home NodeB, home eNodeB, next-generation NodeB such as gNodeB (gNB), new radio (NR) NodeB, site controller, access point (AP), wireless router, etc. Although base stations 114a and 114b are depicted as single elements, it will be understood that base stations 114a and 114b may include any number of interconnected base stations and / or network elements.

[0009] Base station 114a may be part of RAN 104, which may also include other base stations and / or network elements (not shown), such as base station controllers (BSCs), radio network controllers (RNCs), relay nodes, etc. 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 cells (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a specific geographic area for a radio service, 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 base station 114a may be divided into three sectors. Thus, in one embodiment, base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In one embodiment, base station 114a may employ multiple-input multiple-output (MIMO) technology, and multiple transceivers may be used for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in a desired spatial direction.

[0010] Base stations 114a and 114b can communicate with one or more of WTRUs 102a, 102b, 102c, and 102d via air interface 116, which can be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, millimeter wave, infrared (IR), ultraviolet (UV), visible light, etc.). Air interface 116 can be established using any suitable radio access technology (RAT).

[0011] More specifically, as noted above, the communication system 100 can be a multiple access system and can employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, base station 114a in RAN 104, and WTRUs 102a, 102b, and 102c can implement radio technologies such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which can use Wideband CDMA (WCDMA) to establish the air interface 116. WCDMA can include communication protocols such as High-Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA can include High-Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High-Speed ​​Uplink (UL) Packet Access (HSUPA).

[0012] In one embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which can use Long Term Evolution (LTE) and / or Advanced LTE (LTE-A) and / or Advanced LTE Pro (LTE-A Pro) to establish air interface 116.

[0013] In one embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as NR radio access, which can use NR to establish air interface 116.

[0014] In one embodiment, base station 114a and WTRUs 102a, 102b, and 102c can implement multiple radio access technologies. For example, base station 114a and WTRUs 102a, 102b, and 102c can jointly implement LTE radio access and NR radio access, for example, using the dual connectivity (DC) principle. Therefore, the air interface utilized by WTRUs 102a, 102b, and 102c can be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0015] In other embodiments, base station 114a and WTRUs 102a, 102b, 102c can implement the following radio technologies, such as IEEE 802.11 (i.e., WiFi), IEEE 802.16 (i.e., WiMAX), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Provisional Standard 2000 (IS-2000), Provisional Standard 95 (IS-95), Provisional Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE), GSMEDGE (GERAN), etc.

[0016] Figure 1A Base station 114b can be, for example, a wireless router, a home Node-B, a home eNode-B, or an access point, and can utilize any suitable RAT to facilitate wireless connectivity in a local area, such as a commercial area, home, vehicle, campus, industrial facility, air corridor (e.g., for drone use), road, etc. In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.11 to establish a wireless local area network (WLAN). In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, base station 114b and WTRUs 102c, 102d can utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish a picocell or femtocell. Figure 1A As shown, base station 114b may have a direct connection to Internet 110. Therefore, base station 114b may not be required to access Internet 110 via CN 106.

[0017] RAN 104 can communicate with CN 106, which can be any type of network configured to provide voice, data, application, and / or Voice over Internet Protocol (VoIP) services to one or more of WTRUs 102a, 102b, 102c, and 102d. Data can have different Quality of Service (QoS) requirements, such as different throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. CN 106 can provide call control, billing services, location-based services, prepaid calling, internet connectivity, video distribution, etc., and / or perform advanced security functions, such as user authentication. Although... Figure 1AAs not shown, but as will be understood, RAN 104 and / or CN 106 can communicate directly or indirectly with other RANs that use the same RAT as RAN 104 or a different RAT. For example, in addition to connecting to RAN 104, which can utilize NR radio technology, CN 106 can also communicate with another RAN (not shown) that uses GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0018] CN 106 may also act as a gateway for WTRUs 102a, 102b, 102c, and 102d to access PSTN 108, the Internet 110, and / or other networks 112. PSTN 108 may include a circuit-switched telephone network providing Common Old-Style Telephone Service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices using common communication protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and / or Internet Protocol (IP) from the TCP / IP Internet Protocol suite. Network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, network 112 may include another CN connected to one or more RANs, which may use the same RAT as RAN 104 or a different RAT.

[0019] Some or all of the WTRUs 102a, 102b, 102c, and 102d in communication system 100 may include multi-mode capabilities (e.g., WTRUs 102a, 102b, 102c, and 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). For example, Figure 1A The WTRU 102c shown can be configured to communicate with a base station 114a that can use cellular-based radio technology and a base station 114b that can use IEEE 802 radio technology.

[0020] Figure 1B This is a system diagram illustrating example WTRU 102. (Example:) Figure 1B As shown, WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power supply 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, etc. It will be appreciated that WTRU 102 may include any sub-combination of the above-described elements while remaining consistent with the embodiments.

[0021] Processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), any other type of integrated circuit (IC), a state machine, etc. Processor 118 may perform signal encoding, data processing, power control, input / output processing, and / or any other functions that enable WTRU 102 to operate in a wireless environment. Processor 118 may be coupled to transceiver 120, which may be coupled to transmitting / receiving element 122. Although... Figure 1B The processor 118 and transceiver 120 are depicted as separate components, but it will be understood that the processor 118 and transceiver 120 can be integrated together in an electronic package or chip.

[0022] Transmitting / receiving element 122 can be configured to transmit signals to or receive signals from a base station (e.g., base station 114a) via air interface 116. For example, in one embodiment, transmitting / receiving element 122 can be an antenna configured to transmit and / or receive RF signals. In one embodiment, transmitting / receiving element 122 can be a transmitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In yet another embodiment, transmitting / receiving element 122 can be configured to transmit and / or receive both RF and optical signals. It will be appreciated that transmitting / receiving element 122 can be configured to transmit and / or receive any combination of wireless signals.

[0023] Although the transmitting / receiving element 122 is in Figure 1B While depicted as a single element, WTRU 102 may include any number of transmitting / receiving elements 122. More specifically, WTRU 102 may employ MIMO technology. Thus, in one embodiment, WTRU 102 may include two or more transmitting / receiving elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals via air interface 116.

[0024] Transceiver 120 can be configured to modulate signals to be transmitted by transmitting / receiving element 122 and demodulate signals received by transmitting / receiving element 122. As noted above, WTRU 102 can have multi-mode capability. Thus, for example, transceiver 120 may include multiple transceivers for enabling WTRU 102 to communicate via multiple RATs (such as NR and IEEE 802.11).

[0025] The processor 118 of WTRU 102 can be coupled to the speaker / microphone 124, keypad 126, and / or display / touchpad 128 (e.g., a liquid crystal display (LCD) unit or an organic light-emitting diode (OLED) display unit), and can receive user input data from them. The processor 118 can also output user data to the speaker / microphone 124, keypad 126, and / or display / touchpad 128. Additionally, the processor 118 can access information from any type of suitable memory (such as non-removable memory 130 and / or removable memory 132), and store data in that memory. Non-removable memory 130 may include random access memory (RAM), read-only memory (ROM), hard disk, or any other type of memory storage device. Removable memory 132 may include a subscriber identity module (SIM) card, memory stick, secure digital storage (SD) card, etc. In other embodiments, processor 118 may access information from memory that is not physically located on WTRU 102 (such as on a server or home computer (not shown)) and store data in that memory.

[0026] The processor 118 can receive power from the power supply 134 and can be configured to distribute and / or control the power going to other components in the WTRU 102. The power supply 134 can be any suitable device for powering the WTRU 102. For example, the power supply 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0027] 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) about 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) via 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 understood that the WTRU 102 may acquire location information using any suitable location determination method, while remaining consistent with the embodiments.

[0028] The processor 118 may be further coupled to other peripherals 138, which may include one or more software and / or hardware modules providing additional features, functions, and / or wired or wireless connectivity. For example, peripherals 138 may include accelerometers, electronic compasses, satellite transceivers, digital cameras (for photos and / or video), Universal Serial Bus (USB) ports, vibration devices, television transceivers, hands-free headsets, Bluetooth® modules, FM radio units, digital music players, media players, video game player modules, internet browsers, virtual reality and / or augmented reality (VR / AR) devices, activity trackers, etc. Peripherals 138 may include one or more sensors. These sensors may be one or more of the following: gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors, geolocation sensors, altimeters, light sensors, touch sensors, magnetometers, barometers, gesture sensors, biometric sensors, humidity sensors, etc.

[0029] WTRU 102 may include a full-duplex radio, for which the transmission and reception of some or all signals (e.g., associated with specific subframes for both UL (e.g., for transmission) and DL (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and / or substantially eliminate self-interference via hardware (e.g., a choke) or via signal processing (e.g., a separate processor (not shown) or via processor 118). In one embodiment, WTRU 102 may include a half-duplex radio, for which the transmission and reception of some or all signals (e.g., associated with specific subframes for UL (e.g., for transmission) or DL ​​(e.g., for reception)) may be concurrent and / or simultaneous.

[0030] Figure 1C The diagram illustrates a system diagram of RAN 104 and CN 106 according to an embodiment. As noted above, RAN 104 can employ E-UTRA radio technology to communicate with WTRUs 102a, 102b, and 102c via air interface 116. RAN 104 can also communicate with CN 106.

[0031] RAN 104 may include eNode-Bs 160a, 160b, and 160c, although it will be understood that RAN 104 may include any number of eNode-Bs while remaining consistent with the embodiments. eNode-Bs 160a, 160b, and 160c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, eNode-Bs 160a, 160b, and 160c may implement MIMO technology. Therefore, eNode-B 160a may, for example, use multiple antennas to transmit radio signals to and / or receive radio signals from WTRU 102a.

[0032] Each of the eNode-B 160a, 160b, and 160c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, and user scheduling in the UL and / or DL, etc. Figure 1C As shown, eNode-B 160a, 160b, and 160c can communicate with each other via the X2 interface.

[0033] Figure 1C The CN 106 shown may include a Mobility Management Entity (MME) 162, a Serving Gateway (SGW) 164, and a Packet Data Network (PDN) Gateway (PGW) 166. Although the foregoing elements are depicted as part of CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0034] The MME 162 can connect to each of the eNode-Bs 162a, 162b, and 162c in RAN104 via the S1 interface and can act as a control node. For example, the MME 162 can be responsible for authenticating users of WTRUs 102a, 102b, and 102c, activating / deactivating bearers, and selecting a specific serving gateway during the initial attachment of WTRUs 102a, 102b, and 102c. The MME 162 can provide control plane functions for handover between RAN104 and other RANs (not shown) employing other radio technologies, such as GSM and / or WCDMA.

[0035] The SGW 164 can connect to each of the eNode Bs 160a, 160b, and 160c in RAN104 via the S1 interface. The SGW 164 can typically route and forward user data packets to / from WTRUs 102a, 102b, and 102c. The SGW 164 can perform other functions, such as anchoring the user plane during eNode-B handover, triggering paging when DL data is available for WTRUs 102a, 102b, and 102c, and managing and storing the context of WTRUs 102a, 102b, and 102c.

[0036] SGW 164 can be connected to PGW 166, which can provide WTRU 102a, 102b, 102c with access to packet-switched networks (such as Internet 110) to facilitate communication between WTRU 102a, 102b, 102c and IP-enabled devices.

[0037] CN 106 facilitates communication with other networks. For example, CN 106 can provide WTRUs 102a, 102b, and 102c with access to a circuit-switched network (such as PSTN 108) to facilitate communication between WTRUs 102a, 102b, and 102c and conventional terrestrial line communication equipment. For example, CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server), which acts as an interface between CN 106 and PSTN 108. Additionally, CN 106 can provide WTRUs 102a, 102b, and 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0038] Despite WTRU in Figures 1A to 1D While described as a wireless terminal, it is envisioned that, in some representative embodiments, such a terminal may use (e.g., temporarily or permanently) a wired communication interface with a communication network.

[0039] In a representative embodiment, the other network 112 may be a WLAN.

[0040] In an Infrastructure Basic Services Set (BSS) mode, a WLAN may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have access or an interface to a distribution system (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating outside the BSS destined for a STA can be delivered to the STA via the AP. Traffic from a STA to a destination outside the BSS can be sent to the AP for delivery to the appropriate destination. Traffic between STAs within the BSS can be sent via the AP, for example, where a source STA can send traffic to the AP, and the AP can deliver the traffic to the destination STA. Traffic between STAs within the BSS can be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic can be sent between source and destination STAs (e.g., directly between them) using a direct link setup (DLS). In some representative embodiments, the DLS may use 802.11e DLS or 802.11z Tunneled DLS (TDLS). A WLAN using the Standalone BSS (IBSS) mode may not have an access point (AP), and STAs within or using the IBSS (e.g., all STAs) can communicate directly with each other. The IBSS communication mode may sometimes be referred to as a "self-organizing" communication mode in this document.

[0041] When using 802.11ac infrastructure operation mode or a similar operation mode, the AP can transmit beacons on a fixed channel, such as a primary channel. The primary channel can be of fixed width (e.g., a 20 MHz bandwidth) or dynamically configured. The primary channel can be the operating channel of the BSS and can be used by STAs to establish connections with the AP. In some representative embodiments, Carrier Sense Multiple Access (CSMA / CA) with collision avoidance can be implemented, for example, in an 802.11 system. For CSMA / CA, STAs including the AP (e.g., each STA) can sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, that STA can back off. A STA (e.g., only one station) can transmit at any given time within a given BSS.

[0042] High-throughput (HT) STAs can communicate using a 40MHz wide channel, for example, by combining a primary 20MHz channel with adjacent or non-adjacent 20MHz channels to form a 40MHz wide channel.

[0043] Very High Throughput (VHT) STAs can support channels with widths of 20MHz, 40MHz, 80MHz, and / or 160MHz. 40MHz and / or 80MHz channels can be formed by combining consecutive 20MHz channels. A 160MHz channel can be formed by combining eight consecutive 20MHz channels or by combining two non-consecutive 80MHz channels (which can be referred to as an 80+80 configuration). For the 80+80 configuration, after channel coding, data is transmitted via a segment resolver that divides the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time-domain processing can be performed separately on each stream. The streams can be mapped onto two 80MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above operations for the 80+80 configuration can be reversed, and the combined data can be sent to the Media Access Control (MAC).

[0044] Operating modes below 1 GHz are supported by 802.11af and 802.11ah. The channel operating bandwidth and carrier 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 a representative embodiment, 802.11ah may support instrument-type control / machine-type communication (MTC), such as MTC devices in macro coverage areas. MTC devices may have certain capabilities, such as limited capabilities, including support for (e.g., only support) certain and / or limited bandwidths. MTC devices may include batteries with a battery life exceeding a threshold (e.g., to maintain a very long battery life).

[0045] 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 the 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 set and / or limited by the STA that supports the minimum bandwidth operating mode among all STAs operating in the BSS. In the 802.11ah example, for STAs that support (e.g., only support) the 1MHz mode (e.g., MTC type devices), the primary channel can be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings can depend on the status of the primary channel. If the primary channel is busy, for example because an STA (which only supports the 1MHz operating mode) is transmitting to the AP, all available frequency bands may be considered busy, even if most available frequency bands are still idle.

[0046] In the United States, the available frequency band for 802.11ah is from 902MHz to 928MHz. In South Korea, the available frequency band is from 917.5MHz to 923.5MHz. In Japan, the available frequency band is from 916.5MHz to 927.5MHz. Depending on the country code, the total available bandwidth for 802.11ah is 6MHz to 26MHz.

[0047] Figure 1D The diagram illustrates a system diagram of RAN 104 and CN 106 according to an embodiment. As noted above, RAN 104 may employ NR radio technology to communicate with WTRUs 102a, 102b, and 102c via air interface 116. RAN 104 may also communicate with CN 106.

[0048] RAN 104 may include gNBs 180a, 180b, and 180c, although it will be understood that RAN 104 may include any number of gNBs while remaining consistent with the embodiments. gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, gNBs 180a, 180b, and 180c may implement MIMO technology. For example, gNBs 180a and 180b may utilize beamforming to transmit signals to and / or receive signals from gNBs 180a, 180b, and 180c. Therefore, gNB 180a may, for example, use multiple antennas to transmit radio signals to and / or receive radio signals from WTRU 102a. In one embodiment, gNBs 180a, 180b, and 180c can implement carrier aggregation technology. For example, gNB 180a can transmit multiple component carriers to WTRU 102a (not shown). A subset of these component carriers can be on unlicensed spectrum, while the remaining component carriers can be on licensed spectrum. In one embodiment, gNBs 180a, 180b, and 180c can implement Cooperative Multipoint (CoMP) technology. For example, WTRU 102a can receive cooperative transmissions from gNBs 180a and 180b (and / or gNB 180c).

[0049] WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using transmissions associated with scalable digitization. For example, OFDM symbol spacing and / or OFDM subcarrier spacing can vary depending on different transmissions, different cells, and / or different portions of the radio transmission spectrum. WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using subframes of various or scalable lengths or transmission time intervals (TTIs) (e.g., containing different numbers of OFDM symbols and / or absolute times of varying durations).

[0050] gNBs 180a, 180b, and 180c can be configured to communicate with WTRUs 102a, 102b, and 102c in standalone and / or non-standalone configurations. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c without also accessing other RANs (e.g., eNode-Bs 160a, 160b, and 160c). In standalone configuration, WTRUs 102a, 102b, and 102c can utilize one or more of gNBs 180a, 180b, and 180c as mobility anchors. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using signals in unlicensed frequency bands. In a non-standalone configuration, WTRUs 102a, 102b, and 102c can communicate with / connect to gNBs 180a, 180b, and 180c, and simultaneously communicate with / connect to another RAN (such as eNode-Bs 160a, 160b, and 160c). For example, WTRUs 102a, 102b, and 102c can implement DC principles to communicate substantially simultaneously with one or more gNBs 180a, 180b, and 180c and one or more eNode-Bs 160a, 160b, and 160c. In a non-standalone configuration, eNode-B 160a, 160b, and 160c can act as mobility anchors for WTRU 102a, 102b, and 102c, and gNB 180a, 180b, and 180c can provide additional coverage and / or throughput to serve WTRU 102a, 102b, and 102c.

[0051] Each of gNBs 180a, 180b, and 180c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, network slicing support, interoperability between DC, NR, and E-UTRA, routing of user plane data to User Plane Functions (UPF) 184a and 184b, routing of control plane information to Access and Mobility Management Functions (AMF) 182a and 182b, etc. Figure 1D As shown, gNB 180a, 180b, and 180c can communicate with each other via the Xn interface.

[0052] Figure 1DThe CN 106 shown may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and may include a Data Network (DN) 185a, 185b. Although the foregoing elements are depicted as part of CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0053] AMF 182a and 182b can connect to one or more of the gNBs 180a, 180b, and 180c in RAN 104 via the N2 interface and can act as control nodes. For example, AMF 182a and 182b can be responsible for authenticating users of WTRU 102a, 102b, and 102c, supporting network slicing (e.g., handling different Protocol Data Unit (PDU) sessions with different requirements), selecting specific SMF 183a and 183b, managing registration areas, terminating Non-Access Stratum (NAS) signaling, mobility management, etc. Network slices can be used by AMF 182a and 182b to customize CN support for WTRU 102a, 102b, and 102c based on the service types utilized by WTRU 102a, 102b, and 102c. For example, different network slices can be built for different use cases, such as services that rely on Ultra Reliable Low Latency (URLLC) access, services that rely on Enhanced Massive Mobile Broadband (eMBB) access, and services for MTC access. AMF 182a and 182b can provide control plane functions for handover between RAN 104 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies, such as WiFi.

[0054] SMF 183a and 183b can connect to AMF 182a and 182b in CN 106 via the N11 interface. SMF 183a and 183b can also connect to UPF 184a and 184b in CN 106 via the N4 interface. SMF 183a and 183b can select and control UPF 184a and 184b, and configure traffic routing through UPF 184a and 184b. SMF 183a and 183b can perform other functions, such as managing and allocating WTRU IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing DL data notifications. PDU session types can be IP-based, non-IP-based, Ethernet-based, etc.

[0055] UPF 184a and 184b can connect to one or more of gNBs 180a, 180b, and 180c in RAN 104 via the N3 interface. These gNBs can provide WTRU 102a, 102b, and 102c with access to packet-switched networks (such as the Internet 110) to facilitate communication between WTRU 102a, 102b, 102c and IP-enabled devices. UPF 184a and 184b can perform other functions such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering DL packets, and providing mobility anchoring.

[0056] CN 106 can facilitate communication with other networks. For example, CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts as an interface between CN 106 and PSTN 108. Additionally, CN 106 can provide WTRUs 102a, 102b, and 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, WTRUs 102a, 102b, and 102c can connect to local DNs 185a and 185b via the N3 interface to UPFs 184a and 184b and the N6 interface between UPFs 184a and 184b and DNs 185a and 185b.

[0057] Given Figures 1A to 1D as well as Figures 1A to 1D The corresponding descriptions may be performed by one or more emulation devices (not shown) to perform one or more of the functions described herein with respect to one or more of the following: WTRU102a-d, base station 114a-b, eNode-B160a-c, MME 162, SGW 164, PGW 166, gNB180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN185a-b, and / or one or more other devices described herein. An emulation device may be one or more devices configured to emulate one or more of the functions described herein. For example, an emulation device may be used to test other devices and / or simulate network and / or WTRU functions.

[0058] Simulation devices can be designed to perform tests on one or more other devices in a laboratory environment and / or a carrier network environment. For example, the one or more simulation devices can perform one or more or all of their functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. The one or more simulation devices can perform one or more or all of their functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. Simulation devices can be directly coupled to another device for testing purposes and / or can use over-the-air wireless communication to perform tests.

[0059] The one or more simulation devices can perform one or more (including all) functions without being implemented / deployed as part of a wired and / or wireless communication network. For example, the simulation devices can be used in test scenarios in a test laboratory and / or in non-deployed (e.g., testing) wired and / or wireless communication networks to perform testing on one or more components. The one or more simulation devices can be test rigs. Direct RF coupling and / or wireless communication via RF circuitry (e.g., which may include one or more antennas) can be used by the simulation devices to transmit and / or receive data.

[0060] Figure 2 An example of codebook-based precoding utilizing feedback information is illustrated. As described herein, feedback can be interchangeable with CSI reporting; however, it is understood that feedback can be any other kind of feedback and CSI is used for illustrative purposes. Generally, feedback information may include a precoding matrix index (PMI), which may be referred to as a codeword index in the codebook shown in the figure. The codebook may include a set of precoding vectors / matrices for each rank and number of antenna ports, and each precoding vector / matrix may have its own index, allowing the receiver to inform the transmitter of the preferred precoding vector / matrix index. Codebook-based precoding may suffer from performance degradation due to its limited number of precoding vectors / matrices compared to non-codebook-based precoding. However, a major advantage of codebook-based precoding can be lower control signaling / feedback overhead. In other words, it can be beneficial if there were a way to improve performance while maintaining lower overhead with a more efficient feedback system in place.

[0061] from Figure 2 The illustration provides a better understanding of an example of codebook-based precoding that utilizes feedback information. For this example, a transmitter 211, a MIMO channel 212, and a receiver 213 may exist. At 202, one or more inputs (x...) to the transmitter 211 may exist. MI)202. At position 204, one or more outputs (Z1, ..., Z) from transmitter 211 may exist. NI ) used for transmission (e.g., via Z) NI Each antenna is mapped to a specific antenna port based on precoding. For example, the subscript MI indicates that the process is based on a precoding matrix (W=P). I The number of data streams before the transformation, which will then use the pre-encoder P I (X1, ..., Z) MI ) 202 is transformed into (Z1, ..., Z NI ) 204. The precoder P is fed back from receiver 213 to transmitter 211 on feedback channel 214. I The feedback codeword index I. In the case of transformation, this output (Z1, ..., Z) NI ) 204 can now be transmitted via multiple antennas on MIMO channel 212. At 206, there can be an input (r1, ..., rNr) that can be received at receiver 213 and transformed back to the original input (e.g., processed using a receiver based on maximum likelihood (ML) or minimum mean square error (MMSE)) (e.g., transmission on a MIMO channel).

[0062] Figure 3 The illustration shows an example of CSI reporting for one or more multiple transmit / receive points (m-TRPs). In New Radio (NR), there is a need to enhance the CSI reporting framework to support more efficient reporting setups for scenarios with multiple TRPs in Non-Coherent Joint Transmission (NCJT). For example, there could be schemes to improve CSI acquisition for FDD Coherent Joint Transmission (CJT) by enhancing the Type II CSI reporting framework.

[0063] from Figure 3 The illustration provides a better understanding of the example of a CSI report for an mTRP. For this example, there may be a first TRP 301, a second TRP 302, and a third TRP 303, as well as a WTRU 304 capable of communicating with one or more of the TRPs (mTRPs). As shown in this example, WTRU 304 can, in this case, receive a CSI reference signal from one or more of the mTRPs and send a CSI report back to the third TRP 303.

[0064] Figure 4An example of an AI / ML framework for CSI feedback is illustrated. AI / ML-based CSI feedback can use an autoencoder (AE) for CSI compression; this is a two-sided system where the estimated CSI is compressed at the WTRU side, fed back to the base station, and then decompressed at the base station. One advantage of AI / ML-based CSI compression can be the performance improvement compared to traditional CSI feedback using a similar payload size. However, a disadvantage of AI / ML-based CSI feedback may be compression errors, which can occasionally lead to a significant mismatch between the precoder computed at the WTRU and the decompressed precoder (X and X') at the network side (e.g., the base station).

[0065] from Figure 4 The illustration provides a better understanding of an example of an AI / ML framework for CSI feedback. For this example, there can be an encoder 401 (e.g., a WTRU) and a decoder 403 (e.g., a network entity, such as a base station, or other entities as described herein). As shown, there can be an input X encoded as Y, which is feedback 402 used for reporting. When feedback, existing in a compressed form Y, is received, it can be decoded by the decoder 403 to generate X'. Although the encoder is shown as a WTRU and the decoder as a network, it can be understood that these can be any entity capable of exchanging CSI information (e.g., CSI-RS, CSI-reports, etc.).

[0066] In some cases, in multi-TRP scenarios, the WTRU can access more than one TRP simultaneously. CSI compression can be used by leveraging one or more mechanisms and / or methods for compression and feedback based on the channel matrix.

[0067] Generally, multi-TRP communication requires feedback from multiple channel states to the network. Especially for CJT, the accuracy of the reconstructed channel matrix at the network can be critical. Accordingly, there is a need for efficient mechanisms to address transmission errors and mismatches in AI / ML-based CSI feedback.

[0068] The channel matrix of TRP measured by WTRU can be jointly compressed to improve compression ratio and reduce CSI feedback overhead. However, there is a need for one or more mechanisms and / or methods for AI / ML-based joint or separate compression for determining and reporting multiple channel matrices.

[0069] In some cases, WTRU can fall back from AI / ML-based CSI compression to traditional CSI reporting. In such cases, there is a need for a mechanism for falling back to traditional CSI reporting for AI / ML-based multi-TRP CSI compression.

[0070] While local CSI collection may be sufficient to perform NCJT across TRPs, for CJT, an additional co-phasing component may be required to adjust for phase mismatch across CSI-RS from different TRPs. There is a need for AI / ML-based feedback for co-phasing.

[0071] To address CSI compression issues in multi-TRPs (such as those described herein and others), there is a need for one or more techniques. For example, one or more techniques described herein can improve the reliability of AI / ML-based CSI feedback in mTRPs to address transmission errors and mismatches. For example, one or more techniques described herein can identify and indicate joint or separate compression for AI / ML-based CSI compression in mTRPs. For example, one or more techniques described herein can identify and indicate backoff to conventional CSI reporting for AI / ML-based CSI compression in mTRPs. For example, one or more techniques described herein can provide feedback on in-phase calibration via AI / ML-based compression.

[0072] As described in this article, CSI compression can refer to the use of compression of the channel matrix or processed channel matrix by AI / ML models.

[0073] CSI compression types can be joint or separate, where joint refers to joint compression of the CSI (e.g., channel matrix or eigenvector) of a set (e.g., more than one) of WTRU-TRP links, and separate refers to individual compression of the CSI feedback for each WTRU-TRP link.

[0074] As described in this article, multiple TRPs (mTRPs) can refer to the use of more than one TRP simultaneously for downlink or uplink communication of the WTRU.

[0075] As described in this article, linear coding can refer to the operation of calculating one or more linear combinations of vectors or matrices based on real-valued coefficients in a linear coding matrix.

[0076] As described in this article, an intermediate matrix can refer to a linear combination of vectors or matrices.

[0077] As described herein, mismatch can refer to the difference (e.g., a significant difference) between the input of the autoencoder at the WTRU side and the output of the autoencoder at the network side (e.g., which may degrade the performance of communication between the WTRU and the network).

[0078] The terms channel matrix and channel response matrix can be used interchangeably in this article.

[0079] In-phase calibration or phase offset can refer to the additional CSI component that includes the phase offset between different TRPs.

[0080] The rollback described in this article can refer to the use of traditional CSI reporting techniques rather than AI / ML-based techniques.

[0081] Generally, techniques and solutions for addressing the problem of CSI compression in multi-TRP communication can have one or more advantages.

[0082] For example, a first set of advantages may include improved resilience to mismatches and transmission errors through the introduction of linearly coded CSI compression and decompression of the channel matrix. In this scheme, the additional CSI report reduces the mismatch between the input and output of the CSI compression / decompression mechanism. Furthermore, the additional CSI report helps recover any lost or incorrectly decoded CSI reports in the event of transmission errors.

[0083] For example, a second set of advantages could include more efficient compression and feedback of CSI via joint compression of channel matrices from different TRPs. In this scheme, the WTRU can group the channel matrices according to their correlation levels and jointly compress the correlated matrices to reduce CSI feedback overhead.

[0084] For example, a third set of advantages could include an efficient mechanism for reverting to legacy operation. In this scheme, the WTRU could receive an indication to revert to legacy operation or determine to revert to legacy operation to prevent significant performance degradation or to meet certain criteria for efficient operation for CSI reporting.

[0085] In some cases, linear coding CSI compression for mTRP may exist.

[0086] WTRU can receive configurations for linearly encoded CSI compression for mTRP.

[0087] The WTRU can receive configuration information for performing linear encoded CSI compression (e.g., via DCI, MAC CE, or RRC in one or more messages). The configuration information may include information related to one or more parameters.

[0088] For example, configuration information may include a set of linear coding matrices. The WTRU can receive the set of linear coding matrices (codebook) to select a linear coding matrix. The WTRU can use the measured channel matrix from the TRP-WTRU connection and the selected linear coding matrix to compute a new matrix.

[0089] For example, configuration information may include the number of TRPs (e.g., M). The WTRU can receive the number of TRPs and determine the number of channel measurement results and CSI reports. The number of TRPs determines the dimension of the linear coding matrix.

[0090] For example, configuration information can include the priority of the TRP-WTRU connection. The TRP-WTRU link can be assigned a priority by the NW. If the WTRU receives the priority of the TRP-WTRU link, the WTRU can determine the linear coding matrix based on the priority.

[0091] For example, configuration information may include the number of compressed CSI feedback messages (e.g., M+k, or only k, where M is known). This parameter can have more than one scheme, and it may depend on one or more factors described herein. The WTRU may receive the number k of additional feedback messages and use this information to determine the dimensions of the linear coding matrix. In one case, M may already be configured or known, so only k needs to be configured. In another case, the WTRU may determine K based on one or more p values.

[0092] Alternatively, the configuration information may instruct the WTRU to determine and report the number k of additional CSI feedback messages, where the instruction may include one or more additional parameters.

[0093] For example, the additional parameter can be an initial value for k. WTRU can accept an initial value for k as the initial value for k during the iterative process used to determine k.

[0094] For example, an additional parameter could be a threshold for k (e.g., the maximum / minimum value of k). WTRU can receive a threshold for k (the maximum value of k) to be used in the process to determine the value of k.

[0095] For example, an additional parameter could be a threshold for the total feedback cost (e.g., maximum cost). If the WTRU receives a threshold for the total CSI feedback cost, then the WTRU can use the threshold to determine the value of k.

[0096] For example, an additional parameter could be a threshold for the block error rate. If the WTRU receives a threshold for the block error rate, then the WTRU can determine a k value that satisfies the target block error rate.

[0097] For example, an additional parameter could be a threshold regarding mismatch. Mismatch can be defined by a metric that measures the similarity between the input and output of the autoencoder (such as cosine similarity or mean squared error). If the WTRU receives a threshold regarding mismatch, then the WTRU can determine the k-value and linear encoding matrix that satisfy the target mismatch.

[0098] For example, an additional parameter could be a threshold for the difference in statistical distributions. If the WTRU receives a threshold for the difference in statistical distributions, then the WTRU can determine the k value and the linear coding matrix based on that threshold.

[0099] WTRU can have one or more processes for linear coded CSI compression for mTRP.

[0100] Figure 5 An example of a linear coding CSI compression mechanism for mTRP with a separate encoder / decoder (option -a) is illustrated.

[0101] from Figure 5 The illustration provides a better understanding of the mechanism used for linear coding CSI compression. For this example, there can be a WTRU 501 and a network entity 505 (e.g., a base station, TRP, etc.). WTRU 501 can utilize encoders (e.g., multiple, such as 503 and 504) for each CSI report. Correspondingly, network entity 505 can have decoders (e.g., multiple, such as 506 and 507) for each CSI report. In some instances, there can be CSI reports for each WTRU-to-TRP link. In some instances, there can be an additional number of CSI reports (e.g., a configured or determined k).

[0102] Figure 6 An example of a linear coding joint CSI compression mechanism (option-b) for mTRP with a joint (e.g., a single) encoder / decoder is illustrated.

[0103] from Figure 6 The diagram provides a better understanding of the mechanism used for linear coding CSI compression. For this example, there can be a WTRU 601 and a network entity 604 (e.g., a base station, TRP, etc.). WTRU 601 can utilize an encoder (e.g., one, such as 603) for all CSI reports. Parallel interchangeably, network entity 604 can have a decoder (e.g., one, such as 605) for all CSI reports. In some instances, there can be CSI reports for each WTRU-to-TRP link. In some instances, there can be an additional number of CSI reports (e.g., a configured or determined k).

[0104] exist Figure 5 The document provides a high-level representation of a linear coding CSI compression mechanism for mTRP with a separate encoder / decoder (option -a), in which... H m , m = 1: M This represents the channel matrix of the m-th TRP to WTRU link; Xn , n = 1: N This represents the intermediate channel matrix (e.g., the processed channel matrix of a linear combination of channel matrices). Y n , n = 1: N This represents the compressed intermediate channel matrix; , n = 1: N Represents the decompressed intermediate matrix; and , m = 1: M This represents the recovered channel matrix. WTRU is used as the channel matrix. H m , m = 1: M and linear encoding matrix A M×N = [ a ij ]in N = M + k The function is used to calculate the intermediate matrix. X n , n = 1: N (For example, a linear combination of channel matrices). Here, k Indicates the number of additional items in the CSI report (e.g., in addition to...). M In addition to the above, in one instance of option (a), the WTRU may use a parallel encoder, and / or in another instance of option (a), the WTRU may sequentially reuse a single encoder for compression. X 1, ... X N .exist Figure 6 The document provides a high-level representation of a linear coding joint CSI compression mechanism for mTRP with a single (e.g., joint) encoder / decoder (option-b), where the WTRU generates a single compressed CSI report. Y .

[0105] For example, in one process, the WTRU receives CSI-RS from each TRP and uses the CSI-RS reference signal to estimate the channel matrix of each TRP-WTRU link.

[0106] Then, WTRU initiates the process for determining the linear encoding matrix. A M×N = [ a ij The process, in which N = M + k And among themk It is an integer greater than or equal to 0. WTRU can be configured with a set of linear coding matrices, where each linear coding matrix in the set will correspond to a certain number of TRPs and a certain number of additional CSI reports. k It is specific to a certain scenario.

[0107] The process for determining the linear coding matrix may include a first part, in which the WTRU determines the number k of additional CSI feedbacks. In one case, the WTRU may receive an indication of the number k of additional CSI feedbacks (e.g., k configured by the network). In another case, the WTRU may receive an indication for determining k based on configurations on one or more additional parameters, as disclosed herein (e.g., the network does not indicate the number k of additional CSI feedbacks, but may indicate one or more parameters that can help determine k). In one case, the one or more additional parameters may be determined from the WTRU and / or indicated indirectly or directly by the network. For example, the WTRU may determine k based on the historical average block error rate of transmissions reported by CSI and an initial value of k. If the historical average block error rate exceeds a configured threshold, then the WTRU may increment k by 1. As another example, the WTRU may determine k based on a historical mismatch metric. If the historical average mismatch (e.g., a cosine similarity measure of the input and output of the autoencoder) exceeds a configured threshold, then the WTRU may increment k by 1. In another case, the WTRU may determine k based on a configured threshold regarding k. When a threshold for the value of k is reached, WTRU can stop incrementing k. Alternatively, WTRU can determine k based on a configured threshold for total feedback overhead. WTRU can limit k such that the total number of CSI feedback reports, including k additional CSI reports, remains below the configured threshold.

[0108] The process for determining the linear coding matrix may include a second part, where, after determining k, the WTRU determines the elements of the linear coding matrix. In one case, the elements of the linear coding matrix may be determined based on an estimated mismatch metric at the WTRU for the input to the encoder. For example, if the channel matrix... H n If the distribution of the channel matrix is ​​significantly different from the distribution of the data used for training (e.g., the difference is higher than the configured threshold), then WTRU can assign higher values ​​to the channel matrix. H n The corresponding elements in the linear coding matrix. As another example, if the WTRU is equipped with a proxy decoder, then the WTRU can estimate the input and output channel matrices. H n The mismatch between the channels (e.g., cosine similarity) and if the mismatch exceeds a mismatch threshold, then WTRU can assign a higher value to the channel matrix.H n The corresponding elements in the linear coding matrix. As another example, the WTRU can determine the elements of the linear coding matrix based on the configured priority of the TRP-WTRU link. In one case, the value of the element can be determined as per H n The mismatch, statistical difference, or priority function.

[0109] In determining the linear encoding matrix A M×N Then, WTRU calculates the intermediate matrix as shown below. X n .

[0110] .

[0111] The following is about M = 3、 N = 4 provides another representation of the computation on the intermediate matrix.

[0112] .

[0113] Finally, in the case of option -a (e.g., split compression), an intermediate matrix can be provided. X n , n = 1: N As input to the encoder for split compression, to generate N = M + k A compressed CSI report. An intermediate matrix can be provided with option -b (e.g., joint compression). X n , n = 1: N As input to the encoder for joint compression, it generates a single compressed CSI report.

[0114] WTRU can send one or more feedback and / or CSI reports for linearly encoded CSI compression.

[0115] WTRU can send one or more reports after determining the linear coding matrix and compressing the CSI feedback using an autoencoder.

[0116] For example, the WTRU can report the determined linear coding matrix. The WTRU can report indices from a set of configured linear coding matrices (e.g., a codebook). An index represents a linear coding matrix that the network can use for post-processing to recover the original channel matrix. An index can occupy a fixed number of bits, determined by the size of the set of linear coding matrices (e.g., the codebook). For example, if the set size is 64, then feedback on the index of the determined linear coding matrix can occupy 8 bits. Additionally / alternatively, the WTRU can report the values ​​of the linear coding matrix directly without using an index to the codebook.

[0117] For example, the WTRU can report the number of additional CSI feedback reports. If configured by the network, the WTRU can report the number of additional CSI feedback reports. The number of CSI feedback reports can occupy a fixed number of bits, determined by the maximum allowed value of k. For example, if the maximum allowed value of k is 7, then the feedback at k can occupy 3 bits.

[0118] For example, the WTRU can report compressed CSI reports. In option -a, the WTRU reports M+k compressed intermediate matrices, obtained by a linear combination of M channel matrices using a linearly coded matrix. In option -b, the WTRU reports a single compressed CSI report obtained by jointly compressing the M+k intermediate matrices.

[0119] For example, if the TRP has an unsatisfactory return, the WTRU may report the timestamp of the received CSI-RS to the network for scheduling purposes.

[0120] The number of reports and additional CSI reports for the determined linear coding matrix can be configured semi-statically via RRC or more dynamically via MAC CE and / or DCI signaling. Compressed CSI reports can be dynamically configured via MAC CE and / or DCI signaling.

[0121] If possible Figure 5 and 6 As understood from the related descriptions, WTRU can calculate: for all TRPs, the channel matrix H m ,1≤ m ≤ M (For example, where M is the number of TRMs, and) m It is 1 to M (Index between); linear encoding matrix A M×N ; and / or intermediate channel matrix X n ( N ≥M ), as H m and A M×N The function. WTRU can feed back the compressed intermediate channel matrix. Y n ,1≤ n ≤ N as well as A M×N Compressed CSI feedback Yn (where n is between 1 and N) can be fed back in a single report or multiple CSI reports. Network entities can recover as... A M×N And decompressed The function If a certain Y n Even if lost, the network entity can still be recovered. (For example, based on one or more schemes described herein, such as, but not limited to, the following examples).

[0122] In one example, CSI feedback is generated at the WTRU for linearly encoded CSI compression of mTRP. This example illustrates the following situation: where the number of TRPs is determined by... M = 3 is given, and the total number of CSI reports is given by N = M + k = 4 of which k = 1 is given, where k = 1 is configured by the network.

[0123] For this example, it can be assumed that WTRU receives data from the set { A 1, A 2, A 3} Select the configuration for matrix A.

[0124] make .

[0125] WTRU as A and channel matrix H 1. H 2. H The intermediate matrix is ​​calculated using a function of 3, as shown below.

[0126] .

[0127] The following provides an example calculation for the intermediate matrix.

[0128] for A = A1 (If the WTRU estimate has similar mismatches for the channel matrix or the NW assignment has equal priority, then it can be selected), the intermediate matrix can be calculated as follows.

[0129] X 1= H 1.

[0130] X 2= H 2.

[0131] X 3= H 3.

[0132] X 4 = 0.33 H 1 + 0.33 H 2+ 0.33 H 3.

[0133] for A = A 2 (If the WTRU estimate is in descending order of mismatch for the channel matrix or in descending order of NW assignment priority, then it can be selected), the intermediate matrix can be calculated as follows.

[0134] X 1= H 1.

[0135] X 2= H 2.

[0136] X 3= H 3.

[0137] X 4 = 0.6 H 1 + 0.3 H 2 + 0.1 H 3.

[0138] for A = A 3 (If WTRU estimate) H 1. Having experienced significant mismatch or when H If 1 is assigned a high priority by NW, then it can be selected. The intermediate matrix can be calculated as follows.

[0139] X 1= H 1.

[0140] X 2= H 2.

[0141] X 3= H3.

[0142] X 4 = 0.9 H 1 + 0.05 H 2+ 0.05 H 3.

[0143] WTRU uses an autoencoder to compress the intermediate matrix and obtain a compressed CSI report. Y 1. Y 2. Y 3. Y 4.

[0144] At the network level, CSI can be reconfigured. When all 4 CSI responses ( Y 1. Y 2. Y 3. Y 4) Received by the network for option -a or Y When the feedback is successfully received for option -b, the network can use the autoencoder's decoder to decompress the feedback and obtain the reconstructed intermediate matrix. .

[0145] Then, as an example, the network can use the pseudo-inverse matrix of A and To reconstruct the channel matrix .

[0146] .

[0147] Where A + It is the pseudo-inverse matrix of A.

[0148] For the demonstration, it can be assumed that the recovered intermediate matrix has a mismatch based on Gaussian noise. Let ,in We can assume a Gaussian normal distribution. Choose the channel matrix.

[0149] Tables 1 and 2 present the normalized mean square error (NMSE) performance of the reconstructed channel matrix for different values ​​of A. In Table 1, the mismatch is similar for all intermediate matrices, making... ,in In Table 2, mismatch is related to... X 1 is higher than 1, making ,in ,and ,in ,in i ≠ 1. Direct decoding in both tables refers to direct use. , and To restore Thus discarding the additional intermediate matrix .

[0150] The results in Table 1 show that, except , and External use The NMSE has been improved. Furthermore, the NMSE of a given channel matrix can be further improved by selecting higher coefficients in the linear coding matrix A corresponding to that channel matrix. For example, if the WTRU is configured with a channel matrix... H If compression has a high priority (1), then WTRU can choose A3 to improve the recovered channel matrix at the network. The NMSE performance.

[0151] The results in Table 2 show the additional intermediate matrix. This can improve NMSE performance, especially if the coefficients of the linear coding matrix A are chosen appropriately. For example, if WTRU is in If the estimated mismatch is higher compared to other channel matrices during the recovery process, then using the linear coding matrix A3 will result in significantly better NMSE results compared to direct decoding. Channel A1 A2 A3 Direct Decoding -38.45 -39.41 -42.47 -37.30 -38.30 -38.03 -37.44 -37.55 -38.20 -37.61 -37.37 -37.56

[0152] Table 1: NMSE (dB) results for similar mismatches on the intermediate matrix Channel A1 A2 A3 Direct Decoding -26.72 -29.64 -34.35 -25.58 -38.09 -37.37 -37.54 -37.50 -38.14 -37.59 -37.52 -37.48 Table 2: NMSE (dB) results for different mismatches on the intermediate matrix.

[0153] When in Y 1. Y 2. Y 3. Y 4. When one of the feedbacks is missing (e.g., applicable to option -a), Y 1. Y 2. Y 3. Y The subset received by 4 can be used for reconstruction. .

[0154] assumed Y If 1 is not successfully received (e.g., CRC failure), then the network can simply reconstruct it. , and Considering network decompression and obtaining... , and Then the network can reconstruct the channel matrix as follows.

[0155] .

[0156] Where A -1 The inverse matrix of A is denoted by A(2:4, :), and A(2:4, :) is denoted by the matrix constructed using the second to fourth rows of the linear encoding matrix A.

[0157] Table 3 presents the NMSE performance of the reconstructed channel matrix for different A values ​​when the first feedback message is lost, where the mismatch is similar for all intermediate matrices, making ,in and In this case, because Y 1 was not successfully received, therefore the direct decoding method cannot recover it. If the proposed solution is used, all channel matrices can be recovered, where It may experience NMSE performance degradation compared to other channel matrices, and the degradation depends on the chosen linear coding matrix. If the WTRU determines to use the linear coding matrix A3, then the NMSE degradation becomes lower. Channel A1 A2 A3 Direct Decoding -16.61 -27.86 -35.58 NA -37.53 -37.38 -37.59 -37.50 -37.52 -37.33 -37.60 -37.48

[0158] Table 3: NMSE (dB) results for similar mismatches on the intermediate matrix in the case of loss of the first feedback message.

[0159] In one example, the WTRU can be configured with linearly encoded CSI compression for mTRP. The WTRU can perform one or more steps, such as: from M TRP estimates M One channel, determine the size ( M + k )× M The linear coding matrix is ​​used to calculate the channel matrix. M + k A linear combination, compression M + k A linear combination, and / or feedback k The determined linear coding matrix and one or more compressed CSI reports.

[0160] The WTRU can receive configuration information in one or more messages to perform linearly coded CSI compression. The configuration information may include one or more of the following: a set of linearly coded matrices; the number of TRPs (e.g., M); the priority of the TRP-to-WTRU link; the number of compressed CSI feedback reports (e.g., ...). M + k In another example, the WTRU can receive information used to determine... kThe configuration, in which the WTRU can receive (e.g., additional) configuration information related to the following: k The initial value; the number of compressed CSI feedback reports ( M + k Thresholds for: total feedback overhead; block error rate; mismatch, where mismatch can be defined by a measure of the similarity between the input and output of the autoencoder (such as cosine similarity or mean square error); and / or the difference in statistical distribution.

[0161] The WTRU can receive CSI-RS and use the CSI-RS reference signal to measure the channel response of each TRP to WTRU link for a total of M channel response matrices.

[0162] The number of additional CSI feedbacks can be determined in one or more ways. k In one instance, the WTRU can determine the historical reliability based on the CSI reports from previously launched systems. k For example, if the historical average block error rate of a transmission reported by CSI exceeds a configured threshold, then WTRU can... k Incremental. In one instance, WTRU can be determined based on historical mismatch performance. k For example, if the historical average mismatch of the autoencoder exceeds a configured threshold, then WTRU can... k Incremental. In one instance, WTRU can be determined based on... k The configured threshold or a threshold related to total feedback overhead limits the number of additional CSI feedbacks. k In one instance, WTRU can be indicated by the network as the number of additional CSI feedbacks. k .

[0163] WTRU can determine the linear coding matrix to use based on one or more of the following: the number of TRPs; the priority of the TRP-to-WTRU links; the estimated mismatch metric; and / or the statistical distribution of the channel matrix (e.g., compared to the data used in training). For example, if a channel matrix has a higher priority than another channel matrix, or if the estimated mismatch for a channel matrix is ​​high (e.g., relative to a threshold or another channel matrix), or if the distribution of the channel matrix is ​​significantly different (e.g., relative to a threshold or another channel matrix), then a higher coefficient can be assigned to the corresponding channel matrix in the supplementary CSI report (e.g., comparatively).

[0164] WTRU can be calculated based on a given linear coding matrix. M + k An intermediate matrix (e.g., M (A linear combination of the measured channel matrices).

[0165] WTRU can use an autoencoder (AE) encoder to separate and compress all intermediate matrices to generate M + k A compressed CSI report.

[0166] Additionally / alternatively, WTRU can use a single encoder to jointly compress all intermediate matrices to generate a single compressed CSI report.

[0167] WTRU can report (e.g., feedback information transmitted to the network in one or more messages) the determined linear coding matrix, the determined number of additional CSI feedback. k And one or more compressed CSI reports.

[0168] In some cases, the WTRU can determine joint or separate compression for AI / ML-based CSI feedback. The WTRU can receive configuration information used to make this determination.

[0169] WTRU can be configured with AI / ML models to support CSI compression for mTRP.

[0170] The WTRU can receive configuration for determining the type of CSI compression (such as separate or joint compression for the TRP). The determination of the compression type can be based on one or more metrics, such as the correlation between channel matrices, the location of the TRP, the speed of the WTRU, etc. (e.g., as described herein).

[0171] The WTRU can calculate the correlation between channels to determine joint or separate compression. TRP localization can help the WTRU filter out irrelevant TRPs based on its own speed and location, where the WTRU can optionally identify the line-of-sight (LOS) and non-line-of-sight (NLOS) between its current / future location and the TRP. The WTRU's speed can assist the WTRU in correcting correlation calculations that take into account feedback delays, such as when the WTRU is in high-speed motion, where, in an option, it can correct the correlation if the WTRU's speed exceeds a pre-configured threshold. Optionally, the WTRU can receive an indication of the AI / ML decoder's capabilities, such as the maximum number of supported joint compression / decompressions. In this option, the WTRU can filter a subset of the correlated matrix accordingly based on the received configuration of the AI / ML model.

[0172] The WTRU can receive configuration information (e.g., related to and / or determining the compression type) via one or more DCI fields, which may include one or more of the following: one or more thresholds regarding the correlation between the TRP and the WTRU channel; the granularity of the correlation, wherein the correlation level may be calculated at the full channel level or the sub-channel level; the location of the TRP, wherein precise positioning can assist the WTRU in estimating the correct correlation level when the WTRU is moving at a certain speed; a distance threshold for the TRP to assist the WTRU in determining the correlation between TRPs; a speed threshold that can assist the WTRU in deciding whether to require further filtering of a subset; AI / ML model capabilities, such as the number of supported joint compression / decompression inputs to be processed by the model; and / or an indication of the specific type of CSI compression to be performed (e.g., from the network).

[0173] The WTRU can determine the compression type for mTRP as described herein. One or more CSI compression types can be used, determined, or configured for the WTRU for mTRP operations, wherein: the mTRP operation may imply that the WTRU reports CSI for one or more TRPs associated with a transmission or reception for the WTRU; the first CSI compression type may be joint CSI compression of channel information for all TRPs (e.g., stacked channel matrix). H all The channel information may include, but is not limited to, the channel matrix, processed channel information (e.g., eigenvectors, channel covariance matrix, implicit channel information such as PMI, RI, CQI, L1-RSRP); the second compression type may be a subset of the TRP (e.g., { H 1, ... H n Joint CSI compression of channel information (a subset of}); and / or a third compression type may be TRP (e.g., H n CSI compression separates channel information.

[0174] Figure 7 Examples of different compression types using an autoencoder are illustrated. Different compression types using an autoencoder as shown in the illustration are possible. Here, H n Indicates TRP- n and The channel matrix is ​​as follows. As shown, there is an encoder 701, transmitted feedback 702 (e.g., generated from the encoder), and a decoder 703 that processes the feedback. In other words, CSI reports can be compressed by the encoder and decompressed by the decoder to reduce the overhead of CSI messages.

[0175] As described in this paper, joint CSI compression can be referred to as the AI / ML model, which uses the same encoder to jointly compress the channel information of multiple TRPs, and the channel information of multiple TRPs can be reconstructed at a receiver with the same decoder. Separate compression can be referred to as the AI / ML model, which separately compresses the channel information of one or more TRPs.

[0176] When channel information from one or more TRPs is associated with the cost of complexity due to larger AI / ML models, joint CSI compression may require less feedback overhead compared to separate CSI compression.

[0177] Separate CSI compression can be a simpler AI / ML model for encoding / decoding channel information per TRP individual (e.g., compared to joint compression) and requires lower complexity than joint CSI compression.

[0178] There may be trade-offs between complexity, feedback overhead, and CSI accuracy. Based on the required complexity, feedback overhead, and CSI accuracy, a CSI compression type can be used.

[0179] In one example, the WTRU can determine the CSI compression type based on measurements of one or more channel information, based on processed channel information, from one or more TRPs having one or more conditions. An example condition could be a WTRU channel condition including at least one of the following: SINR level (e.g., based on the last reported CQI), WTRU speed, measurement accuracy level, and WTRU battery level. An example condition could be a WTRU operating state including at least one of the following: RRC status (e.g., RRC connected, RRC inactive, and RRC idle), power-saving status (e.g., active time or sleep time), and the number of active WTRU panels. An example condition could be the channel information correlation level. An example condition could be the uplink CSI report payload size.

[0180] For conditions related to the correlation level of channel information, for example, the WTRU can correlate channel matrices from one or more TRPs. If the correlation level is above a threshold, the WTRU can determine a first CSI compression type (e.g., joint compression); otherwise, the WTRU can determine a second CSI compression type (e.g., separate compression). The correlation level can be calculated or determined based on one or more considerations.

[0181] For example, one consideration could be the distance between two channel matrices from two TRPs, where the distance could be a matrix distance (e.g., correlation coefficient, sine distance, cosine similarity, norm of matrix difference, Euclidean distance, etc.).

[0182] For example, one consideration could be the location of the TRPs, and the speed of the WTRU could be used to adjust the correlation level. For instance, if the WTRU speed is below a configured threshold and the distance between the two TRPs is below a configured threshold, then the WTRU can group the two channel matrices into the same subset.

[0183] Alternatively, the distance can be calculated or determined based on a processed matrix of the channel matrix (e.g., eigenvectors, covariance matrix, average covariance matrix over multiple time / frequency resources) instead of using the channel matrix.

[0184] The threshold for the relevance level can be configured by the network for WTRU. If the number of CSI compression types is greater than 2, one or more of the thresholds can be used.

[0185] For conditions related to the uplink CSI report payload size, for example, the WTRU can determine the CSI compression type based on the payload size for the CSI report. If the allocated or authorized uplink payload size is less than a threshold, the WTRU can perform or determine a first CSI compression type (e.g., joint CSI compression); and if the payload size is greater than the threshold, the WTRU can perform or determine a second CSI compression type (e.g., separate CSI compression). The payload size can be determined based on one or more of the following: uplink resource type (PUCCH or PUSCH); the number of RBs authorized, allocated, or configured for the uplink resource; the modulation order, number of layers, and / or coding rate for the uplink resource; and / or the bandwidth portion (BWP), BWP-id, carrier, or carrier-ID associated with the report.

[0186] In one example, the WTRU can be instructed to perform one of the CSI compression types via one or more of the following signals: AI / ML model pairing-ID; transport scheme; and / or explicit bits in DCI.

[0187] For example, one or more AI / ML model pair-IDs can be used, and each AI / ML model pair-ID can be associated with a CSI compression type. Based on the indicated AI / ML model pair-ID, WTRU can determine the associated CSI compression type. In the following text, AI / ML model pair-IDs can be used interchangeably with AI / ML model IDs, function IDs, AI / ML model pairs, AI / ML pairs, and AI / ML model pairs of both sides of the model.

[0188] For example, one or more transport schemes can be used, and each transport scheme can be associated with a CSI reporting configuration, where each CSI reporting configuration can have a corresponding identity. A WTRU can be indicated to have a CSI configuration identity, and the WTRU can execute its associated CSI compression type.

[0189] For example, when a WTRU is triggered to report a CSI, CSI compression can be indicated to the WTRU in the associated DCI (e.g., one or more bits in the DCI) that triggered the CSI report.

[0190] The WTRU can report the compression type of the CSI report for mTRP to the network. The WTRU can indicate whether joint compression of the entire channel matrix or the processed channel matrix was performed at the WTRU, subset-based joint compression, or separate compression. For example, the WTRU can use a two-bit field from the UCI to indicate the compression type.

[0191] For joint compression of all channel matrices, WTRU can feed back a single CSI report to the network, consisting of a single compressed (e.g., stacked) channel matrix.

[0192] For the separate compression of all channel matrices, WTRU can feed back one or more CSI reports consisting of multiple compressed channel matrices.

[0193] For subset-based joint compression of the channel matrix, the WTRU can feed back one or more CSI reports constructed based on a determined subset of the channel matrix. The WTRU can also report information related to one or more determined subsets of the channel, allowing the NW to reconstruct the channel matrix accordingly.

[0194] In one example, WTRU may report one or more of the following: the number of subsets; the identifier (e.g., index) of the TRP within each subset; and / or information related to the compression ratio of each subset.

[0195] Optionally, if the TRP has a less than ideal return, the WTRU may feed back the timestamp of the received CSI-RS to the network for scheduling purposes.

[0196] Information related to a subset of joint compression and the reported compression type can be configured semi-statically via RRC or more dynamically via MAC CE and / or DCI signaling.

[0197] In one example, the WTRU can be configured with CSI compression for mTRP. The WTRU can perform one or more actions, such as: receiving CSI-RS and estimating the channel matrix for TRP, determining a subset of the channel matrix or sub-channels for joint compression or a processed channel matrix based on metrics such as correlation, performing joint compression on channels in the subset, performing separate compression on channels not in the determined subset, and / or feeding back compressed CSI reports and subset-related information.

[0198] The WTRU can receive configuration information in one or more messages for determining the compression type (union or separation) for a TRP. The configuration information may include one or more of the following: a threshold for the correlation between the TRP and the WTRU channel; the granularity of the correlation, such as full-channel or sub-channel level correlation; a distance threshold for the TRP to assist the WTRU in determining the correlation between TRPs; and / or a velocity threshold that can assist the WTRU in determining the compression type.

[0199] The WTRU can receive CSI-RS and measure the channel for each TRP (M TRPs).

[0200] WTRU can calculate the correlation between different TRPs to the WTRU channel matrix or the processed channel matrix.

[0201] WTRU can determine the type of CSI compression for mTRP operations. If the relevance level is above a threshold, WTRU can use an AI / ML model to jointly compress all CSIs at once (e.g., H all If the correlation is below a threshold, WTRU can use an AI / ML model M times to separate and compress each CSI (e.g., H n The WTRU can compute a correlation matrix for one or more sub-channels of one or more TRP-to-WTRU channels. The WTRU can then determine, based on the correlation matrix, one or more subsets of the sub-channels and / or channel matrices to which joint compression is applicable (e.g., {...}). H 1, ... H M The WTRU can compress each of one or more of the identified subsets using joint compression (e.g., using an AI / ML model). The WTRU can also separately compress each of other sub-channels and / or channels (e.g., those not in one or more of the identified subsets).

[0202] The WTRU may send feedback indications in one or more messages regarding whether joint compression or separate compression was used. The WTRU may also send information (e.g., feedback) in one or more messages regarding one or more determined subsets of the channel and / or subchannels and the compressed CSI (e.g., one or more jointly compressed CSIs and one or more separately compressed CSIs).

[0203] In some cases, WTRU can determine to fall back to codebook-based CSI feedback for mTRP (e.g., in contrast to AI / ML compressed CSI).

[0204] The WTRU can be configured with one or more behaviors associated with fallback to codebook-based CSI feedback for multi-TRP reporting. In one example, the WTRU can be configured with rules / conditions for fallback to codebook-based CSI feedback when operating in a joint compression mode. In another example, the WTRU can be configured with rules / conditions for fallback to codebook-based CSI feedback when operating in AI / ML-based in-phase calibration compression. In yet another example, the WTRU can be configured with rules / conditions for fallback to codebook-based CSI feedback when operating in joint and / or separate compression. Possibly, the rules / conditions can be features of the current CSI compression mode. As described herein, the terms codebook-based CSI feedback and conventional CSI feedback can be used interchangeably.

[0205] In one scenario, the WTRU can be configured with one or more parameters associated with backoff to codebook-based CSI feedback for multiple TRPs.

[0206] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback based on the number of antennas per TRP. For example, the WTRU can be configured with a threshold associated with the number of antennas per TRP. For instance, the WTRU can be configured to fall back to codebook-based CSI feedback when the number of antennas per TRP falls below the configured threshold. For example, the WTRU can be configured to fall back to codebook-based CSI feedback when the number of antennas in a TRP (e.g., the TRP with the lowest number of antennas among TRPs configured for multi-TRP operations) falls below the configured threshold.

[0207] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback based on the number of TRPs. For example, the WTRU can be configured with a threshold associated with the number of TRPs applicable to multi-TRP reporting. For instance, the WTRU can be configured to fall back to codebook-based CSI feedback when the number of TRPs falls below the configured threshold.

[0208] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback based on the performance gain associated with linear coding compression and / or in-phase calibration compression. This performance gain may be derived based on intermediate KPIs such as SGCS, NMSE, phase quantization loss, etc. For example, the WTRU can be configured with a threshold associated with SGCS. For example, the WTRU can be configured to fall back to codebook-based CSI feedback when the SGCS associated with joint compression falls below the configured threshold. Similarly, the WTRU can be configured with a threshold associated with NMSE. For example, the WTRU can be configured to fall back to codebook-based CSI feedback when the NMSE associated with joint compression exceeds the configured threshold. For example, the WTRU can be configured with a threshold associated with phase quantization loss. For example, the WTRU can be configured to fall back to codebook-based CSI feedback when the phase quantization loss associated with joint compression exceeds the configured threshold.

[0209] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback based on reporting overhead. For example, the WTRU can be configured with a threshold associated with the reporting overhead. This reporting overhead may be derived based on the number of payload bits required for CSI feedback. For instance, the WTRU can be configured to fall back to codebook-based CSI feedback when the overhead associated with joint compression becomes above the configured threshold.

[0210] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback based on the configured reporting resources. For example, the WTRU can be configured with different reporting resources. These different reporting resources may be associated with different payload sizes, periodicity, reliability, etc. In one instance, each reporting resource can be associated with a different CSI reporting method. For example, the WTRU can be configured to fall back to codebook-based CSI feedback when the triggered CSI feedback targets a CSI reporting resource associated with codebook-based CSI feedback.

[0211] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback upon receiving an implicit or explicit indication from the network. For example, the explicit indication could be carried in the DCI. Such an explicit indication could be an aperiodic CSI request.

[0212] In one scenario, the WTRU can be configured to fall back to codebook-based CSI feedback according to applicable conditions pre-configured for the AI / ML model used for joint compression and / or in-phase calibration compression. For example, applicable conditions can be configured as one or more of the following: base station, cell, region, TRP group, carrier frequency, bandwidth, BWP, RSRP, SNR, SINR, CQI, antenna port layout, model ID, pairing ID, etc. For example, the WTRU can be configured to monitor changes in applicable conditions. For example, the WTRU can be configured to select a CSI feedback mechanism based on observed applicable conditions. This selection may include falling back to codebook-based CSI feedback when the observed conditions do not match the applicable conditions configured for joint compression and / or in-phase calibration compression.

[0213] WTRU can determine to fall back to a conventional (e.g., non-AI / ML) process based on the fact that a condition is no longer met. This condition can be related to a context in which an AI / ML model "applicable" in one scenario is no longer applicable in another. The AI / ML model can include any one or more of the following: one or more autoencoders at the WTRU for CSI compression, one or more autoencoders at the WTRU for compressing in-phase calibration information, and / or a corresponding decoder at the base station (e.g., for reconstructing CSI). One or more conditions can exist that could cause the WTRU to fall back to a conventional mechanism, as described herein.

[0214] For example, a condition could be an internal condition of the WTRU (e.g., computing / processing power, memory, battery, storage capacity, etc.). For instance, the WTRU could determine the subset of TRPs to fall back to based on the availability of its computing resources.

[0215] For example, a condition could be a TRP condition / configuration. For instance, when the number of antennas in a TRP falls below a threshold, the WTRU can fall back to traditional CSI feedback for that TRP. For instance, when the number of TRPs is less than a threshold, the WTRU can fall back to traditional mTRP codebook-based CSI feedback.

[0216] For example, a condition could be the configuration that the WTRU receives from the network, such as any of the conditions mentioned herein.

[0217] For example, one condition could be an instruction / command received by the WTRU from the network to switch to traditional CSI compression.

[0218] For example, a condition can be associated with performance monitoring. For instance, the WTRU can monitor the estimated performance gain for each TRP (e.g., in terms of CQI, PMI, RI, SNR, SINR, throughput) and determine rollback accordingly. For example, the WTRU can use a proxy AI / ML decoder for each TRP. In one instance, if the WTRU detects performance degradation for at least one TRP, then the WTRU can roll back to traditional CSI reporting for at least the TRPs involved.

[0219] For example, one condition could be the quantization loss of the conventional in-phase calibration report. For instance, if the quantization loss of the conventional in-phase calibration report is below a threshold, then WTRU can determine to fall back to the conventional in-phase calibration report (e.g., to save computational power).

[0220] For example, a condition could be a dependency between two or more autoencoders at the WTRU. For example, the WTRU could have more than one AE. For instance, one might be used for compressed CSI and another for compressed in-phase calibration. The WTRUs could jointly determine a fallback to conventional. In one instance, if the WTRU determines a fallback to conventional CSI reporting or receives an indication to do so, this can trigger a fallback to the conventional in-phase calibration report. In another instance, if the WTRU determines a fallback to conventional in-phase calibration reporting or receives an indication to do so, this can trigger a fallback to the conventional CSI report.

[0221] For example, one condition could be training suitability. For instance, the WTRU might be moving, and the set of conditions following the WTRU's movement (e.g., new cell / radio conditions) might no longer match the set of parameters of the AI / ML model trained on the WTRU.

[0222] For example, a condition could be certain scenarios (e.g., channel conditions, WTRU distribution, WTRU mobility level, carrier frequency, etc.). If the measured RSRP with respect to TRP is below a pre-configured threshold, the WTRU can fall back to the traditional mechanism.

[0223] For example, a condition could be certain configurations (e.g., WTRU / base station / TRP configuration, bandwidth, antenna port layout).

[0224] For example, a condition could be certain sites. For instance, training might not have taken into account certain sites / deployments. Deploying the model on sites where it might not have been trained could lead to poor model performance.

[0225] For example, one condition could be the loss of synchronization between the autoencoder and the corresponding decoder at the TRP.

[0226] Based on any one or more of the conditions described herein, WTRU can determine whether to fall back to the conventional CSI compression process, whether to fall back to the conventional CSI compression process for all TRPs or a subset of TRPs, the number and / or identity of TRPs for which it falls back to the conventional CSI compression process, and whether the fallback to the conventional process is a one-time event, or lasts for a certain duration, or continues indefinitely, or continues until the event that is triggered (e.g., if the quantization loss of the conventional in-phase calibration report exceeds a pre-configured threshold, WTRU can fall back to the AI / ML mechanism).

[0227] When falling back to codebook-based feedback (e.g., based on one or more examples described herein), the WTRU can determine the CSI feedback based on a pre-configured codebook. The WTRU can emit CSI feedback according to parameters configured for codebook-based CSI feedback. The WTRU can be configured to explicitly or implicitly indicate the type of CSI feedback included in the CSI report. For example, when falling back to codebook-based CSI feedback, the WTRU can emit a CSI report in a format corresponding to the indication of codebook-based CSI feedback. For example, the WTRU can indicate the type of CSI feedback in a first CSI section and the actual CSI feedback in a second CSI section. Possibly, the WTRU can indicate in the first CSI section that the CSI feedback in the second section is based on codebook-based CSI feedback. In one instance, the indication can be implicit. For example, the WTRU can be configured with a first reporting resource and a second reporting resource. For example, the first reporting resource can be associated with joint compression and / or in-phase calibration compression. For example, the second reporting resource can be associated with codebook-based compression. WTRU can implicitly indicate the selection / emission of codebook-based CSI feedback based on CSI feedback on a second reporting resource.

[0228] In one example, a WTRU configured with CSI compression for mTRP receives CSI-RS and estimates the channel matrix for TRP, determines backoff to conventional CSI reporting based on configured parameters, and / or feeds back CSI reports and information related to backoff for each TRP.

[0229] The WTRU can receive configuration information (e.g., in one or more messages) related to one or more parameters concerning the fallback to conventional CSI and conventional in-phase calibration reports for mTRP CSI compression. These parameters may include: a threshold regarding the number of antennas per TRP; a threshold regarding the number of TRPs; a threshold regarding performance gain; and / or a threshold regarding in-phase calibration quantization loss.

[0230] The WTRU can receive CSI-RS and measure the channel for each TRP.

[0231] WTRU can determine the type of CSI feedback for TRP.

[0232] When the number of antennas in the TRP drops below a threshold, the WTRU can fall back to traditional CSI feedback for the TRP.

[0233] WTRU can determine the subset of TRPs to fall back to based on the availability of WTRU computing resources.

[0234] When the number of TRPs is less than the threshold, WTRU can fall back to traditional mTRP codebook-based CSI feedback.

[0235] WTRU can monitor the estimated performance gain (e.g., in terms of CQI, SNR, throughput) for each TRP and determine fallback accordingly. For example, WTRU can use the agent AI / ML decoder per TRP. In one instance, if WTRU detects a performance degradation for at least one TRP, then WTRU can fall back to traditional CSI reporting for that TRP. In another instance, WTRU can determine fallback on a per-TRP basis.

[0236] If the quantization loss of the conventional in-phase calibration report is below a threshold, then WTRU can determine the fallback to the conventional in-phase calibration report (e.g., to save computational power).

[0237] A WTRU can have more than one AE. For example, one for compressed CSI and another for compressed in-phase calibration. WTRUs can jointly determine a rollback to a conventional CSI report. In one instance, if a WTRU determines a rollback to a conventional CSI report or receives an instruction to do so, this can trigger a rollback to a conventional in-phase calibration report. In another instance, if a WTRU determines a rollback to a conventional in-phase calibration report or receives an instruction to do so, this can trigger a rollback to a conventional CSI report.

[0238] WTRU can send messages (e.g., feedback) of the determined type of CSI feedback for TRP and CSI reports generated using the determined type of CSI feedback for TRP.

[0239] In some cases, WTRU can perform AI / ML-based in-phase calibration compression.

[0240] The WTRU can be configured with in-phase calibration report compression. The configuration may include one or more of the following: a set of in-phase calibration representation types, anchor TRP determination type, reconstruction accuracy parameters (e.g., reconstruction accuracy type or threshold or target accuracy), and / or feedback overhead.

[0241] The WTRU can be configured to or can determine reconstruction accuracy or its parameters. Reconstruction accuracy can be compared to a target accuracy or threshold. The target accuracy or threshold can be determined based on one or more of the following: indications from the base station (e.g., via DCI, MAC-CE, or RRC); transmission type (e.g., the WTRU can determine target accuracy based on associated transmission type, where transmission type can include at least one of the following: reliability, delay, priority, SRB, DRB, LCH, etc.); RS type (e.g., the WTRU can determine target accuracy based on the RS type or RS parameters of the TRP (such as RS mode, density, periodicity, configuration, etc.); anchor TRP; phase representation type; feedback overhead (e.g., the WTRU can determine target accuracy based on the available feedback overhead for feedback reporting); and / or the performance of previous transmissions (e.g., associated transmissions) (e.g., based on the calculated rate of HARQ-ACK, the WTRU can determine target accuracy, such as if the HARQ-ACK rate is below a certain value, the WTRU can improve the target accuracy).

[0242] WTRU can determine reconstruction accuracy by using a proxy decoder to process the coded feedback. WTRU can also predict reconstruction accuracy based on channel measurements.

[0243] WTRU can determine feedback overhead based on at least one of the following: DCI indication, feedback channel (e.g., PUSCH, PUCCH, or PSSCH), feedback resources, feedback timing, feedback priority, and / or conflict between feedback and other (higher, equal, or lower priority) feedback.

[0244] WTRU can determine the anchor TRP from the TRP group. The anchor TRP can be used as a reference TRP from which all in-phase values ​​in the TRP group can be determined.

[0245] WTRU can identify multiple TRP groups for which feedback should be provided. WTRU can identify the anchor TRP for each TRP group.

[0246] The anchor TRP determination type can be either base station indicated or WTRU determined. The WTRU can receive the anchor TRP indication from one or more of the following: DCI, RRC (re)configuration, and / or MAC CE. The anchor TRP indication can be received via one or more of the following: signaling for scheduling, feedback report configuration, and / or feedback report activation / deactivation.

[0247] The WTRU can determine the anchor TRP. The WTRU can indicate the determined anchor TRP in a feedback report (e.g., to the base station). The WTRU can determine or select a TRP as the anchor TRP based on one or more factors (e.g., for at least one feedback report).

[0248] For example, one factor could be the TRP / cell / base station ID. For instance, the WTRU might select the TRP with the highest or lowest ID as the anchor TRP.

[0249] For example, one factor could be the RS configuration associated with the TRP. For instance, WTRU selects a TRP as an anchor TRP based on the RS type or pattern, periodicity, or density associated with the TRP.

[0250] For example, one factor could be timing. For instance, the WTRU can be configured or can determine the anchor TRP selection scan mode. Based on at least one of the following: the timing of feedback reports or the TRP selection scan mode, the WTRU can determine the TRP to be used as the anchor TRP. In another example, the WTRU can select a TRP as the anchor TRP based on one or more of the following: the timing of the feedback request, the measured RS of the TRP or other TRP, the timing of the feedback report, and / or the timing of previous feedback reports.

[0251] For example, one factor could be the WTRU mobility parameters. For instance, the WTRU could select the anchor TRP based on one or more of the following: its location, its speed, and / or its direction of movement.

[0252] For example, one factor could be measurement results. For instance, the WTRU could determine the anchor TRP based on measurements on one or more RSs associated with one or more TRPs. Measurement results could include one or more of the following: RSRP, CSI (e.g., RI, CQI, PMI, LI, CRI), RSRQ, SINR, RSSI, channel occupancy, AoA, AoD, Doppler shift, Doppler spread, delay spread, and / or average delay. In another example, the WTRU could select a TRP as the anchor TRP based on in-phase measurements. In this example, the WTRU could determine in-phase measurements for multiple anchor TRP assumptions and select the anchor TRP from multiple anchor TRP assumptions based on the obtained in-phase measurements. For example, the WTRU could select an anchor TRP such that the average, minimum, or maximum phase difference is minimized or maximized, or a threshold requirement is met.

[0253] For example, one factor could be previous feedback. For instance, the WTRU could determine which TRP to use as the anchor TRP based on previous feedback or the anchor TRP. The WTRU could determine the anchor TRP for one or more feedback reports. In cases where the WTRU determines the anchor TRP for multiple feedback reports, the WTRU could report the selected anchor TRP in one feedback report, and all other feedback in the other feedback reports could be associated with the anchor TRP indicated in that one feedback report.

[0254] For example, one factor could be associated transport. For instance, the WTRU could report feedback for a specific type of transport or associated with a set of transport parameters (such as reliability, delay, priority, etc.). Based on the associated transport type or set of transport parameters, the WTRU could determine or select the TRP as the anchor TRP.

[0255] For example, one factor could be reconstruction accuracy. For instance, WTRU could select a TRP from a set of TRPs as the anchor TRP that maximizes reconstruction accuracy (e.g., compared to any other TRP in the set used as the anchor TRP). In another example, WTRU could select a TRP as the anchor TRP if it achieves the minimum required reconstruction accuracy.

[0256] For example, one factor could be feedback cost. For instance, a WTRU could select a TRP based on available feedback cost. For example, a WTRU could select a TRP that minimizes the required feedback cost. In another example, a WTRU could select a TRP that maximizes feedback accuracy for the configured feedback cost.

[0257] For example, a factor can be a prediction of any of the above (in terms of time, space, or frequency). For instance, WTRU can obtain a predicted value for any of the listed examples. The predicted value can be obtained from an AI / ML model. In one example, WTRU can predict future reconstruction errors and can select the TRP as the anchor TRP that minimizes the predicted future reconstruction errors. In another example, WTRU can predict future measurements or measurements in a second frequency band or measurements for a second TRP (e.g., based on current measurements or measurements in a first frequency band or measurements for a first TRP), and WTRU can select the TRP as the anchor TRP based on the predicted measurements.

[0258] WTRU can use any of the above methods to determine the anchor RS (e.g., CSI-RS), in which determining the anchor TRP can be considered equivalent to determining the anchor RS.

[0259] The WTRU can be configured with one or more in-phase calibration representation types. In-phase calibration representation types can include one or more of the following: (0, 360) or (0, 2). π );(cos φ , sign(sin φ )); (sin φ , sign(cos φ )); and / or (cos φ , sin φ ).in φ It is the in-phase value between the measured channels associated with the two TRPs.

[0260] WTRU can determine the in-phase calibration representation type to be used for one or more feedback reports. The determination of the in-phase representation type can be based on one or more factors described herein.

[0261] For example, one factor could be the identified or selected anchor TRP / cell.

[0262] For example, a factor could be the RS configuration associated with one or more TRPs.

[0263] For example, one factor could be timing. For instance, WTRU determines the in-phase calibration representation type based on a defined timing or timing reported in feedback.

[0264] For example, one factor could be the WTRU mobility parameters. For instance, the WTRU could select its in-phase representation type based on at least one of the following: its position, its speed, and its direction of movement.

[0265] For example, one factor could be the measurement result. For instance, WTRU can select the in-phase representation type based on channel measurements such as RSRP, CSI (e.g., RI, CQI, PMI, LI, CRI), RSRQ, SINR, RSSI, channel occupancy, AoA, AoD, Doppler shift, Doppler spread, delay spread, and average delay.

[0266] For example, one factor could be previous feedback. For instance, the selected or determined in-phase representation type could be effective for multiple consecutive feedback reports.

[0267] For example, one factor could be associated transmission. For instance, the WTRU could report feedback for a specific type of transmission or associated with a set of transmission parameters (such as reliability, delay, priority, etc.). Based on the associated transmission type or set of transmission parameters, the WTRU could determine or select the in-phase representation type.

[0268] For example, one factor could be reconstruction accuracy. For instance, WTRU can determine the reconstruction accuracy associated with one or more in-phase representation types. WTRU can select the in-phase representation type such that reconstruction accuracy is maximized. In another example, WTRU can select the in-phase representation type such that a potentially configurable threshold accuracy level is achieved.

[0269] For example, one factor could be feedback overhead. For instance, the WTRU can determine the feedback overhead associated with one or more in-phase representation types. The WTRU can select the in-phase representation type that minimizes the feedback overhead. In another example, the WTRU can select the in-phase representation type such that a potentially configurable threshold feedback overhead is implemented. The feedback overhead can be the overhead of the in-phase information alone or the total feedback overhead of the entire feedback report (e.g., including, for example, in-phase information from one or more TRPs and additional joint or separate channel information).

[0270] For example, one factor could be the priority of the in-phase representation type. For instance, WTRU can select the in-phase representation type with the highest priority that implements one or more criteria (e.g., cost threshold or accuracy threshold).

[0271] For example, a factor can be a prediction of any of the above (e.g., in terms of time, space, frequency). For example, the WTRU can select the in-phase representation type of one or more criteria to be predicted to achieve one or more of the following: measurements at a first time, in a first BW, or for a first beam.

[0272] WTRU can indicate the determined / selected anchor TRP or the determined / selected in-phase calibration representation type in the feedback report (e.g., a dedicated feedback report for indicating the selected anchor TRP or in-phase representation type, or a feedback report in which the selected anchor TRP or in-phase representation type is used to generate the feedback value).

[0273] The WTRU can calculate in-phase calibration information between the channels of two or more TRPs based on channel measurements for two or more TRPs (e.g., measurements performed on RSs associated with two or more TRPs), the identified / selected anchor TRPs, and / or the identified / selected in-phase representation type.

[0274] The WTRU can compress feedback reports (e.g., where feedback reports may include one or more of the following: in-phase information for one or more TRPs, channel measurements for one or more TRPs, and / or differential channel information for one or more TRPs), and the compression rate can be determined based on the selected in-phase representation type or its payload. Compression can be performed using an encoder (e.g., using an AI / ML autoencoder architecture), where the parameters of the AI / ML model or the model itself can be determined based on one or more of the following: the selected anchor TRP, channel measurements, and / or the selected in-phase representation type.

[0275] In one example, the WTRU can be configured with AI / ML-based in-phase calibration compression, receive CSI-RS and measure in-phase calibration, determine the in-phase calibration representation for AI / ML-based compression, determine a reference CSI-RS, and provide feedback on the compressed in-phase calibration, the type of phase representation, and the reference CSI-RS.

[0276] The WTRU can receive a configuration for performing AI / ML-based in-phase calibration compression, wherein the configuration may include: a phase representation type; an anchor (reference) TRP for in-phase calibration calculations (e.g., the WTRU can be configured to determine the anchor (reference) TRP); a threshold for the reconstruction accuracy of the in-phase calibration information; and / or a threshold for the feedback overhead of the in-phase calibration information. For the in-phase calibration representation type, these may include one or more of the following: (0, 360) or (0, 2...). π );(cos φ , sign(sin φ )); (sin φ , sign(cos φ )); and / or (cos φ , sin φ (For example, where) φ It is the in-phase value between the measured channels associated with the two TRPs.

[0277] The WTRU can receive instructions related to the anchor (reference) TRP used for in-phase calibration calculations. In some instances, if the WTRU is instructed to determine the anchor TRP, then the WTRU can determine the anchor TRP according to the measured in-phase calibration (e.g., CSI-RS). For example, the WTRU can select a CSI-RS with the lowest average phase difference to other CSI-RSs as the reference.

[0278] The WTRU can receive instructions regarding the type of phase representation to be used for compression. In some instances, if the WTRU is instructed to determine the phase representation type, then the WTRU can determine the phase representation type according to the configured accuracy target and feedback overhead. For example, if the WTRU is configured with a threshold regarding the feedback overhead, then the WTRU can determine the phase representation type regarding (cos... φ , sin φ If the cost exceeds the feedback cost threshold, then (cos) is selected. φ , sign(sin φ As another example, if WTRU is configured with a threshold regarding reconstruction accuracy, then WTRU can be configured to adjust the threshold based on (cos...) φ , sign(sin φ If the accuracy of (cos) is below the threshold for reconstruction accuracy, then (cos) is selected. φ , sin φ WTRU can use a proxy (e.g., a generic) WTRU-side decoder to measure reconstruction accuracy.

[0279] WTRU can calculate in-phase calibration information based on phase representation and anchor TRP.

[0280] WTRU can use an AE encoder to compress in-phase calibration information for in-phase calibration.

[0281] The WTRU can provide feedback on compressed in-phase calibration, the determined phase representation type, and / or the determined reference TRP (e.g., by sending one or more related messages).

[0282] Figure 8An example process according to one or more embodiments disclosed herein is illustrated. As illustrated, a method for use in a Wireless Transmitter Receiver Unit (WTRU) may exist. At 802, the WTRU may receive configuration information relating to linearly coded channel state information (CSI) compression for a plurality of Transmitter Receiver Points (TRPs). At 804, the WTRU may receive a CSI-reference signal (RS) from each of the plurality of TRPs. At 806, the WTRU may perform measurements using the CSI-RS on one or more associated channels for each of the plurality of TRPs. At 805, the WTRU may determine a linear coding matrix based on the configuration information and the measurement results of one or more associated channels for each of the plurality of TRPs. At 810, the WTRU may calculate a set of linear combinations of channel matrices based on the determined linear coding matrix and the measurement results of one or more associated channels. At 812, the WTRU may compress the set of linear combinations of channel matrices. At 814, the WTRU may transmit the compressed set of linear combinations of channel matrices and information associated with the determined linear coding matrix. In some instances, configuration information may include one or more of the following: the set of linear coding matrices, the multiple TRPs (M), the priority of the TRP-WTRU links, and / or the number of additional CSI reports. In some instances, the linear coding matrix may be further determined based on the number of additional CSI reports. In some instances, the number of additional CSI reports may be determined based on historical error rates, mismatch rates, or allowed feedback overhead. In some instances, the linear coding matrix may be further determined based on estimated mismatch metrics or the statistical distribution of the channel matrix. In some instances, information associated with the determined linear coding matrix may include the determined linear coding matrix or an index used to identify the determined linear coding matrix. In some instances, information associated with the determined linear coding matrix may include the determined number of additional CSI reports. In some instances, a set of compressed linear combinations may be performed by using multiple encoders for each combination to generate multiple CSI reports, or by using a single encoder for all combinations to generate a single CSI report.

[0283] As described herein, a higher layer can refer to one or more layers in a protocol stack or a specific sublayer within a protocol stack. A protocol stack can consist of one or more layers in a WTRU or network node (e.g., eNB, gNB, other functional entities, etc.), where each layer can have one or more sublayers. Each layer / sublayer can be responsible for one or more functions. Each layer / sublayer can communicate directly or indirectly with one or more other layers / sublayers. In some cases, these layers can be numbered, such as Layer 1, Layer 2, and Layer 3. For example, Layer 3 can consist of one or more of the following: Non-Access Stratum (NAS), Internet Protocol (IP), and / or Radio Resource Control (RRC). For example, Layer 2 can consist of one or more of the following: Packet Data Convergence Control (PDCP), Radio Link Control (RLC), and / or Media Access Control (MAC). For example, Layer 3 can consist of Physical (PHY) layer type operations. The higher the number of layers, the higher it is relative to other layers (e.g., Layer 3 is higher than Layer 1). In some cases, the examples mentioned above can be referred to as layers / sublayers themselves, regardless of the layer number, and can be called higher layers as described herein. For example, from highest to lowest, a higher layer can refer to one or more of the following layers / sublayers: NAS layer, RRC layer, PDCP layer, RLC layer, MAC layer, and / or PHY layer. Any reference to a higher layer in connection with a process, device, or system herein will refer to a layer higher than the layer described in that process, device, or system. In some cases, a reference to a higher layer herein may refer to a function or operation performed by one or more layers described herein. In some cases, a reference to a higher layer herein may refer to information sent or received by one or more layers described herein. In some cases, a reference to a higher layer herein may refer to the configuration sent and / or received by one or more layers described herein.

[0284] Although features and elements have been described above in specific combinations (e.g., embodiments, methods, examples, etc.), those skilled in the art will appreciate that each feature or element may be used individually or in any combination with other features and elements. For example, as disclosed herein, methods may be described in association with figures for illustrative purposes, and those skilled in the art will appreciate that one or more features or elements from that method may be used individually or in combination with one or more features from another method described elsewhere. The symbol “ / ” (e.g., a forward slash) may be used herein to indicate “and / or,” where, for example, “A / B” may imply “A and / or B.” As used herein, “a” and “one” and similar phrases should be interpreted as “one or more” and “at least one.” Similarly, any term beginning with the prefix “(one or more)” should be interpreted as “one or more” and “at least one.” The term “may” should be interpreted as “may, for example” or indicating that something “occurs” or “is capable of occurring.” Furthermore, the methods described herein may be implemented in computer programs, software, or firmware incorporated into 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-ROMs and digital versatile discs (DVDs)). The processor associated with the software can be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0285] As disclosed herein, “a” and “one” and similar phrases should be interpreted as “one or more” and “at least one”. Similarly, any term beginning with the prefix “(one or more)” should be interpreted as “one or more” and “at least one”. The term “may” should be interpreted as “may, for example”. The symbol “ / ” (e.g., a forward slash) as used herein means “and / or”, unless otherwise indicated, where, for example, “A / B” may imply “A and / or B”.

Claims

1. A method for use in a wireless transmit-receive unit (WTRU), the method comprising: Receive configuration information related to linearly coded channel state information (CSI) compression for multiple transmit / receive points (TRPs); Receive the CSI-reference signal (RS) from each of the multiple TRPs; Measurements are performed using CSI-RS on one or more associated channels for each of the plurality of TRPs; The linear coding matrix is ​​determined based on the configuration information and the measurement results of one or more associated channels for each of the plurality of TRPs; The set of linear combinations of channel matrices is calculated based on the determined linear coding matrix and the measurement results of one or more associated channels; A set of linear combinations of compressed channel matrices; as well as The compressed set of linear combinations of the transmission channel matrix and the information associated with the determined linear coding matrix.

2. The method of claim 1, wherein the configuration information includes one or more of the following: a set of linear coding matrices, the plurality of TRPs (M), the priority of the TRP to WTRU link, and the number of additional CSI reports.

3. The method of claim 1, wherein the linear coding matrix is ​​further determined based on the number of additional CSI reports.

4. The method of claim 3, wherein the additional number of CSI reports is determined based on historical error rate, mismatch rate, or allowed feedback overhead.

5. The method of claim 1, wherein the linear coding matrix is ​​further determined based on the estimated mismatch metric or the statistical distribution of the channel matrix.

6. The method of claim 1, wherein the information associated with the determined linear encoding matrix includes the determined linear encoding matrix or an index for identifying the determined linear encoding matrix.

7. The method of claim 1, wherein the information associated with the determined linear coding matrix includes the determined number of additional CSI reports.

8. The method of claim 1, wherein the set of compressed linear combinations is performed by using multiple encoders for each combination to generate multiple CSI reports or by using a single encoder for all combinations to generate a single CSI report.

9. A wireless transmit / receive unit (WTRU), the WTRU comprising: A processor coupled to the transceiver is configured to receive configuration information relating to linearly coded channel state information (CSI) compression for multiple transmit-receive points (TRPs); The processor and transceiver are configured to receive a CSI-reference signal (RS) from each of the plurality of TRPs. The processor and transceiver are configured to perform measurements using CSI-RS on one or more associated channels for each of the plurality of TRPs; The processor and transceiver are configured to determine a linear coding matrix based on the configuration information and measurements of one or more associated channels for each of the plurality of TRPs; The processor and transceiver are configured to calculate a set of linear combinations of channel matrices based on the determined linear coding matrix and the measurement results of the one or more associated channels; The processor and transceiver are configured as a set of linear combinations of compressed channel matrices; as well as The processor and transceiver are configured to transmit a compressed set of linear combinations of channel matrices and information associated with a determined linear coding matrix.

10. The WTRU of claim 9, wherein the configuration information includes one or more of the following: a set of linear coding matrices, the plurality of TRPs (M), the priority of the TRP-WTRU link, and the number of additional CSI reports.

11. The WTRU of claim 9, wherein the linear coding matrix is ​​further determined based on the number of additional CSI reports.

12. The WTRU of claim 11, wherein the additional number of CSI reports is determined based on historical error rate, mismatch rate, or permissible feedback overhead.

13. The WTRU of claim 9, wherein the linear coding matrix is ​​further determined based on the estimated mismatch metric or the statistical distribution of the channel matrix.

14. The WTRU of claim 9, wherein the information associated with the determined linear coding matrix includes the determined linear coding matrix or an index for identifying the determined linear coding matrix.

15. The WTRU of claim 9, wherein the information associated with the determined linear coding matrix includes the determined number of additional CSI reports.

16. The WTRU of claim 9, wherein the set of compressed linear combinations is performed by using multiple encoders for each combination to generate multiple CSI reports or by using a single encoder for all combinations to generate a single CSI report.

Images