Temporal-spatial-frequency compression of channel state information associated with multi-resolution multi-part transmissions

Abstract

This document describes systems, methods, and apparatus associated with time-space-frequency (TSF) compression utilizing multi-resolution multi-part transmission. TSF compression can be performed using fixed and / or variable part sizes (e.g., common part, specific part). For example, parameters for long-term and short-term TSF parts can be determined based on channel conditions, allocated uplink budget, and / or metric thresholds. The determined parameters can be used to compress the channel (e.g., generate TSF parts). The determined parameters can be reported.

Description

[0001] Cross-references to related applications This application claims the benefit of U.S. Provisional Application No. 63 / 552,419, filed on February 12, 2024, the entire contents of which are incorporated herein by reference. Background Technology

[0002] Mobile communications using wireless communication continue to evolve. The fifth-generation mobile radio access technology (RAT) can be referred to as 5G New Radio (NR). Previous (traditional) generation mobile communication RATs could be, for example, fourth-generation (4G) Long Term Evolution (LTE). Summary of the Invention

[0003] This document describes systems, methods, and apparatus associated with time-space-frequency (TSF) compression utilizing multi-resolution multi-part transmission. TSF compression can be performed using fixed and / or variable part sizes (e.g., common part, specific part). For example, parameters for long-term and short-term TSF parts can be determined based on channel conditions, allocated uplink budget, and / or metric thresholds. The determined parameters can be used to compress the channel (e.g., generate TSF parts). The determined parameters can be reported.

[0004] A wireless transmit / receive unit (WTRU) can perform TSF compression using multi-resolution multipart transmission. The WTRU may include a processor configured to perform one or more of the following operations: The WTRU can receive configuration information associated with TSF compression. The configuration information may include configuration parameters associated with TSF compression. The configuration parameters associated with TSF compression may include one or more of the following: the number of TSF compression CSI channel state information (CSI) portions, CSI portion sizes (e.g., minimum CSI portion size and / or maximum CSI portion size), indications (e.g., portion allocation determination and compression indication). The configuration information may include reporting configuration information. The configuration information may include conditions (e.g., channel conditions) associated with TSF portion determination. These conditions (e.g., channel conditions) may be associated with a metric threshold associated with TSF portion determination. For example, based on at least configuration information and / or measurements associated with a CSI reference signal (CSI-RS), the WTRU can determine a first TSF parameter. Based on a first measured channel parameter and / or a first lookup table, the first TSF parameter may be determined. Based on the metric threshold, a first TSP parameter may be determined. The first TSF parameter can be one or more of the following: a first size, a valid time, a first quantization parameter, etc. For example, the WTRU can determine the second TSF parameter based on at least configuration information and / or measurements associated with CSI-RS. The second TSF parameter can be determined based on a second measurement channel parameter and / or a second lookup table. The second TSF parameter can be determined based on a metric threshold. The second TSF parameter can be one or more of the following: a second size, a second quantization parameter, etc. For example, based on the first TSF parameter, the WTRU can determine the first TSF compressed CSI portion. The first TSF compressed CSI portion can be a long-term CSI portion (e.g., a common CSI portion). The first TSF parameter can be associated with a long-term CSI portion. For example, based on the second TSF parameter, the WTRU can determine the second TSF compressed CSI portion. The second TSF compressed CSI portion can be a short-term CSI portion (e.g., a specific CSI portion). The second TSF parameter can be associated with a short-term CSI portion. The WTRU can send at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter (e.g., based on report configuration information). Attached Figure Description

[0005] Figure 1A This is a system diagram illustrating an exemplary communication system that can implement one or more of the disclosed embodiments.

[0006] Figure 1B The illustration is based on an embodiment and can be used Figure 1A The diagram shows a system diagram of an exemplary wireless transmit / receive unit (WTRU) used in a communication system.

[0007] Figure 1C The illustration is based on an embodiment and can be used Figure 1A The diagram shows an exemplary radio access network (RAN) and an exemplary core network (CN) used within a communication system.

[0008] Figure 1D The illustration is based on an embodiment and can be used Figure 1A The diagram shows another exemplary RAN and another exemplary CN used within the communication system.

[0009] Figure 2 The diagram illustrates an exemplary CSI measurement setup.

[0010] Figure 3 The illustration shows an exemplary representation of training a variable-rate artificial intelligence / machine learning autoencoder model.

[0011] Figure 4 The illustration shows an exemplary AI / ML autoencoder model with a multipart latent domain, which includes a fixed-size common part and specific parts.

[0012] Figure 5 The illustration shows an exemplary AI / ML autoencoder model with a multipart latent domain, which includes a variable-size common part and specific parts.

[0013] Figure 6 The illustration shows an example of SF compression using a two-sided autoencoder model.

[0014] Figure 7 The illustration shows an example of traditional training of the AE model.

[0015] Figure 8 The illustration shows an example of AE training using a common part and a specific part, where the weights associated with the common part are updated and the specific part is frozen.

[0016] Figure 9 The illustration shows an example of AE training using common and specific parts, where the weights associated with the specific parts are updated and the weights of the common parts are frozen.

[0017] Figure 10 The illustration shows an example of training an AE model using a common encoder / decoder module.

[0018] Figure 11 The illustration shows an example of AE training utilizing common and specific parts.

[0019] Figure 12 The illustration shows an exemplary architecture of a TSF compression model with variable-size common parts and specific parts.

[0020] Figure 13 The illustration shows an example TSF type. Detailed Implementation

[0021] Figure 1A This is a diagram illustrating an exemplary communication system 100 that can implement one or more of the disclosed embodiments. The communication system 100 can 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 this content through the sharing of system resources (including wireless bandwidth). For example, the communication system 100 may employ one or more channel access methods, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), Single Carrier FDMA (SC-FDMA), Zero Tail Unique Word DFT Spread Spectrum OFDM (ZT UW DTS-s OFDM), Unique Word OFDM (UW-OFDM), Resource Block Filtered OFDM, Filter Library Set Multicarrier (FBMC), etc.

[0022] like Figure 1A As shown, the communication system 100 may include Wireless Transmit / Receive Units (WTRUs) 102a, 102b, 102c, 102d, RAN 104 / 113, CN 106 / 115, Public Switched Telephone Network (PSTN) 108, Internet 110, and other networks 112. However, it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, and 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” and / or “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 WTRU in WTRUs 102a, 102b, 102c, and 102d may be interchangeably referred to as a UE.

[0023] The communication system 100 may also include base station 114a and / or base station 114b. Each of the base stations 114a and 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, and 102d to facilitate access to one or more communication networks (such as CN 106 / 115, Internet 110, and / or other networks 112). As an example, base stations 114a and 114b may be base transceivers (BTS), Node-B, eNode B, home Node B, home eNode B, gNB, NR Node B, field controllers, access points (APs), wireless routers, 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.

[0024] Base station 114a may be part of RAN 104 / 113, 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 of a specific geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, the cell associated with base station 114a may be divided into three sectors. Therefore, in one embodiment, base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In embodiments, base station 114a may employ multiple-input multiple-output (MIMO) technology and may use multiple transceivers for each sector of the cell. For example, beamforming can be used to transmit and / or receive signals in a desired spatial direction.

[0025] Through air interface 116, base stations 114a and 114b can communicate with one or more WTRUs among WTRUs 102a, 102b, 102c, and 102d. Air interface 116 can be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). Air interface 116 can be established using any suitable radio access technology (RAT).

[0026] More specifically, as described 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 stations 114a and WTRUs 102a, 102b, and 102c in RAN 104 / 113 can implement radio technologies such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which can use Wideband CDMA (WCDMA) to establish air interfaces 115 / 116 / 117. WCDMA may include communication protocols such as High-Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High-Speed ​​UL Packet Access (HSUPA).

[0027] In the 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 LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro) to establish air interface 116.

[0028] In the embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as NR radio access, which can use New Radio (NR) to establish air interface 116.

[0029] In the embodiments, base station 114a and WTRUs 102a, 102b, and 102c can implement multiple radio access technologies. For example, using a dual connectivity (DC) principle, base station 114a and WTRUs 102a, 102b, and 102c can implement both LTE radio access and NR radio access. Therefore, the air interface used 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).

[0030] In other embodiments, base station 114a and WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., WiFi), IEEE 802.16 (i.e., WiMAX), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, transitional standard 2000 (IS-2000), transitional standard 95 (IS-95), transitional standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE), GSM EDGE (GERAN), etc.

[0031] 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 use any suitable RAT to facilitate wireless connectivity in a local area, such as a commercial location, home, vehicle, campus, industrial facility, air corridor (e.g., used by drones), road, etc. In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technology (such as IEEE 802.11) to establish a wireless local area network (WLAN). In another embodiment, base station 114b and WTRUs 102c, 102d can implement radio technology (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 use a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish a pico or femtocell. Figure 1A As shown, base station 114b may have a direct connection to Internet 110. Therefore, base station 114b may not need to access Internet 110 via CN 106 / 115.

[0032] RAN 104 / 113 can communicate with CN 106 / 115, 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 WTRUs of WTRUs 102a, 102b, 102c, and 102d. Data may have varying Quality of Service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. CN 106 / 115 can provide call control, billing services, mobile location-based services, prepaid calling, internet connectivity, video distribution, etc., and / or perform advanced security functions such as user authentication. Although not mentioned in Figure 1AAs shown, but will be understood, RAN 104 / 113 and / or CN 106 / 115 may communicate directly or indirectly with other RANs that use the same RAT as or a different RAT than RAN 104 / 113. For example, in addition to being connected to RAN 104 / 113, which may use NR radio technology, CN 106 / 115 may also communicate with another RAN (not shown) that uses GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0033] CN 106 / 115 can also serve as a gateway for WTRU 102a, 102b, 102c, 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). Internet 110 may include globally interconnected computer networks and apparatus systems 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 / 113 or a different RAT.

[0034] Some or all of the WTRUs 102a, 102b, 102c, and 102d in communication system 100 may include multi-mode capability (e.g., WTRUs 102a, 102b, 102c, and 102d may include multiple transceivers for communicating with different wireless networks on different wireless links). For example, Figure 1A The WTRU 102c shown can be configured to communicate with base station 114a, which can employ cellular-based radio technology, and with base station 114b, which can employ IEEE 802 radio technology.

[0035] Figure 1B This is a system diagram illustrating an exemplary 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 peripheral devices 138, etc. It will be understood that WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with the embodiments.

[0036] Processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. Processor 118 may perform signal decoding, 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, and transceiver 120 may be coupled to transmitting / receiving element 122. Although... Figure 1B While the processor 118 and transceiver 120 are depicted as separate components, it will be understood that the processor 118 and transceiver 120 may be integrated together in an electronic package or chip.

[0037] Transmitting / receiving element 122 may 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 may be an antenna configured to transmit and / or receive RF signals. In embodiments, for example, transmitting / receiving element 122 may be a transmitter / detector configured to transmit and / or receive IR, UV, or visible light signals. In another embodiment, transmitting / receiving element 122 may be configured to transmit and / or receive both RF and optical signals. It will be understood that transmitting / receiving element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0038] Although the transmitting / receiving element 122 is in Figure 1B While depicted as a single element, WTRU 102 may include any number of transmit / receive elements 122. More specifically, WTRU 102 may employ MIMO technology. Thus, in one embodiment, WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals via air interface 116.

[0039] 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 described above, WTRU 102 may have multi-mode capability. Therefore, transceiver 120 may include multiple transceivers to enable WTRU 102 to communicate over various RATs (such as, for example, NR and IEEE 802.11).

[0040] The processor 118 of WTRU 102 can be coupled to a speaker / microphone 124, a keypad 126, and / or a 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 the speaker / microphone 124, keypad 126, and / or display / touchpad 128. 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 said memory. Non-removable memory 130 may include random access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. Removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a 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 the data in said memory.

[0041] The processor 118 may receive power from the power supply 134 and may be configured to distribute and / or control power to other components in the WTRU 102. The power supply 134 may be any suitable device for powering the WTRU 102. For example, the power supply 134 may include one or more dry cell battery packs (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0042] Processor 118 may also be coupled to GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) about the current location of WTRU 102. In addition to or alternative to information from GPS chipset 136, WTRU 102 may receive location information via air interface 116 from base stations (e.g., base stations 114a, 114b) and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be understood that WTRU 102 may acquire location information using any suitable location determination method while remaining consistent with the embodiments.

[0043] The processor 118 may be further coupled to other peripheral devices 138, which may include one or more software and / or hardware modules providing additional features, functions, and / or wired or wireless connectivity. For example, peripheral devices 138 may include accelerometers, electronic compasses, satellite transceivers, digital cameras (for photos and / or videos), Universal Serial Bus (USB) ports, vibration devices, television transceivers, hands-free headsets, Bluetooth® modules, frequency modulation (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. Peripheral devices 138 may include one or more sensors, such as 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, and / or humidity sensors.

[0044] WTRU 102 may include a full-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with a specific subframe of both UL (e.g., for transmission) and downlink (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and / or substantially eliminate self-interference through hardware (e.g., a choke) or through signal processing (e.g., a separate processor (not shown) or through processor 118). In an embodiment, WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with a specific subframe of either UL (e.g., for transmission) or downlink (e.g., for reception)) may occur.

[0045] Figure 1C This is a system diagram illustrating RAN 104 and CN 106 according to an embodiment. As described above, RAN 104 can communicate with WTRUs 102a, 102b, and 102c via air interface 116 using E-UTRA radio technology. RAN 104 can also communicate with CN 106.

[0046] RAN 104 may include eNode-Bs 160a, 160b, and 160c, but it will be understood that RAN 104 may include any number of eNode-Bs while remaining consistent with the embodiments. Each eNode-B 160a, 160b, and 160c may 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.

[0047] 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.

[0048] Figure 1C CN 106 shown may include a Mobility Management Entity (MME) 162, a Serving Gateway (SGW) 164, and a Packet Data Network (PDN) Gateway (or PGW) 166. Although each of the foregoing elements is depicted as part of 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.

[0049] The MME 162 can be connected to each of the eNode-Bs 162a, 162b, and 162c in RAN 104 via the S1 interface and can be used as a control node. For example, the MME 162 can be responsible for authenticating users of WTRUs 102a, 102b, and 102c, activating / deactivating bearers, selecting a specific serving gateway during the initial attachment of WTRUs 102a, 102b, and 102c, etc. The MME 162 can provide control plane functions for handover between RAN 104 and other RANs (not shown) employing other radio technologies (such as GSM and / or WCDMA).

[0050] The SGW 164 can be connected to each of the eNode Bs 160a, 160b, and 160c in RAN 104 via the S1 interface. The SGW 164 can typically route and forward user packets to / from WTRUs 102a, 102b, and 102c. The SGW 164 can also perform other functions, such as anchoring the user plane during inter-eNode B handovers, 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.

[0051] SGW 164 can be connected to PGW 166, which provides 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.

[0052] CN 106 can facilitate 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 landline communication devices. For example, CN 106 may include an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server), or can communicate with said IP gateway, which serves 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.

[0053] Although WTRU is Figure 1A-1D While described as a wireless terminal, it is conceivable that in some representative embodiments, such a terminal may use (e.g., temporarily or permanently) a wired communication interface with a communication network.

[0054] In a representative embodiment, the other network 112 may be a WLAN.

[0055] A WLAN in an Infrastructure Basic Services Set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may access a Distribution System (DS) or another type of wired / wireless network, or have an interface with a Distribution System (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating outside the BSS destined for a STA can be delivered to the AP via the AP. Traffic originating from a STA destined for 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 transmitted 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 may be considered and / or referred to as peer-to-peer traffic. Using Direct Link Establishment (DLS), peer-to-peer traffic can be transmitted between source and destination STAs (e.g., directly between source and destination STAs). In some representative embodiments, the DLS may use 802.11e DLS or 802.11z Tunneled DLS (TDLS). WLANs using Standalone BSS (IBSS) mode may not have access points (APs), and STAs within the IBSS or using the IBSS (e.g., all STAs within a STA) can communicate directly with each other. IBSS communication mode may sometimes be referred to herein as "ad-hoc" communication mode.

[0056] When operating in 802.11ac infrastructure mode or a similar 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 set via signaling. The primary channel can be the operating channel of the BSS and can be used by the STA to establish a connection with the AP. In some representative embodiments, such as in an 802.11 system, carrier-sense multiple access (CSMA / CA) with collision avoidance can be implemented. For CSMA / CA, each STA (including the AP) can sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, that particular STA can back off. In a given BSS, one STA (e.g., only one station) can transmit at any given time.

[0057] For example, a high-throughput (HT) STA can communicate using a 40 MHz wide channel by combining a primary 20 MHz channel with adjacent or non-adjacent 20 MHz channels.

[0058] Very High Throughput (VHT) STAs can support channels with widths of 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz. 40 MHz and / or 80 MHz channels can be formed by combining adjacent 20 MHz channels. A 160 MHz channel can be formed by combining eight adjacent 20 MHz channels, or by combining two non-adjacent 80 MHz channels (this can be referred to as an 80+80 configuration). For the 80+80 configuration, after channel coding, data is delivered via a segment resolver, which 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 80 MHz 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).

[0059] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. In 802.11af and 802.11ah, the channel operating bandwidth and carrier are reduced 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, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support instrument-type control / machine-type communication, such as MTC devices in macro coverage areas. MTC devices may have certain capabilities, such as limited capabilities, including support (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).

[0060] WLAN systems that 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 may have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by the STA that supports the minimum bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for STAs that support (e.g., only support) the 1 MHz mode (e.g., MTC type devices), the primary channel may be 1 MHz wide even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Assignment Vector (NAV) settings may depend on the status of the primary channel. If, for example, the primary channel is busy due to a STA (that only supports the 1 MHz operating mode) transmitting to the AP, the entire available band may be considered busy even if most of the band remains idle and may be available.

[0061] In the United States, the available frequency bands for 802.11ah are from 902 MHz to 928 MHz. In South Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. Depending on the country code, the total bandwidth available for 802.11ah is 6 MHz to 26 MHz.

[0062] Figure 1D This is a system diagram illustrating RAN 113 and CN 115 according to an embodiment. As described above, RAN 113 can communicate with WTRUs 102a, 102b, and 102c via air interface 116 using NR radio technology. RAN 113 can also communicate with CN 115.

[0063] RAN 113 may include gNBs 180a, 180b, and 180c, but it will be understood that RAN 113 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 use 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 embodiments, 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 may be on unlicensed spectrum, while the remaining component carriers may be on licensed spectrum. In embodiments, gNBs 180a, 180b, and 180c can implement Coordinated Multipoint (CoMP) technology. For example, WTRU 102a can receive coordinated transmissions from gNBs 180a and 180b (and / or gNB 180c).

[0064] Using transmissions associated with scalable digital theory, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c. For example, OFDM symbol spacing and / or OFDM subcarrier spacing can vary for different transmissions, different cells, and / or different portions of the radio transmission spectrum. Using various or scalable length subframes or transmission time intervals (TTIs) (e.g., containing a varying number of OFDM symbols and / or an absolute time of continuously varying length), WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c.

[0065] 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 use one or more gNBs from 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 also 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 be used as mobility anchors for WTRU 102a, 102b, and 102c, and gNB 180a, 180b, and 180c can provide additional coverage and / or throughput for serving WTRU 102a, 102b, and 102c.

[0066] Each gNB in ​​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, dual connectivity, interoperability between 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.

[0067] Figure 1DThe CN 115 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 possibly a Data Network (DN) 185a, 185b. Although each of the foregoing elements is depicted as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0068] AMF 182a and 182b can be connected to one or more gNBs (gNBs) 180a, 180b, and 180c in RAN 113 via the N2 interface and can be used as control nodes. For example, AMF 182a and 182b can be responsible for authenticating users of WTRU 102a, 102b, and 102c, supporting network slices (e.g., handling different PDU sessions with different requirements), selecting specific SMF 183a and 183b, managing registration areas, terminating 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 type of services used by WTRU 102a, 102b, and 102c. For example, different network slices can be established for different use cases, such as services relying on Ultra Reliable Low Latency (URLLC) access, services relying on Enhanced Massive Mobile Broadband (eMBB) access, and services for Machine Type Communication (MTC) access. AMF 162 can provide control plane functionality for switching between RAN 113 and other RANs (not shown) employing other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies, such as WiFi.

[0069] SMF 183a and 183b can be connected to AMF 182a and 182b in CN 115 via the N11 interface. SMF 183a and 183b can also be connected to UPF 184a and 184b in CN 115 via the N4 interface. SMF 183a and 183b can select and control UPF 184a and 184b, and configure the routing of services through UPF 184a and 184b. SMF 183a and 183b can perform other functions, such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing downlink data notifications. PDU session types can be IP-based, non-IP-based, or Ethernet-based.

[0070] UPF 184a and 184b can be connected via the N3 interface to one or more gNBs (gNBs) 180a, 180b, and 180c in RAN 113. This provides 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 184 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 downlink packets, and providing mobility anchoring.

[0071] CN 115 can facilitate communication with other networks. For example, CN 115 may include an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server), or may communicate with said IP gateway, which serves as an interface between CN 115 and PSTN 108. Additionally, CN 115 may 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 be connected to DNs 185a and 185b via UPFs 184a and 184b, through their N3 interfaces and the N6 interface between UPFs 184a and 184b and local data networks (DNs) 185a and 185b.

[0072] Considering Figure 1A-1D and Figure 1A-1D The corresponding descriptions herein regarding WTRU 102a-d, base station 114a-b, eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF183a-b, DN 185a-b, and / or any other device(s) described herein, and / or the functions described herein, may be performed by one or more emulation devices (not shown). 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.

[0073] The simulation device may be designed to perform one or more tests on other devices in a laboratory environment and / or in a carrier network environment. For example, while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network, the one or more simulation devices may perform one or more or all of the functions to test other devices within the communication network. While being temporarily implemented / deployed as part of a wired and / or wireless communication network, the one or more simulation devices may perform one or more or all of the functions. The simulation device may be directly coupled to another device for testing purposes, and / or may use over-the-air wireless communication to perform the tests.

[0074] While not implemented / deployed as part of a wired and / or wireless communication network, the one or more simulation devices may perform the one or more functions (including all functions). For example, the simulation devices may be used in test scenarios in test laboratories and / or non-deployed (e.g., test) wired and / or wireless communication networks to perform testing of one or more components. The one or more simulation devices may be test equipment. Wireless communication via direct RF coupling and / or through an RF circuit system (e.g., the RF circuit system may include one or more antennas) may be used by the simulation devices to transmit and / or receive data.

[0075] This document describes systems, methods, and apparatus associated with time-space-frequency (TSF) compression utilizing multi-resolution multi-part transmission. TSF compression can be performed using fixed and / or variable part sizes (e.g., common part, specific part). For example, parameters for long-term and short-term TSF parts can be determined based on channel conditions, allocated uplink budget, and / or metric thresholds. The determined parameters can be used to compress the channel (e.g., generate TSF parts). The determined parameters can be reported.

[0076] A wireless transmit / receive unit (WTRU) can perform TSF compression using multi-resolution multipart transmission. The WTRU may include a processor configured to perform one or more of the following operations: The WTRU can receive configuration information associated with TSF compression. The configuration information may include configuration parameters associated with TSF compression. The configuration parameters associated with TSF compression may include one or more of the following: the number of TSF compression CSI channel state information (CSI) portions, CSI portion sizes (e.g., minimum CSI portion size and / or maximum CSI portion size), indications (e.g., portion allocation determination and compression indication). The configuration information may include reporting configuration information. The configuration information may include conditions (e.g., channel conditions) associated with TSF portion determination. These conditions (e.g., channel conditions) may be associated with a metric threshold associated with TSF portion determination. For example, based on at least configuration information and / or measurements associated with a CSI reference signal (CSI-RS), the WTRU can determine a first TSF parameter. Based on a first measured channel parameter and / or a first lookup table, the first TSF parameter may be determined. Based on the metric threshold, a first TSP parameter may be determined. The first TSF parameter can be one or more of the following: a first size, a valid time, a first quantization parameter, etc. For example, the WTRU can determine the second TSF parameter based on at least configuration information and / or measurements associated with CSI-RS. The second TSF parameter can be determined based on a second measurement channel parameter and / or a second lookup table. The second TSF parameter can be determined based on a metric threshold. The second TSF parameter can be one or more of the following: a second size, a second quantization parameter, etc. For example, based on the first TSF parameter, the WTRU can determine the first TSF compressed CSI portion. The first TSF compressed CSI portion can be a long-term CSI portion (e.g., a common CSI portion). The first TSF parameter can be associated with a long-term CSI portion. For example, based on the second TSF parameter, the WTRU can determine the second TSF compressed CSI portion. The second TSF compressed CSI portion can be a short-term CSI portion (e.g., a specific CSI portion). The second TSF parameter can be associated with a short-term CSI portion. The WTRU can send at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter (e.g., based on report configuration information).

[0077] A wireless transmit / receive unit (WTRU) can perform TSF compression using multi-resolution multi-part transmission. The WTRU can receive configuration information associated with TSF compression. The configuration information may include configuration parameters associated with TSF compression (e.g., the number of TSF compression CSI parts, the minimum size of the CSI parts, the maximum size of the CSI parts, part allocation determination, and compression indication). The configuration information may include conditions associated with TSF part determination. The conditions may include metric thresholds. The configuration information may include reporting configuration information. The WTRU can receive a Channel State Information (CSI) Reference Signal (RS). The WTRU can determine one or more TSF configuration parameters (e.g., a first TSF configuration parameter and a second TSF configuration parameter). The TSF configuration parameters may include one or more of the following: size, validity period, quantization information, etc. The TSF configuration parameters may be associated with corresponding TSF compression CSI parts. For example, based on the corresponding TSF configuration parameters, the WTRU can determine the TSF compression CSI parts. For example, based on the first TSF configuration parameter, a first TSF compression CSI part can be determined. Based on the second TSF configuration parameter, a second TSF compression CSI part can be determined. The first TSF compressed CSI portion can be a long-term CSI portion. The second TSF compressed CSI portion can be a short-term CSI portion. WTRU can report at least one TSF compressed CSI portion and its associated TSF configuration parameters.

[0078] For example, WTRU can reduce channel state information (CSI) reporting overhead by using models that can take advantage of the time-related properties of CSI (e.g., to improve compression performance) (e.g., two-sided artificial intelligence (AI) / machine learning (ML) models).

[0079] Details related to Channel State Information (CSI) reports can be provided in this article.

[0080] Channel state information may include one or more of the following: Channel Quality Index (CQI), Rank Indicator (RI), Predecoding Matrix Index (PMI), L1 channel measurement (e.g., RSRP (such as L1-RSRP) or SINR), CSI-RS Resource Indicator (CRI), SS / PBCH Block Resource Indicator (SSBRI), Layer Indicator (LI), and / or measurements (e.g., any other) taken by the WTRU from a configured reference signal (e.g., CSI-RS or SS / PBCH block or any other reference signal).

[0081] Details of the CSI reporting framework can be found in this article.

[0082] The WTRU may report CSI via the uplink control channel on the Physical Uplink Control Channel (PUCCH), or upon request from the gNB, on UL PUSCH permission. For example, depending on the configuration, CSI-RS may cover a portion of the bandwidth (BWP) (e.g., the entire bandwidth of the BWP, or a portion thereof). Within the CSI-RS bandwidth, CSI-RS can be configured in PRBs (e.g., every PRB or every other PRB). In the time domain, CSI-RS resources can be configured as periodic, semi-permanent, or aperiodic. Semi-permanent CSI-RS can resemble periodic CSI-RS. For example, resources (e.g., for semi-permanent CSI-RS) can be activated (deactivated) via signaling (e.g., via MAC CE). For example, if a resource is activated (e.g., only when the resource is activated), the WTRU may report the relevant measurements. For aperiodic CSI-RS, the WTRU may be triggered, for example, upon request in the DCI, to report the measured CSI-RS on the PUSCH. Periodic reports may be carried on the PUCCH. Semi-permanent reports can be carried on PUCCH and / or PUSCH (e.g., on PUCCH or PUSCH). For example, the reported CSI can be used by the scheduler if optimal resource blocks are allocated (e.g., possibly based on channel time-frequency selectivity), the pre-decoding matrix, beam, transmission mode, and / or a suitable MCS is determined (e.g., when optimal resource blocks are allocated (e.g., possibly based on channel time-frequency selectivity), the pre-decoding matrix, beam, transmission mode, and / or a suitable MCS is selected). The reliability, accuracy, and timeliness of WTRU CSI reports meet URLLC service requirements (e.g., are critical to meeting URLLC service requirements).

[0083] The WTRU can receive configuration information indicating (e.g., configured) CSI measurement settings. CSI measurement settings may include one or more CSI reporting settings, resource settings, and / or links between one or more CSI reporting settings and one or more resource settings. Figure 2 Exemplary configurations for CSI reporting settings, resource settings, and links are shown.

[0084] Figure 2 The diagram illustrates an exemplary CSI measurement setup.

[0085] In the CSI measurement settings, one or more of the following configuration parameters can be provided: N ≥ 1 CSI reporting settings, M ≥ 1 resource settings, and CSI measurement settings (e.g., CSI measurement settings linking N CSI reporting settings with M resource settings); CSI reporting settings (e.g., including time-domain behavior (e.g., aperiodic or periodic / semi-permanent), frequency granularity (e.g., at least for PMI and CQI), CSI report type (e.g., PMI, CQI, RI, CRI, etc.), PMI type (Type I or II), and codebook configuration (e.g., if PMI is reported). At least one of the following: resource settings (e.g., including time-domain behavior (e.g., aperiodic or periodic / semi-permanent), RS type (e.g., for channel measurement or interference measurement), S ≥ 1 resource set (e.g., where each resource set can contain Ks resources); CSI measurement settings (e.g., including at least one of (e.g., a) CSI reporting settings, (e.g., a) resource settings, reference transmission scheme settings (e.g., for CQI); frequency granularity for CSI reporting of component carriers (e.g., wideband CSI, partial band CSI, subband CSI); etc.

[0086] Details related to the use of artificial intelligence (AI) can be provided in this article.

[0087] Artificial intelligence can include behaviors exhibited by machines. These behaviors can mimic cognitive functions to sense, reason, modify, and act. The terms artificial intelligence (AI), machine learning (ML), deep learning (DL), and deep neural networks (DNN) are used interchangeably. The methods described herein are exemplified based on learning in wireless communication systems. These methods are not limited to this situation, system, or service, and are applicable to any type of transmission, communication system, and / or service.

[0088] Details related to autoencoders (AEs) can be provided in this article.

[0089] Autoencoders (AEs) can include deep neural networks (DNNs) of a class (e.g., a specific class) that appear in unsupervised machine learning settings (e.g., where a DNN-based encoder is used to transform high-dimensional data into lower-dimensional latent vectors in a non-linear manner, and the lower-dimensional latent vectors are then used to regenerate the high-dimensional data using a non-linear decoder). An encoder can be represented as... For example, where x may include high-dimensional data, and W e This can include encoder parameters. The decoder can be represented as... , where z may include a low-dimensional latent representation, and W d This can include decoder parameters. Additionally, training data can be used. The autoencoder can be trained by solving the optimization problem shown in Equation 1 below.

[0090] Equation 1 For example, using backpropagation (e.g., the backpropagation algorithm), Equation 1 can be solved (e.g., approximately solved). The trained encoder... It can be used to compress high-dimensional data, and the decoder has been trained. It can be used to decompress latent representations.

[0091] Variable-rate AEs can be trained.

[0092] For example, by modifying the training process, such as Figure 3 As shown, the AI / ML encoder-decoder model can utilize a variable-rate compression scheme. This training process can achieve a variable-size bottleneck, where the first K elements in the latent domain can be used to reconstruct the CSI with specific reconstruction performance, and from the... Start until the Elements (e.g., each additional element) can be transferred to, for example, further improve the reconstruction associated with the first K elements (e.g., where kmax may include the total number of elements in the latent space).

[0093] The training requires access to (e.g., access to) the encoder and decoder model architecture. The model can be initialized using some form of pre-training or can be trained from scratch.

[0094] Training access is available (e.g., access is required) to the training data and the loss function (e.g., the desired loss function).

[0095] The training is accessible (e.g., requires access) to a set of training masks applied in the latent space and (e.g., each) a corresponding probability. The training masks may indicate (e.g., define) the compression ratio and the granularity at which feedback can vary. (e.g., all) masks may have element (e.g., at least one element) 1, for example, allowing information to pass through.

[0096] For example, a set of training masks for a 4-dimensional latent representation could include (1,0,0,0), (1,1,0,0), (1,1,1,0), and (1,1,1,1), where each mask has an equal probability. In these masks, the first element can be 1, which indicates (e.g., regardless of the chosen mask) that the first element of the latent vector z is the most important and has the highest information content. Similarly, the second element can have the second highest probability, thus indicating (e.g., ensuring) that it is the second most information-rich element, followed by the third and fourth elements.

[0097] In (e.g., each) training iteration (e.g., for each CSI in a training batch), a mask (e.g., one) from a given set of training masks can be selected using associated probabilities. For example, the selected mask can be applied to the latent vector received as the encoder's output via element-wise multiplication between the latent vector and the mask.

[0098] Figure 3 The illustration shows an exemplary representation of training a variable-rate artificial intelligence / machine learning autoencoder model.

[0099] CSI enhancements can be applied for AI / ML use, for example, in relation to CSI compression and CSI prediction. When using AI / ML, CSI compression can be enhanced, for example, taking into account AI / ML complexities (e.g., LCM, model transfer, model generalization, etc.). In addition to spatial-frequency (SF) compression, CSI compression can also include utilizing the time-related properties of the channel (e.g., time-space-frequency (TSF) compression).

[0100] AI / ML applications for CSI compression can include models (e.g., bilateral models, such as autoencoders) that use an AI encoder model to compress space-frequency (SF) channel samples estimated at a given time into a latent representation. The compressed channel can be transmitted and / or decompressed by an AI decoder model to, for example, reconstruct the channel. For example, using TSF, compression performance (e.g., from an overhead perspective or reconstruction quality, or both) can be improved by incorporating time correlation of the channel during compression. Utilizing CSI time correlation in addition to SF compression can improve reconstruction performance for a given overhead, reduce overhead for a given performance, improve both performance and overhead relative to SF compression, and / or increase flexibility in controlling CSI feedback overhead over time.

[0101] TSF compression can be enabled and / or performed. A latent domain / representation can be structured (e.g., to enable TSF compression) to include two or more TSF sections. TSF sections may include (e.g., one) a common section that captures long-term variations or common information in a sequence of related CSI samples. TSF sections may include specific sections that capture (e.g., each) short-term variations or individual information in a sample. The common section can be used (e.g., together with the specific section) to reconstruct (e.g., anticipated) CSI samples. The specific section can be used (e.g., together with the common section) to reconstruct (e.g., anticipated) CSI samples. Common information can be (e.g., needs to be) sent periodically (e.g., once every certain number of CSI samples / reporting occasions). Specific information can be (e.g., needs to be) transmitted periodically (e.g., transmitted at each CSI reporting occasion). Implementing this structure in the latent domain reduces CSI feedback reporting signaling overhead.

[0102] Flexible TSF operations may include structuring the latent domain into two parts (e.g., a common part and a specific part). For example, the size of the common part and the specific part can be controlled and / or determined (e.g., based on conditions / measurements).

[0103] Multi-part TSF generation with controllable part sizes can be enabled. Different part sizes can be selected / determined for a given uplink overhead budget. Changing / updating the size of one or more of the parts can be triggered.

[0104] The AE latent space can be structured (e.g., to enable efficient TSF compression) into common latent portions and specific latent portions. Common latent portions capture long-term variations in a time-dependent CSI sample sequence. Short-term latent representations capture short-term variations in CSI samples (e.g., between two consecutive CSI samples). The terms long-term latent representation and / or common latent representation and / or common portion can be used interchangeably to represent long-term variations in a CSI sample sequence. The terms short-term latent representation and / or specific latent representation and / or common portion can be used interchangeably to represent short-term variations in a CSI sample sequence.

[0105] Figure 4 The illustration shows an exemplary AI / ML autoencoder model with a multipart latent domain, which includes a fixed-size common part and specific parts.

[0106] Figure 5 The illustration shows an exemplary AI / ML autoencoder model with a multipart latent domain, which includes a variable-size common part and specific parts. Figure 5 As shown, z v It can be attached (e.g., fully attached) to a common part (e.g., to increase its size to z). c + z v ) or attached to a specific part (e.g., to increase its size to z). s +z v The number of elements in z. In the example, across the common part and the specific part, z v It can be divided.

[0107] Other implementations can be considered to handle multi-size, multi-part delivery. For example, a common part can be generated using separately trained AE models with adaptive bottleneck sizes (e.g., a common AE model). Specific parts can be generated using different AE models with adaptive bottleneck sizes that can utilize the output of the common AE model (e.g., a residual AE model).

[0108] Time-space-frequency (TSF) CSI compression (e.g., utilizing multi-resolution multipart transmission) can be performed and / or enabled.

[0109] Compared to SF compression, TSF with fixed-size common and specific parts offers improved compression performance. However, a fixed-size TSF with common and specific parts may lack the flexibility to adjust the size of individual parts based on the environment. For example, a small common part and a large specific part might be used (e.g., for high-speed applications), or a large common part and a small specific part might be used (e.g., for low-speed applications) because common characteristics may decrease across samples (e.g., in high-speed applications). With TSF compression, the size of the underlying structural parts (e.g., long-term and short-term part sizes) can be controlled.

[0110] The WTRU can perform TSF-based CSI compression. For example, based on (e.g., according to) one or more of the following, the WTRU can determine one parameter (e.g., multiple parameters) of the long-term and short-term TSF portions (e.g., the size of the long-term and short-term components in the latent space and the quantization associated with each portion): channel conditions, allocated uplink budget, and / or (one or more) configured metric thresholds. The WTRU can use the determined parameters to compress the channel (e.g., generate TSF portions). The WTRU can report the determined parameters.

[0111] In the example, the WTRU may receive configuration information (e.g., configured with) one or more parameters (associated with TSF compression) to generate CSI feedback, for example, based on time-space-frequency (TSF) compression (e.g., using a two-sided model). TSF-compressed CSI may include multiple (e.g., two or more) parts. For example, TSF-compressed CSI may include a long-term / common part. The long-term / common part may capture long-term variations(s) in the relevant sample sequence. The long-term / common part may be fed back (e.g., by the WTRU) after CSI feedback transmission, for example, once every multiple CSI feedback transmissions (e.g., once every N CSI feedback transmissions, which can be configured) (e.g., periodically). The long-term / common part may be stored and / or reused in feedback reports (e.g., consecutive N feedback reports). The long-term / common part may be associated with a controllable / variable-size feedback overhead (e.g., a size range) (e.g., having a controllable / variable-size feedback overhead (e.g., a size range)). For example, TSF-compressed CSI may include a short-term / specific part. A short-term / specific segment can capture short-term variations between (one or more) pairs of samples (e.g., each pair of connected samples) in N related sample sequences. The short-term / specific segment can be sent in (e.g., each) CSI feedback transmission. The short-term / specific segment can have a controllable / variable-sized feedback overhead, such as a size range.

[0112] The WTRU may receive configuration information (e.g., associated with TSF compression), which may indicate one or more configuration parameters (e.g., TSF configuration parameters) associated with TSF compression. Configuration parameters associated with TSF compression may include one or more of the following: TSF configuration and its parameters (e.g., the number of TSF compressed CSI portions, minimum CSI portion size, maximum CSI portion size, portion allocation determination, and compression indication, etc.); conditions / parameters used for TSF portion (e.g., potential representation) determination (e.g., selection); reporting configuration information; and so on.

[0113] TSF configuration and its parameters may include one or more of the following: the number of TSF-compressed CSI parts / potential representations; the size or payload of a (e.g., each) part (e.g., long-term / common part or short-term / specific part) (e.g., minimum size or payload, maximum size or payload); part allocation determination and compression indication (e.g., a flag), where, for example, if the indication is set to 1, the WTRU can determine (e.g., each) part size / payload and use its determination to perform compression; input domain type (e.g., intrinsic values ​​(EV) versus complete CSI); and so on.

[0114] Conditions and / or parameters used for TSF latent representation / partial determination (e.g., selection) may include one or more of the following: short-term performance metric thresholds (e.g., short-term squared generalized cosine similarity (SGCS) thresholds between consecutive CSI samples in, for example, the full CSI domain); long-term performance metric thresholds (e.g., long-term SGCS thresholds between, for example, two CSI samples (e.g., one CSI sample in a TSF sequence and a first CSI sample, such as a TSF sample for which the WTRU has fed back the long-term portion) or in the latent domain between the active common portion associated with the first CSI sample in the TSF sequence (e.g., fed back by the WTRU and stored in the gNB buffer for CSI reconstruction) and the inactive common portion associated with the remaining CSI samples in the TSF sequence (e.g., determined by the WTRU but not transmitted to the gNB); combined performance metric thresholds (e.g., combined SGCS thresholds); and so on.

[0115] Report configuration information may include information associated with specific sections of a report. For example, modulation and decoding schemes (MCS) and / or quantization (e.g., quantization parameters), one or more UL resources, or one or more multi-part allocations / budgets may be configured as budgets for two or more parts (e.g., maximum budget) or budgets for each part (e.g., maximum budget).

[0116] The WTRU can receive CSI-RS transmissions. For example, based on the received CSI-RS transmissions, the channel can be estimated (e.g., measured). The measured CSI (e.g., complete channel) can be stored.

[0117] For example, based on received configuration information (e.g., indicating one or more pre-configured conditions and / or metric thresholds) and measurements (e.g., measurements associated with received CSI-RS transmissions), the WTRU can determine one or more TSF configuration parameters (e.g., first TSF parameters and / or second TSF parameters) associated with one or more TSF compressed CSI portions / potential representations. For example, based on one or more of the following conditions / measurements, the WTRU can determine one or more parameters (e.g., size, associated validity period, quantization information (e.g., quantization parameters), etc.) of a first TSF compressed CSI portion (e.g., a long-term (e.g., common) TSF compressed CSI portion). Based on the configured multi-part allocation budget and / or the configured size (e.g., maximum / minimum size), the WTRU can determine one or more parameters (e.g., first TSF parameters) of a long-term (e.g., common) TSF compressed CSI portion. Based on measured channel parameters (e.g., Doppler effect, WTRU rate), the WTRU can determine one or more parameters (e.g., a first TSF parameter) of the long-term (e.g., common) TSF compressed CSI portion. For example, based on the estimated Doppler effect and compared with a threshold, the long-term latent representation size can be determined (e.g., a high Doppler effect indicates a smaller size, and vice versa). For example, based on a defined mapping between rate ranges and size ranges, this can be used to reduce the search space for the common portion size. Based on CSI measurements (e.g., comparing the measured long-term SGCS with a configured long-term SGCS threshold), the WTRU can determine one or more parameters (e.g., a first TSF parameter) of the long-term (e.g., common) TSF compressed CSI portion. For example, if the measured long-term SGCS is greater than / less than the threshold, the common size can be changed (e.g., a change of + / - x%) relative to the currently used size. This determination can be based on x% and a predefined mapping between the measured SGCS and the threshold. Based on mapping two thresholds (e.g., long-term and short-term) to a lookup table of each part size (e.g., a dual-index lookup table), WTRU can determine one or more parameters (e.g., the first TSF parameter) of the long-term (e.g., common) TSF compressed CSI part.

[0118] For example, the WTRU can determine one or more parameters (e.g., size and quantization information) of a potential representation / part of short-term (e.g., specific) TSF compressed CSI based on one or more of the following: Based on a multi-part allocation budget (e.g., the configured multi-part allocation budget), a configured minimum / maximum allocation budget, and / or the determined long-term portion budget, the WTRU can determine one or more parameters (e.g., a second TSF parameter) of a potential representation / part of short-term (e.g., specific) TSF compressed CSI. Based on measured channel parameters (e.g., Doppler effect or WTRU rate), the WTRU can determine one or more parameters (e.g., a second TSF parameter) of a potential representation / part of short-term (e.g., specific) TSF compressed CSI. For example, a higher Doppler effect may use a larger size for the short-term / specific portion, and vice versa. For example, if the WTRU rate exceeds a threshold (e.g., a certain threshold), a certain size (e.g., a maximum size) may be used. Based on CSI measurements (e.g., comparing the measured short-term SGCS with a configured short-term SGCS threshold), the WTRU can determine one or more parameters (e.g., a second TSF parameter) of the potential representation / part of short-term (e.g., a specific) TSF compression CSI. For example, the size may be modified by + / - y% relative to a size (e.g., the current specific size) based on the difference between the measurement and the threshold. Based on a lookup table (e.g., a dual-index lookup table) that maps two thresholds (e.g., long-term and short-term) to the respective part sizes, the WTRU can determine one or more parameters (e.g., a second TSF parameter) of the potential representation / part of short-term (e.g., a specific) TSF compression CSI.

[0119] For example, based on determined TSF configuration parameters (e.g., allocations determined for each portion), the WTRU can compress CSI and / or generate TSF-compressed CSI portions (e.g., common and specific). For example, based on a first TSF parameter, a first TSF-compressed CSI portion (e.g., long-term and / or common CSI portion) can be determined. For example, based on a second TSF parameter, a second TSF-compressed CSI portion (e.g., short-term and / or specific CSI portion) can be determined.

[0120] The WTRU may report one or more TSF compressed CSI sections and / or associated section parameters. For example, the WTRU may report TSF configuration parameters (e.g., the number of sections, the allocation of each transmitted / reported section). For example, the WTRU may report TSF compressed CSI for one or more sections. For example, the WTRU may send one or more of the following: a first TSF compressed CSI section, a first TSF parameter, a second TSF compressed CSI section, or a second TSF parameter.

[0121] CSI feedback utilizing time-space-frequency (TSF) compression can be enabled and / or used. The details described herein regarding CSI feedback utilizing TSF compression may not be limited to CSI feedback and TSF, but can be applied to any delivery, reporting, measurement, etc., where the proposed structure is suitable (e.g., extracting common and specific information). AI / ML frameworks can be used as implementation means, and these procedures can be applied to non-AI / ML-based delivery.

[0122] Space-frequency (SF) compression may include compression techniques, such as using a model (e.g., an encoder model) in the WTRU to compress the estimated CSI samples (e.g., the original channel or eigenvectors) and using a model (e.g., a decoder model) in the gNB to recover the decompressed CSI using the compressed CSI. For example, SF compression may be used (e.g., independently) for each CSI sample without using time information (e.g., previous CSI estimates). The channel estimated at time t can be used to derive the compressed channel.

[0123] Time-space-frequency (TSF) compression may include compression techniques that generate TSF compressed CSI in the WTRU using (e.g., at least one) past / historical CSI samples (e.g., the original channel or eigenvectors) and currently estimated CSI samples, and generate / recover the current decompressed CSI in the gNB using (e.g., at least one) past / historical CSI measurements and the current compressed CSI.

[0124] A TSF multipart structure may include a structure (e.g., a forced structure) on the output of an AI / ML model to enable TSF compression. For example, the model output is structured to include multiple parts, at least one part capturing common information in a sequence of samples (e.g., time-series data) (this information may be referred to as common information), and other parts capturing specific information in each sample of the sequence (this information may be referred to as specific information).

[0125] Multi-resolution TSF multipart structures may include TSF multipart structures with controllable / dynamic common and / or specific part sizes.

[0126] TSF multipart models may include AI / ML models that are trained to perform TSF compression, for example, by generating common parts and specific parts.

[0127] The TSF sequence may include a sequence of N related CSI samples associated with a specific WTRU. The samples in the TSF sequence (e.g., all samples) may have (e.g., may be assumed to have) (e.g., one) a common part that is reused for samples (e.g., all samples) during reconstruction / decompression.

[0128] The public portion may include a portion that carries potential public information or captures coarse variations in a relevant data sample sequence (e.g., a TSF sequence). The terms sample public portion, public portion, and long-term portion may be used interchangeably to represent the public information carried by the public portion.

[0129] The active common portion may include, for example, a common portion generated using the first sample in the TSF sequence. This common portion may be transmitted, stored, and (e.g., by gNB) used in the reconstruction process of samples (e.g., all samples).

[0130] Inactive common portions may include (e.g., refer to) common portions generated from the other N-1 samples in the TSF sequence (e.g., but may not be transmitted to the gNB). Inactive common portions may be stored (e.g., stored in the WTRU) to, for example, track differences between active and inactive common portions.

[0131] A specific portion may include a section carrying potential specific information or related data from each sample, or a section showing subtle variations between consecutive sample pairs in a sample sequence. The terms sample-specific portion, specific part, and short-term portion may be used interchangeably to represent specific information carried out by a specific portion.

[0132] TSF potential buffers may include: a buffer in the WTRU for storing past CSI samples (e.g., the original channel or eigenvectors) or a buffer in the gNB for storing past decompressed CSI samples or active common portions.

[0133] Details relating to spatial frequency (SF) compression can be described in this article.

[0134] Spatial frequency (SF) compression can be performed sample-by-sample. For example, WTRU can be performed in time slot n based on the estimated channel H. n Compression is performed using an AE model. WTRU can (e.g., firstly) use a model (e.g., an encoder model) to compress H. n To generate and return a latent representation (e.g., compressed CSI) z n gNB can use a model (e.g., a decoder model) to process the received latent representation z. n Decompress to recover H n For example, where the channel H estimated by WTRU n The difference / distance between the channel recovered / decompressed in the gNB can represent the compression loss. Figure 6 The illustration shows an example of SF compression using a two-sided autoencoder model.

[0135] Details related to TSF compression can be described in this article.

[0136] To further improve SF compression performance (e.g., from an overhead reduction and / or performance perspective), an AI / ML encoder model can be trained to represent compressed information as two or more parts (e.g., one part carries common information of the relevant sample sequence (e.g., a TSF sequence) and another part captures specific information in each sample). This information from both parts can be input (e.g., fed together) to an AI / ML decoder model to reconstruct, for example, CSI samples. Common information can be sent for samples in the TSF sequence (e.g., all samples). Specific information can be sent along with the samples in the TSF sequence (e.g., each sample). This model can be referred to as a TSF multipart model. This compression mode can be referred to as time-space-frequency (TSF) compression, for example, where the temporal correlation properties of the channel samples can be used to generate latent parts with some forced structure to reduce feedback overhead over time (e.g., as...). Figure 4 (As shown in the image). AI / ML models can be trained to, for example, generate (e.g., multiple) latent parts (e.g., which may have different sizes, such as...). Figure 5 As shown in the diagram, the latent portion captures the long-term and short-term correlations of the original CSI samples. Enforcing this structure in the latent domain, relative to SF compression, reduces (e.g., leads to reduced) signaling overhead.

[0137] A fixed-size TSF with common and specific parts may be enabled, implemented, and / or described herein.

[0138] Figure 4 Examples of TSF multi-part models are shown, where a single AI / ML model (e.g., AE) is used, and common and specific parts can be generated. One or more parts (e.g., two parts) may have a fixed size. Using different model architectures, it is possible to obtain the proposed framework (e.g., possibly not limited to...). Figure 4 (The model architecture is illustrated in the diagram). For example, using a first AI / ML (e.g., AE) model, common parts can be generated. Using a second AIML model, specific parts can be obtained. The outputs of the first and second AI / ML models can be combined to, for example, reconstruct / recover the expected information.

[0139] Variable-size TSFs with common and specific parts can be enabled, implemented, and / or described in this document.

[0140] A multi-part TSF model can be trained to generate one or more controlled-size parts (e.g., two or more controlled-size parts) to enable, for example, a more efficient TSF framework. For instance, the model can generate variable-size common parts and variable-size specific parts. This can be used to handle multiple WTRU scenarios (e.g., rate) using a single AI / ML TSF model. For example, high-speed scenarios may use (e.g., require) small common parts and large rate parts (e.g., because channel samples tend to be less correlated with increasing rate and therefore have fewer common characteristics in the TSF sequence). Low-speed scenarios may use (e.g., require) large common parts for more efficient communication and small specific parts for capturing small variations in the channel. Figure 5 The illustration shows an example of a TSF model with variable-sized common parts and specific parts.

[0141] Different training protocols for both variable-size and fixed-size TSF multipart models are used, provided, and / or described in this paper.

[0142] like Figure 4 and 5 The exemplary structure shown can be applied to compression problems involving time-series data, such as related sample sequences. TSF compression can be described as an example, for example, in this document. The details described herein are applicable to... Figure 4 and 5 The structure in the text is applicable to any (e.g., any) framework.

[0143] TSF training can be performed and / or described in this paper.

[0144] WTRU can train AI / ML models (e.g., autoencoders) to produce encoder outputs with forced structures for use in TSF compression operations. For example, given a sequence {H1,…, H...} of N time-correlated samples... N (e.g., a TSF sequence of length N), the AE model can be trained to output the long-term component (e.g., z). c ) and short-term sample-specific portions (e.g., z) i The long-term / common portion captures long-term correlations in the input sample sequence. The short-term portion captures short-term correlations, such as between samples in the input sequence (e.g., every two consecutive samples). Long-term portion size. It can be larger than the short-term size. For each short-term size in, The sum of the sizes can be less than or equal to the given maximum size z. max .

[0145] Details associated with an exemplary procedure for training a TSF multipart model with a fixed-size part can be described in this document.

[0146] For example, using the following operation, an AE model can be trained to produce a latent output that has a common structure z. c (e.g., the common part of the samples) and the short-term part z i , (e.g., a specific portion of the sample). Using one or more channel samples (e.g., the same channel samples) as input and label feeds for model training, an autoencoder model can be trained (e.g., in the conventional way). For example, given a sequence of N (e.g., N=3) time-related samples... The model can be trained using the following input / output pairs: , , For example, during the first phase of training, the model's weights (e.g., all weights) can be updated. Channel matrix H i It can be used as input and / or label (e.g., used as both input and label), such as Figure 7 As shown in the image.

[0147] Figure 7 The illustration shows an example of traditional training of the AE model.

[0148] Once training is complete, the model's weights (e.g., all weights) (e.g., except for weights that directly interact with the latent representation (e.g., the weights of the encoder's output layer and the decoder's input layer or first layer)) can be frozen and can be prevented from being updated (e.g., not updated). This relates to the generation of the common part z. c Related training can be performed (e.g., by conducting a process). This is to generate the long-term / common part z. c One or more of the following sample pairs can be constructed: , , , , , .

[0149] Pairing different channels can be used to force a model (e.g., force the model to learn common components between different channels). While training this framework, the latent representation is compared with the common component z. c The corresponding portion can (e.g., is allowed) propagate to the decoder during forward propagation. The corresponding gradient can (e.g., is allowed) propagate back to the encoder. The latent representation and the short-term component z i The corresponding part can be blocked. By making the potential component z i Multiplying by (e.g., forced multiplication) the zero vector, blocking this part of the latent representation can be achieved (e.g., as...). Figure 8 (as shown in the image).

[0150] Figure 8 The illustration shows an example of AE training using common and specific parts. The weights associated with the common parts are updated, while the weights associated with the specific parts are frozen (e.g., using all-zero vectors).

[0151] During this phase of training, for example, because the common parts of the latent representations (e.g., only the common parts) can be propagated to the decoder and the gradients associated with these parts (e.g., only these parts) can be backpropagated, the weights (e.g., only those directly related to z) are also propagated. c The weights of interactions can be updated.

[0152] Once training for the common part has been completed, the short-term components... It can be trained. This training can be performed using channel pairs, where a set of channels (e.g., the same set of channels) can be used both as input and as output (e.g., as shown in the image). Figure 9 (as shown), so as to, for example, train the network to generate short-term components z. i For example, the part. , , The output latent representation z i Can be used with public potential representation / part of z c Used together for refactoring.

[0153] Figure 9 The illustration shows an example of AE training using common and specific parts, where the weights associated with the specific parts are updated and the weights of the common parts are frozen.

[0154] An example associated with training a TSF multipart model with variable-size parts can be described in this paper.

[0155] In the example of training a TSF model using variable-size parts, different models can be used to generate the variable-size common parts of the latent representation (e.g., z). c ) and the variable-size short-run portion of the potential representation (e.g., z) i For example, a model can be trained to use a common encoder / decoder module to produce common parts (e.g., such as...). Figure 10 (As shown in the diagram). For training, different channels can be used as inputs. Sample pairs can be labeled to force the model (e.g., to force the model) to learn common components between different channels. Therefore, training data can have input and label pairs, such as one or more of the following input and label pairs: , , , , , To handle the variable-rate common parts, a variable-rate training process is used, and the common encoder / decoder module can be trained (e.g., as described in this paper).

[0156] Figure 10 The illustration shows an example of training an AE model using a common encoder / decoder module.

[0157] In post-training, the common encoder weights can be frozen, and a second encoder-decoder pair (e.g., a residual encoder-decoder) can be used (e.g., introduced). This is done to train the model (e.g., the model can generate short-term components). This training can be performed using channel pairs, where the same set of channels is used both as input and as labels (e.g., , , Using a training process (e.g., as described in this paper), a variable-rate specific portion can be generated. Figure 11 The diagram illustrates an exemplary summary of the training.

[0158] Figure 11 The illustration shows an example of training using common and specific parts of the encoder-decoder model. The weights of the common encoder and decoder models can be fixed (e.g., kept fixed). For example, the residual encoder-decoder can be updated using a defined loss function.

[0159] The weights of the common encoder and decoder models can be fixed (e.g., kept fixed), and the residual encoder-decoder can be updated using a defined loss function. In addition to the common encoder-decoder model, this residual model can also learn (e.g., effectively learn) compression.

[0160] An exemplary architecture of variable-size common parts and specific parts is shown in Figure 12 middle.

[0161] Figure 12 The illustration shows an exemplary architecture of a TSF compression model with variable-size common parts and specific parts.

[0162] Time-space-frequency compression schemes (e.g., as described herein) can achieve one or more of the following (e.g., benefits): for a given target performance, TSF can leverage the time-dependent properties of CSI to achieve high compression capability relative to spatial-frequency (SF) and conventional-based compression schemes; at a given compression ratio, TSF can leverage the time-dependent properties of CSI to further improve the performance of SF and conventional-based compression schemes; TSF can provide performance and overhead reduction gains relative to SF and conventional compression (e.g., providing both performance and overhead reduction gains); TSF can provide dynamic modifications and flexible use of past historical samples to achieve a balance between performance, complexity, overhead, and storage; and so on.

[0163] The TSF portion can be indicated (e.g., by WTRU).

[0164] For example, time correlation can be utilized when transmitting via multiple TSF CSI components.

[0165] The WTRU can transmit CSI feedback in sections (e.g., two sections), such as a first section including common information (e.g., long-term channel characteristics / variations / natures) and a second section including specific information (e.g., short-term channel characteristics / variations / natures). In an example, the WTRU can transmit CSI feedback in sections (e.g., multiple sections). For example, the multiple sections may include (e.g., one) common section and (e.g., one or more) specific sections. In an example, the size of the common section and / or specific sections may be fixed and / or variable within a pre-configured range. In an example, the WTRU may apply different post-processing (e.g., quantization) to the common section and specific sections. The WTRU may receive configuration information indicating (e.g., configured with) conditions / rules for determining the size and / or post-processing applied to the common section and specific sections, e.g., based on UL resources configured for feedback transmission. In an example, the WTRU may instruct / report the parameters and / or format of the common and / or specific sections and the associated CSI feedback. The WTRU may instruct / report the parameters of the common and / or specific sections separate from the associated CSI report. Using implicit signaling, explicit signaling, or a combination of both, WTRU can indicate the TSF section or its parameters.

[0166] PUCCH bundling can be used, for example, for multipart TSF CSI transmissions.

[0167] The WTRU can receive configuration information indicating (e.g., configured) PUCCH bundles for multi-part TSF CSI transmission. A PUCCH bundle (e.g., each PUCCH bundle) can be associated with multiple PUCCH resources. Each PUCCH resource within a PUCCH bundle can be configured for transmission of a portion (e.g., at least one portion) of the multi-part TSF CSI. For example, the WTRU can transmit a common portion within a first PUCCH resource within a PUCCH bundle. The WTRU can transmit a specific portion within PUCCH resources within a PUCCH bundle (e.g., all PUCCH resources). The WTRU can transmit a specific portion within a PUCCH bundle, for example, within PUCCH resources other than the first PUCCH resource (e.g., all PUCCH resources). The WTRU can receive configuration information indicating (e.g., configured) conditions / rules for disposing of PUCCH resources within a PUCCH bundle. For example, the WTRU can transmit (e.g., one) common portion within a PUCCH bundle. Common portion transmission can be performed before (e.g., any) specific portion transmission. Specific portions (e.g., all specific portions) within a PUCCH bundle can be associated with common portions transmitted within the PUCCH bundle. The WTRU can receive configuration information indicating (e.g., configured) parameters for the PUCCH bundle (e.g., different parameters), such as, but not limited to, the number of PUCCH resources within the PUCCH bundle, the time-domain / frequency-domain pattern / periodicity of the PUCCH resources within the PUCCH bundle, the periodicity of the PUCCH bundle, the offset of the first PUCCH resource within the PUCCH bundle, etc.

[0168] Resource types may depend on public and / or specific parts.

[0169] The WTRU may transmit common portions using a first resource type (e.g., within the first resource type) and / or transmit specific portions using a second resource type (e.g., within the second resource type). The WTRU may transmit common portions using a PUSCH resource (e.g., within a PUSCH resource). For example, the WTRU may transmit specific portions using a PUCCH resource. The WTRU may receive configuration information indicating (e.g., configured with) a PUSCH resource (e.g., a semi-permanent PUSCH resource) for transmitting common portions and a PUCCH resource for transmitting specific portions. The WTRU may receive configuration information indicating (e.g., configured with) a link between a PUSCH resource carrying common portions and a PUCCH resource carrying specific portions. The WTRU may receive configuration information indicating (e.g., configured for) different behaviors, such as conditions based on PUSCH resources (e.g., semi-permanent PUSCH resources). For example, if a PUSCH resource associated with a common part (e.g., a semi-permanent PUSCH resource) is deactivated (e.g., when a PUSCH resource associated with a common part (e.g., a semi-permanent PUSCH resource) is deactivated), the WTRU may fall back to traditional CSI reporting. For example, if a PUSCH resource associated with a common part (e.g., a semi-permanent PUSCH resource) is activated (e.g., when a PUSCH resource associated with a common part (e.g., a semi-permanent PUSCH resource) is activated), the WTRU may transmit (e.g., multi-part) TSF CSI feedback (e.g., using a semi-permanent PUSCH resource to transmit the common part and using a PUCCH resource to transmit the specific part). The WTRU may transmit the common part in the Uplink Control Information (UCI) and / or transmit the specific part in the same or different UCIs. The WTRU may transmit the common part via signaling (e.g., in MAC CE signaling) and transmit the specific part in the UCI.

[0170] Resource selection / instructions may depend on public sections and / or specific sections.

[0171] The WTRU can use PUCCH resources (e.g., the same or different PUCCH resources) to transmit common and specific portions. The WTRU can receive configuration information indicating (e.g., configured) PUCCH resources (e.g., multiple PUCCH resources) for transmitting multi-part TSF CSI feedback (e.g., where an association can be pre-configured between PUCCH resources carrying common portion feedback and PUCCH resources carrying specific portion feedback). This association can, for example, be defined in the time and / or frequency domains. This association can be used (e.g., to help) determine / indicate the common portions that may be applicable to a specific portion (e.g., so that the complete CSI can be reconstructed by the gNB).

[0172] For example, based on conditions and / or rules (e.g., pre-configured / predefined conditions / rules), the WTRU can determine the mapping between portions and PUCCH resources within a multi-part TSF. For example, the WTRU can map a common portion to a PUCCH resource whose payload is configured to be greater than or equal to the size of the common portion. For example, the WTRU can map a common portion to a PUCCH resource whose periodicity matches a periodicity pre-configured for the common portion. For example, the WTRU can map a common portion to a PUCCH resource whose reporting format (e.g., quantization, quantization parameters) matches a quantization (e.g., quantization parameters) configured (pre-configured) for the common portion. Similar rules can be configured for specific portions. The WTRU can indicate in the feedback whether the PUCCH carries a common portion and / or a specific portion. For example, this indication can be included (e.g., explicitly included) in the CSI feedback via an indicator bit. This indication can be made (e.g., implicitly) by selecting from multiple configured PUCCH resources, each associated with a part type (e.g., common or specific). For example, this indication can be implicitly made by the order in which the report content is included. For instance, the common part may be included first, followed by the specific part. The WTRU can use a single PUCCH resource to transmit both the common and specific parts; for example, using the same PUCCH resource (e.g., within the same PUCCH resource), the WTRU can transmit the common part in a first CSI part (e.g., CSI part 1) and the specific part in a second CSI part (e.g., CSI part 2).

[0173] Time-space-frequency CSI compression (e.g., utilizing multi-resolution multipart transmission) can be performed and / or enabled.

[0174] WTRU configuration (e.g., configuration information) for TSF multi-resolution multipart structures can be received, indicated, and / or determined.

[0175] The WTRU may be capable of performing TSF-based CSI compression. The WTRU (e.g., capable of performing TSF-based CSI compression) may receive configuration information for TSF operation, which may include parameters for TSF operation, TSF CSI reporting configuration (e.g., reporting parameters), and parameters for determining the common portion size (e.g., one or more TSF compression CSI portion parameters). This configuration or reconfiguration may be performed via signaling (e.g., RRC signaling).

[0176] Parameters used for TSF operation can be determined and / or received. Parameters used for TSF operation can be described as follows. Parameters used for TSF operation may include one or more of the following: the ML model(s) to be used for TSF CSI compression; the number of parts in the latent domain; part sizes (e.g., if, for example, the WTRU is configured for multi-part operation (e.g., two or more parts) (e.g., when the WTRU is configured for multi-part operation (e.g., two or more parts)), these parameters may indicate the size of the common part and(s) of specific parts(s) (e.g., each specific part within a specific part); quantization information (e.g., quantization parameters) for one (e.g., each) part (e.g., the common part and(s) of one or more specific parts), for example, where the quantization information may include the quantization type (e.g., scalar or vector quantization, uniform or non-uniform quantization). The number of bits per potential element; multi-resolution indicators (e.g., whether the size of each part (e.g., common and / or specific) is fixed or can be dynamically controlled); validity period (e.g., associated with the common part size, such as indicating the duration for which the WTRU can use the configured common part size (e.g., how long the WTRU can use the configured common part size) (e.g., before the WTRU may be triggered or configured to determine the updated part size)), where the validity period can be expressed in time units (e.g., ms or the number of slots, TTIs, frames, or CSI reports using the configured common part size); and so on.

[0177] Parameters used for TSF CSI report configuration can be determined and / or received. Parameters used for TSF CSI report configuration can be described as follows. Parameters used for TSF CSI report configuration may include one or more of the following: common section reporting time period (e.g., the time period between two consecutive CSI feedback reports including the common section); report size (e.g., the WTRU can be configured to report the common section separately from (one or more) specific sections, for example, where the WTRU can receive separate report sizes for reporting the common section and for reporting the specific section(s); the WTRU can be configured to report multiple (e.g., all) sections in the same CSI feedback report, for example, where the report size can indicate the total size available for the common section and one / more specific sections); reporting resources, such as for periodic and semi-permanent reporting; and so on.

[0178] The parameters used to determine the size of the common part can be determined and / or received. The parameters used to determine the size of the common part can be described as follows.

[0179] The WTRU can determine the size of the common part (e.g., enabling the WTRU to use different procedures to determine the size of the common part). The WTRU can receive instructions from the NW for the method to be used (e.g., a channel-based method or a method based on the time variability of the common part) so that, for example, the WTRU supports one or more methods for determining the size of the common part.

[0180] Channel-based methods can use one or more of the following: WTRU rate, Doppler frequency, or channel coherence time, to determine, for example, the common part size. WTRU may be configured with tables (e.g., one or more tables) that map the configured channel metrics (WTRU rate, Doppler frequency, channel coherence time) to the common part size.

[0181] WTRU can be configured with performance metrics (e.g., one or more thresholds corresponding to the performance metrics), such as methods for time-dependent variability of common parts. For example, the performance metric can be associated with a quantity that determines the variability between active and inactive common parts. WTRU can use this metric, for example, based on the distance between inactive and active common parts, to determine whether to update common part or part parameters. Examples of metrics can include one or more of the following: SGCS, NMSE, or Euclidean distance. WTRU can be instructed whether to determine the metric in the latent domain or in the complete (i.e., input) domain.

[0182] For example, performance thresholds can be used. A performance threshold can indicate the threshold that will be used for a configured performance metric, such as the triggering condition for the WTRU to determine whether a partial parameter update is met. For example, if SGCS is used as a performance metric, the WTRU may trigger a partial parameter update if the measured SGCS is less than a configured (SGCS) threshold (e.g., when the measured SGCS is less than the configured (SGCS) threshold). Similarly, if NMSE is used as a performance metric, the WTRU may trigger a partial parameter update if the measured NMSE is greater than a configured (NMSE) threshold (e.g., when the measured NMSE is greater than the configured (NMSE) threshold).

[0183] Many parameters of the TSF can be determined (e.g., by WTRU).

[0184] WTRU can be configured for multi-part compression of TSF using a model (e.g., a two-sided AI / ML model). Multi-part TSF compression can involve generating parts (e.g., two or more parts) within the latent domain of a two-sided model (e.g., an AE). For example, TSF compression utilizing two parts may include: (e.g., a) common part, representing a latent common representation in a sequence of CSI samples (e.g., a TSF sequence); and specific parts, capturing specific information about the samples (e.g., specific information within each sample). In this paper, the resulting CSI information associated with the two parts in the latent domain may be referred to as TSF-compressed CSI.

[0185] The WTRU can (e.g., be configured to) estimate the channel response, for example, based on the received CSI-RS. For example, the WTRU can process (preprocess) the estimated CSI by deriving the channel's eigenvectors. The WTRU can determine one or more parameters associated with the one or more portions (e.g., common (e.g., long-term) portions and specific (e.g., short-term) portions). For example, based on the determined parameters, the WTRU can perform TSF multipart compression. The WTRU can (e.g., be configured to) store the measured CSI or a preprocessed version (e.g., EV), for example, one or more partial parameters used by the WTRU to determine (e.g., assist the WTRU in determining) the partial parameters.

[0186] Some parameters may be used and / or described in this document.

[0187] TSF partial parameters may include one or more common part parameters and one or more specific part parameters. The one or more common part parameters may include one or more of the following: the size of the common part, for example, represented as the number of potential elements; quantization information (e.g., quantization parameters), for example, represented as the number of bits per potential representation and the type of quantization (e.g., where different elements may use different numbers of quantization bits); the validity period associated with the common part size (e.g., the validity period may be defined as how long the determined / indicated common part size can be used before the WTRU can be reconfigured to determine the updated size); performance metrics, for example, the long-term cosine similarity between the measured active and inactive common parts; and so on.

[0188] One or more specific part parameters may include one or more of the following: the size of the specific part, for example, represented as the number of latent elements; quantization information (e.g., quantization parameters), for example, represented as the number of bits per latent representation and the type of quantization (e.g., where different elements may use different numbers of quantization bits); performance metrics, for example, the measured short-term cosine similarity between the current CSI at time t and time t-1; common part parameter determination; and so on.

[0189] The determination of the size of the public section can be executed and / or enabled.

[0190] The WTRU may (for example, be configured to) determine and indicate the size of the common portion based on one or more of the following: resource / reporting budget; channel parameter conditions; link performance; intermediate KPIs (for example, based on CSI measurements); and so on.

[0191] For example, based on resource / reporting budgets, WTRU can determine and indicate the size of the common area. This is based on the maximum allocation budget reported by TSF or the minimum and maximum allowed sizes configured for the common area (e.g., ), WTRU can determine the size of the common parts (e.g., ).

[0192] For example, based on channel parameter conditions, the WTRU can determine and indicate the size of the common part. Channel parameters may include Doppler frequency, WTRU rate, and / or channel coherence time. The WTRU can determine the common part size based on one or more of the following: a pre-configured mapping between WTRU rate and common part size; a pre-configured mapping between Doppler frequency and common part size; a pre-configured mapping between channel coherence time and common part size; and so on. In any of these options (e.g., as described herein), the WTRU can measure (e.g., any) channel parameter (e.g., rate) and select a corresponding size from a mapping table or predefined relation that correlates the channel parameter (e.g., rate) with the size (e.g., ...). ,in This can include the measured WTRU rate, and f(.) can include a pre-configured function. For example, the size and rate of the common size can be defined by an inverse relationship, where increasing the WTRU rate means decreasing the common size.

[0193] For example, based on link performance (e.g., PDSCH), WTRU can determine and indicate the size of the common portion.

[0194] In the example, WTRU may determine the size of the common part based on one or more of the following: a function of PDSCH performance; the measured CQI; etc.

[0195] Based on a function of PDSCH performance (e.g., BLER), WTRU can determine the common part size. For example, if the number of consecutive NACKs exceeds a threshold (e.g., a certain threshold), WTRU can reduce the common part size by x% (e.g., where x can be configured or determined by WTRU). For example, if the number of consecutive ACKs exceeds one or more thresholds, WTRU can increase the common part size by x%.

[0196] Based on the measured CQI, the WTRU can determine the size of the common part. For example, if the measured CQI is below one or more thresholds, the WTRU can decrease the size of the common part. Otherwise, the WTRU can increase or fix the size.

[0197] For example, based on intermediate KPIs (e.g., based on CSI measurements), WTRU can determine and indicate the size of the common portion.

[0198] In the example, WTRU can determine the size of the common area based on CSI measurements. It can indicate CSI samples in TSF sequences, and This can be represented as the associated common portion generated for each sample in the TSF sequence. The common portion associated with the first TSF sample (e.g., only that common portion) (e.g., the active common portion) is transmitted and / or used by the gNB to reconstruct the samples in the TSF sequence (e.g., all samples). Other common portions (e.g., all other common portions) can be generated on the WTRU side to determine... and The differences between them, for In the example (e.g., the ideal case), ,for Depending on how well the model is trained, there may be some errors. WTRU can determine the common part size by performing one or more of the following measurements: a long-term metric measured against the i-th sample in the TSF sequence within the latent domain. Long-term metric measured for the i-th sample in a TSF sequence within the complete domain. ;etc.

[0199] By performing a long-term metric (e.g., SGCS) on the i-th sample in the TSF sequence within the latent domain. WTRU can determine the size of the common part; for example, this long-term metric can be represented by Equation 2.

[0200] Equation 2 For the i-th compression instance, WTRU can measure the long-term SGCS. Compare with the configured long-term threshold. Based on and the configured threshold The difference between WTUR and WTUR can determine the size of the common part. For example, if If the current size is x%, then WTRU can increase the common size by x%. Otherwise, for example, WTRU can decrease the common size by x%. In the example, based on... and The gap between the two can be increased or decreased by a percentage for WTRU.

[0201] By performing a long-term metric (e.g., SGCS) on the i-th sample in the TSF sequence across the entire domain. WTRU can determine the size of the common part; for example, this long-term metric can be represented by Equation 3.

[0202] Equation 3 in This can include the eigenvector associated with the i-th CSI sample in the TSF sequence. For example, based on and By defining the gaps between them, WTRU can determine the size of the common area (e.g., increase / decrease by x% relative to the current size).

[0203] In the example, WTRU can determine the common part size based on a predefined table that maps long-term metrics to the common part size as a percentage of the maximum potential representation size, as shown in Table 1.

[0204] Table 1. Mapping between long-term metrics (e.g., SGCS) and common part size expressed as a percentage of the maximum potential representation size.

[0205] Common part quantification information (e.g., common part quantification parameters) can be determined.

[0206] The WTRU can determine quantization information associated with the common part (e.g., quantization parameters, such as quantization type and / or the number of bits). Quantization types can include uniform quantization, where common part elements / potential representations (e.g., all common part elements / potential representations) are assigned the same number of bits. Quantization types can also include non-uniform quantization, where different potential representations can be quantized using different numbers of bits. In the case of variable-rate common parts, non-uniform quantization can be used (e.g., is beneficial), where, for example, the top potential representation can be assigned a higher number of bits compared to the bottom potential representation. The WTRU can determine the quantization type based on the rate of change of each potential element in the common part.

[0207] The validity period of the public portion size can be used, determined, and / or enabled.

[0208] The WTRU can be configured to determine the effective time associated with the determined common part size. This can indicate how long the determined and indicated common part size should be used by the gNB, for example, until a size update is performed (e.g., required). In the example, the size update may occur as a supplement (e.g., incremental) to the common size used in the NW. In this case, the WTRU can convey common information associated with the incremental / difference potential element. In the example, the size update may occur as a replacement of the total size used by the NW. In this case, the WTRU can determine and indicate the size (e.g., the new size) and the associated common part CSI information.

[0209] In the example, WTRU can determine the effective time for the common size based on the rate of change of the common portion. For example, by measuring... and The difference is then compared to a pre-configured threshold. A smaller difference (e.g., compared to a larger difference) between the active common portion derived from the first sample in the TSF sequence and the inactive common portion associated with the second sample in the TSF sequence can be associated with a higher effective time of the determined magnitude. Based on the measured quantity WTRU determines the valid time by mapping between the valid time and the common part size (e.g., a predefined mapping). The valid time can be expressed as the number of samples or in milliseconds. The number of samples can be less than or equal to the number of samples in the TSF sequence.

[0210] Specific parameters can be determined.

[0211] In the example, WTRU can determine and indicate the size of a specific portion based on one or more of the following: resource / reporting budget, channel parameter conditions, intermediate KPIs (e.g., based on CSI measurements), etc.

[0212] Based on resource / reporting budgets, WTRU can determine and indicate the size of a specific portion. This is based on allocation budgets from TSF reports (e.g., maximum allocation budgets). ), the allowed size of a specific part (e.g., the configured minimum and maximum allowed sizes) (e.g., ) or the allocated budget (e.g., maximum allocation budget) and the determined size of the common area (e.g., ), WTRU can determine the size of a specific part (e.g., ).

[0213] Based on one or more channel parameter conditions, the WTRU can determine and indicate the size of a specific portion. Channel parameters may include one or more of the following: Doppler frequency, WTRU rate, and / or channel coherence time. The WTRU can determine the size of the specific portion based on one or more of the following: a pre-configured mapping between the WTRU rate and the specific portion size; a pre-configured mapping between the Doppler frequency and the specific portion size; a pre-configured mapping between the channel coherence time and the specific portion size; and so on. In any of these options (e.g., as described herein), the WTRU can measure (e.g., any) channel parameter (e.g., rate) and select a corresponding size from a mapping table or predefined relation that correlates the channel parameter (e.g., rate) with the specific portion size (e.g., ...). , where v may include the measured WTRU rate and g(.) may include a pre-configured function. For example, using linear or nonlinear relationships, the size and rate of a specific size can be associated (e.g., the size and rate of a specific size can be defined by linear or nonlinear relationships), for example, where increasing the WTRU rate is associated with increasing the size of a specific portion.

[0214] For example, based on intermediate KPIs (e.g., based on CSI measurements), WTRU can determine and / or indicate the size of a specific section. In the example, WTRU can determine the size of a specific section based on CSI measurements. It can indicate CSI samples in TSF sequences, and This can be identified as a specific portion of the association generated for each sample in the TSF sequence. Unlike the common portion, the specific portion associated with different samples in the TSF sequence may be different (e.g., completely different). The size of a specific portion can be determined by performing one or more of the measurements below.

[0215] By performing a short-term metric (e.g., SGCS) on the i-th sample in the TSF sequence within the full CSI domain. WTRU can determine the size of a specific part, and this short-term metric can be represented by Equation 4.

[0216] Equation 4 The eigenvector associated with the i-th CSI sample in the TSF sequence may include For example, based on and By identifying gaps between samples, WTRU can determine the size of a specific segment (e.g., an increase / decrease of x% relative to the current size). In the example, WTRU determines the size of a specific segment based on a predefined mapping between the measured correlation and the size of that segment, as shown in Table 2. Higher correlations between consecutive samples can be associated with smaller sizes of specific segments, and vice versa.

[0217] Table 2 - Mapping between short-term metrics (e.g., SGCS) and specific part sizes expressed as a percentage of the maximum potential representation size.

[0218] For example, the size of each part can be determined based on prioritizing common parts or specific parts.

[0219] In the example, WTRU can determine (e.g., first determine) the common part size, and then use its determination, along with the maximum allocated uplink budget, to calculate the specific part size. In the example, WTRU can determine the size of a specific part while taking into account (e.g., considering) Condition c can (e.g., should) be satisfied. In the example, the WTRU can determine (e.g., first determine) the size of a specific part. The WTRU can use (e.g., then use) its determination and the allocated budget (e.g., the maximum allocation budget) to calculate the size of the common part. WTRU may consider calculating the size of the common part, for example, taking into account (e.g., considering or based on) conditions. This can be beneficial when the allocation budget for both parts (e.g., the maximum allocation budget) needs to be reduced. In this case, WTRU can recommend the allocated uplink budget (e.g., the maximum allocation uplink budget).

[0220] Some TSF parameters may be reported and / or indicated (e.g., reported and / or indicated by WTRU).

[0221] A WTRU can be configured to indicate / report one or more parameters associated with TSF multipart CSI feedback. In an example, TSF multipart CSI feedback may include one or more common part parameters and one or more specific part parameters. A WTRU can be configured to indicate / report one or more common part parameters and / or one or more specific part parameters among the common part parameters. In this document, "one or more common part parameters" can be used interchangeably with "common parameters." "One or more specific part parameters" can be used interchangeably with "specific parameters." The terms TSF multipart feedback report, TSF report, and TSF CSI report can be used interchangeably to describe, for example, a CSI report carrying TSF multipart parameters. A TSF multipart report may include (e.g., divided into) a common part report and / or a specific part report, for example, where a common part report may include common part CSI and common part parameters, and a specific part report may include specific part CSI and specific part parameters.

[0222] Common parameters may be reported and / or indicated (e.g., reported and / or indicated by WTRU).

[0223] WTRU can report common part parameters as part of the TSF multipart feedback report. (One or more) common part parameters may include at least one of the following: common part size, common part size validity period, common part quantization information (e.g., quantization parameters, such as, for example, quantization type and / or number of bits), common part performance metric, AI / ML model identifier, AI / ML model input (e.g., EV or full CSI), etc.

[0224] In the example, WTRU may report the common part size as the number of elements / latent representations. In the example, WTRU may report the common part size as a fraction of the total number of elements / latent representations in the AI / ML encoder (e.g., 0.25). In the example, WTRU may report the common part size as an update to the currently used size (e.g., an increase or decrease of x% relative to the currently used size). WTRU may report quantization information associated with the common part size. Quantization information may include quantization parameters such as, for example, quantization type (e.g., uniform or non-uniform) and / or the number of quantization bits. The number of quantization bits may be indicated as the same for common latent representations (e.g., all common latent representations), or as a distinct number of bits for each latent representation.

[0225] In the example, the WTRU can report the validity period of the common part size. In the example, the validity period can be expressed as an integer number of samples, an integer number of time slots, or a time unit (e.g., milliseconds). The validity period of the common part size can indicate how long the indicated common part size can be used. In the example, the validity period of the common part size can be indicated in different formats, for example, where (e.g., each) the format corresponds to a different meaning. For example, format 1 can indicate that for n time slots, the reported common part size and associated CSI information can be valid, and thereafter, different common part sizes (e.g., new common part sizes) and CSI information can be transmitted. For example, format 2 can indicate that for up to n2 time slots, the reported common part size and associated CSI information can be valid, but after n1 time slots, incremental / supplementary common part size and associated CSI information for improved reconstruction, in addition to the common part size and associated CSI information available in NW, can be signaled, where n1 <n2。

[0226] In the example, the WTRU may report a performance metric associated with the public part report. This performance metric may be determined based on one or more long-term metrics (e.g., as described herein for the public part parameter determination). For example, the performance metric may include one or more of the SGCS / NMSEs between the active public part and(one or more) inactive public parts. In the example, the performance metric may include one or more of the SGCS / NMSEs between the first CSI sample or associated EV in the TSF sequence and(one or more) other CSI samples or associated EVs in the same TSF sequence.

[0227] In the example, the WTRU may receive configuration information indicating (e.g., configured with) periodic PUCCH / PUSCH resources for reporting one or more common part parameters and / or one or more specific part parameters. In the example, the WTRU may utilize periodic PUCCH / PUSCH transmissions (once or multiple times) to report one or more common part parameters of a first group (e.g., common part size and associated validity period), and report one or more common part parameters of a second group (e.g., performance metrics) based on non-periodic requests from the gNB. In the example, the WTRU may report the one or more common part parameters from the common part parameters via signaling (e.g., in MAC CE).

[0228] One or more specific partial parameters may be reported and / or indicated (e.g., reported and / or indicated by WTRU).

[0229] WTRU can report one or more specific part parameters as part of the TSF multipart feedback report. One or more specific part parameters may include one or more of the following: specific part size, specific part quantization information (e.g., quantization parameters, such as quantization type and number of bits), specific part performance metric, AI / ML model identifier, AI / ML model input (e.g., EV or full CSI), etc.

[0230] In the example, WTRU may report a specific portion size represented as the number of elements / latent representations. In the example, WTRU may report a specific portion size as a fraction of the total number of elements / latent representations in the AI / ML encoder (e.g., 0.25). In the example, WTRU may report a specific portion size as an update to the currently used size, such as an increase or decrease relative to x% of the currently used size. WTRU may report quantization information (e.g., quantization parameters) associated with the specific portion size. Quantization information may include quantization parameters such as, for example, quantization type (e.g., uniform or non-uniform) and / or the number of quantization bits.

[0231] In the example, the WTRU may report a performance metric associated with a specific part of the report. This performance metric may be determined based on one or more short-term metrics (e.g., as described herein for determining parameters for one or more specific parts). For example, the performance metric may include one or more of the SGCS / NMSE between the i-th CSI sample or (e.g., possibly) associated EV in the TSF sequence and the (i-1)-th sample or possibly associated EV.

[0232] In the example, the WTRU may receive configuration information indicating (e.g., configured) periodic PUCCH / PUSCH resources for reporting one or more specific partial parameters. In the example, the WTRU may utilize periodic PUCCH / PUSCH transmissions (once or multiple times) to report one or more specific partial parameters (e.g., specific partial size) of a first group, and report one or more specific partial parameters (e.g., performance metrics) of a second group based on non-periodic requests from the gNB. In the example, the WTRU may report the one or more specific partial parameters in the specific partial parameters via signaling (e.g., in MAC CE).

[0233] WTRU can use multiple parts (e.g., two parts) to send TSF feedback reports. For example, the first part can be sent for one or more parameters. For example, the second part can be sent for TSF CSI information.

[0234] In the example, the WTRU may utilize multiple parts (e.g., two separate parts) to report TSF multipart CSI feedback. The WTRU may report identified common part(s) and specific part parameters (e.g., size and quantization information) in the first part of the TSF CSI feedback report, and report the common part and specific part CSI in the second part of the TSF CSI feedback report (e.g., as described herein in the WTRU indications for TSF parts). In the example, the WTRU may receive configuration information indicating (e.g., configured) periodic PUCCH / PUSCH resources for reporting the first part of the TSF feedback report. In the example, the WTRU may receive configuration information configured (e.g., configured) for reporting the first part of the TSF feedback report based on non-periodic requests from the gNB.

[0235] One or more partial parameter updates can be triggered (e.g., for WTRU partial parameter updates).

[0236] One or more of the following items may constitute the triggering conditions for WTRU to update TSF section parameters, such as: the number of TSF compressed CSI sections, the size and / or size range of each section, the number of symbols in each section, the size ratio of common sections to specific sections, the allocation of each transmission / reporting section, etc.

[0237] Triggering conditions for updating TSF parameters in WTRU may include changes in the common potential part exceeding a pre-configured threshold (e.g., measured by the number of irrelevant data samples / symbols or by the number of irrelevant data samples relative to the total number of data samples / symbols in the common part).

[0238] The triggering conditions for WTRU to update (one or more) TSF component parameters may include changes in specific potential components (e.g., if the change between consecutive sample pairs in a relevant data sample sequence is greater than a pre-configured threshold or is measured according to data samples and / or symbols).

[0239] The triggering conditions for WTRU to trigger the update of TSF part parameters may include the duration / length of the change in the potential part, for example, the change greater than a threshold is measured to be the number of consecutive samples exceeding a pre-configured threshold.

[0240] The triggering conditions for WTRU to update TSF parameters may include the duration / length of changes to common parts.

[0241] Triggering conditions for WTRU to update TSF portion parameters may include receiving an instruction from the network. This instruction may include one or more of the following: an update instruction (e.g., a simple update instruction); an instruction to update one or more parameters (e.g., the size of each portion); an instruction in the gNB's decoder (e.g., a new decoder); an instruction to update the TSF configuration from the network; or an instruction from the gNB to switch to a different encoder, activate a different encoder, or train (retrain) an encoder (e.g., WTRU may re-evaluate TSF portions and associated parameters).

[0242] Simple update instructions can be received by the WTRU. The WTRU may have multiple (e.g., two) configurations (e.g., tsf_config1, tsf_config2) for TSF compression, such that simple switchover / update instructions from the network can instruct the WTRU to switch from the currently applied configuration. The configuration (e.g., tsf_config) may be associated with one or more specific parameters such as the number of parts, the size of each part, the allocation of each transmitted / reported part, etc.

[0243] Indications from different decoders in the gNB can be received by the WTRU. For example, if the WTRU receives an indication (e.g., a simple indication) from a different (e.g., new) decoder active in the gNB, the WTRU may disable (e.g., possibly not perform) TSF compression for a period of time (e.g., until it receives information about the tsf_config to be applied and / or an update to the parameters of the currently active tsf_config). Indications from different (e.g., new) decoders in the gNB can be transmitted along with updates to associated parameters, such as the size of a common potential portion (e.g., a new size).

[0244] Indications of TSF configuration updates from the network can be received by the WTRU. For example, the WTRU can receive updates to the TSF configuration that have one or more different (e.g., new) parameters, such as the number of parts, the size of each part, quantization information, etc. (e.g., updates to new tsf_config3, new tsf_config4, and / or tsf_config1 / tsf_config2, where the initial configuration may have been previously received in RRC configuration (reconfiguration)).

[0245] Triggering conditions for WTRU to update TSF parameters may include WTRU measurements of channel conditions. WTRU can measure channel conditions (e.g., cell RSRP, L1-RSRP, Doppler effect, channel coherence time, channel coherence bandwidth, CSI parameters such as CQI, PMI, RI, etc.). Changes in channel quality (e.g., sudden changes) can trigger WTRU to switch to a different configuration or update some parameters within the configuration. For example, channel degradation over a short period can trigger WTRU to allocate a larger size to a specific potential segment.

[0246] Triggering conditions for WTRU to update TSF portion parameters may include WTRU measurements of WTRU rate / movement / location / positioning. At high speeds, the WTRU may disable (e.g., may not use) TSF compression (e.g., any TSF compression), or may therefore modify TSF configuration parameters. At different (e.g., new) locations, the WTRU may determine to update the TSF portion and one or more associated parameters (e.g., size, quantization information).

[0247] The triggering conditions for updating TSF parameters by WTRU may include WTRU activation of a different AI / ML encoder (e.g., a new AI / ML encoder).

[0248] The triggering conditions for WTRU to update some parameters of TSF can include WTRU switching to a different AI / ML encoder.

[0249] TSF type determination can be executed. Multipart transfers with a controllable part-specific overhead WTRU configuration for time-related multipart generation can be executed.

[0250] Potential structures can be categorized (e.g., classified as cases / types), such as TSF type. Fixed / variable can be used to indicate whether the size of the part is fixed or variable. Public / specific can be used to indicate whether the information associated with the part is shared / reusable / public across multiple CSI samples, or specific to a single (e.g., per) sample.

[0251] Public-fixed-specific-fixed can include situations where the latent domain is structured to include a fixed-size public portion and a fixed-size specific portion. Public-fixed-specific-variable can include situations where the latent domain may include (e.g., may be structured to include) a public portion (e.g., a fixed-size public portion) and a specific portion (e.g., a variable-size specific portion). Public-variable-specific-fixed can include situations where the latent domain is structured to include a variable-size public portion and a fixed-size specific portion. Public-variable-specific-variable can include situations where the latent domain may include (e.g., may be structured to include) a variable-size public portion and a variable-size specific portion.

[0252] The TSF type and parameters can be configured.

[0253] A TSF CSI report can be defined or used. For example, a CSI report can be determined or defined as a TSF CSI if one or more of the following conditions are met: the CSI is generated, derived, or estimated (e.g., based on previously reported CSI); a portion of the CSI was reported at some time (e.g., at an earlier time), and the remainder of the CSI is reported; the receiver uses (e.g., needs to use) the CSI reported in multiple time instances in order to, for example, reconstruct the CSI; the CSI is constructed to have multiple parts, for example, where a first part can be considered a common part (e.g., a long-term part) and a second part can be considered a specific part (e.g., a short-term part), and where the common part can be used or valid in multiple CSI reporting instances and the specific part can be used or valid in the time instances where the specific part was reported (e.g., the common part can be fixed-size or variable-size and / or the specific part can be fixed-size or variable-size); the CSI is compressed using an AI / ML model (e.g., a two-sided model); and so on.

[0254] One or more TSF types may be used, defined, or configured for CSI reporting. A TSF type may be determined or defined based on one or more of the following: the number of parts used, determined, or defined to construct the CSI; whether each part is fixed-size or variable-size and is configured or used; the maximum and / or minimum size of each part configured or used; the uplink resource type used for CSI reporting (e.g., PUSCH, PUCCH, etc.); and so on.

[0255] WTRU can be configured with one or more of the following for TSF CSI reporting.

[0256] WTRU can be configured (e.g., for TSF CSI reporting) to have (e.g., at least one) common parts and (e.g., one or more) specific parts.

[0257] For example, if the common part size or specific part size is fixed, the WTRU can be configured (e.g., for TSF CSI reporting) to have a common part size and / or one or more specific part sizes. Otherwise, for example, a range of common part sizes or specific parts can be indicated, configured, predefined, or used. The WTRU can determine the size of the common part or specific part within this range based on one or more of the following: the WTRU rate, channel correlation in the time domain; the Time Domain Channel Properties (TDCP) value associated with the report; and so on. In the example, the TDCP value can be reported along with the common part. The common part size can be determined based on the TDCP value. For example, if the TDCP value is high (e.g., when the TDCP value is high), the common part size can be relatively large; otherwise, the common part size can be relatively small (e.g., vice versa).

[0258] WTRU can be configured (e.g., for TSF CSI reporting) as a range of common part sizes or specific part sizes (e.g., the range is indicated, configured, or used) as variable sizes.

[0259] The WTRU can be configured (e.g., for TSF CSI reporting) to have uplink resources for reporting common parts and / or (one or more) specific parts. The uplink resources (e.g., PUCCH, PUSCH, PRACH, etc.) may differ for common parts and specific parts. Common parts can be reported using more reliable uplink resources or at a lower decoding rate compared to specific parts (e.g., considering that erroneous transmission / reception of common parts could lead to consecutive errors in CSI reporting).

[0260] WTRU can be configured (e.g., for TSF CSI reporting) to have one or more uplink reporting characteristics (e.g., periodic, non-periodic, semi-permanent) with one or more common parts and specific parts. The common parts can be reported periodically, while one or more specific parts can be reported semi-permanently or non-periodicly.

[0261] The WTRU can be configured (e.g., for TSF CSI reporting) so that a Cyclic Redundancy Check (CRC) can be attached to the common section, while no CRC can be attached to a specific section. Therefore, the receiver can receive a detection error for the common section, for example, while the specific section can be used without checking for errors.

[0262] WTRU can be configured (e.g., for TSF CSI reporting) to have reporting durations / cycles for one or more common and specific parts. Reporting durations / cycles may differ across common and / or specific parts. Common part reporting cycles may be longer than specific parts. Durations, cycles, time periods, or gaps can be used interchangeably.

[0263] WTRU can be configured (e.g., for TSF CSI reporting) to have a priority order for its parts. For example, if WTRU reports (e.g., needs to report) multiple parts (e.g., when WTRU reports (e.g., needs to report) multiple parts), WTRU can be configured to have priorities across one or more common and specific parts. The priority order can (e.g., alternatively) be predefined or predetermined. One or more of the following may apply: common parts may have higher priority than specific parts; common parts that are the same as the most recently reported common parts may have lower priority than specific parts (e.g., in this case, WTRU may indicate that the reported common parts can be reused); if more than one specific part is used or reported (e.g., when more than one specific part is used or reported), a specific part with a lower part index may be considered higher priority; when the allocated or permitted uplink resources are insufficient to carry the parts determined for reporting in this instance, WTRU may discard lower priority parts; and so on.

[0264] For example, a WTRU may withdraw from a TSF CSI to an SF CSI (e.g., where an SF CSI may be referred to as a CSI report independent of previously reported CSIs) if one or more of the following conditions are met (e.g., when one or more of the following conditions are met): if the WTRU receives consecutive NACKs (e.g., many consecutive NACKs) for the reported CSI (e.g., common parts) (e.g., when the WTRU receives consecutive NACKs (e.g., many consecutive NACKs) for the reported CSI (e.g., common parts); if the channel time correlation is below a threshold (e.g., the TDCP value is below a threshold); if the WTRU receives a withdrawal indication (e.g., when the WTRU receives a withdrawal indication); if the common part change is greater than a threshold within the time window; if the channel reconstruction error is greater than a threshold; if the TSF compression error is greater than a threshold; and so on.

[0265] The TSF type and parameters can be determined (e.g., by WTRU).

[0266] The details of WTRUs capable of performing TSF-based compression can be described in this article.

[0267] A WTRU with TSF-based compression capabilities can receive CSI-RS transmissions and / or estimate CSI. For example, depending on the configured input domain type, the WTRU can generate inputs for a TSF-based compression model. The input domain type can be a channel representation, such as a channel matrix, channel eigenvectors, or a processed channel matrix. For example, if configured, the WTRU can store TSF-based compressed inputs (e.g., channel matrix, eigenvectors).

[0268] For example, based on the configured default TSF type and parameters, WTRU can activate and use the TSF compression model. In the example, different types (e.g., four different types) of TSF-based compression can be used and / or provided (e.g., such as...). Figure 13 (As shown in the diagram). WTRU can be configured with one of the compression types based on TSF as described in this document.

[0269] WTRUs can be configured with common-fixed and specific-fixed TSF-based compression (e.g., TSF Type 1). For example, in TSF Type 1, the potential encoder structure may include a fixed size. common parts and fixed size A specific part of it.

[0270] WTRUs can be configured with common-fixed and specific-variable TSF-based compression (e.g., TSF type 2). For example, in TSF type 2, the potential encoder structure can include a fixed size. public areas and and( A specific portion of the variable size between ).

[0271] WTRUs can be configured with common-variable and specific-fixed TSF-based compression (e.g., TSF type 3). For example, in TSF type 3, the potential encoder structure may include... and( The variable-size common part between and the fixed-size part. A specific part of it.

[0272] WTRU can be configured with common-variable and specific-variable TSF-based compression (e.g., TSF type 4). For example, in TSF type 3, the potential structure of the encoder may include... and( The variable-size common part between ) and and( A specific portion of the variable size between ).

[0273] For example, based on the configured first TSF type and associated parameters, the WTRU can generate TSF compressed CSI portions (e.g., common and specific). For example, the associated parameters could be the size of the common and specific portions of the TSF compression. The WTRU can store one or more portions of the TSF compressed CSI.

[0274] The WTRU can determine a second type of TSF compression and associated parameters(s). The second type of TSF compression can be, for example, one of type 1, type 2, type 3, or type 4. Associated parameters can be, for example, the size of common and specific parts and / or quantization information associated with one (e.g., each) part (e.g., one or more quantization parameters). For example, based on pre-configured conditions and measurements, the WTRU can determine the second type of TSF compression and associated parameters(s).

[0275] For example, WTRU can determine the second TSF type based on one or more of the following.

[0276] For example, based on one or more channel parameters (e.g., Doppler effect, WTRU rate), the WTRU can determine a second TSF type. For instance, the WTRU can use channel measurements to estimate the Doppler effect and compare the estimated Doppler effect with one or more configured thresholds to determine the second TSF type (e.g., each Doppler effect range is mapped to a specific type). For example, if the WTRU is in a stable environment (e.g., there is no variation in the WTRU rate or the WTRU rate / Doppler effect is below a configured threshold), the WTRU can determine TSF type 1. For example, if the WTRU is in a highly dynamic environment (e.g., the WTRU rate / Doppler effect range is above a configured threshold), the WTRU can determine TSF type 4.

[0277] For example, based on CSI measurements, the WTRU can determine a second TSF type. For example, the WTRU can estimate long-term / short-term SGCS for common and specific parts. The WTRU can compare the estimated long-term / short-term SGCS with configured long-term / short-term SGCS thresholds to, for example, determine the identification (e.g., fixed or variable) of the common and specific parts. For example, if the long-term SGCS is higher than the configured long-term SGCS, the WTRU can determine the identification of the common part as fixed. Otherwise, the WTRU can determine the identification of the common part as variable. For example, if the short-term SGCS is higher than the configured short-term SGCS, the WTRU can determine the identification of the specific part as fixed. Otherwise, the WTRU can determine the identification of the specific part as variable.

[0278] For example, based on the first TSF type, the WTRU can determine the second TSF type. For example, relative to the first TSF type, the WTRU can determine the second TSF type. For example, if the WTRU measures an increase in the WTRU rate / Doppler effect, the WTRU can determine a TSF type with a higher index (e.g., if the first TSF type is type 2, the WTRU can select type 3 for the second TSF type). For example, if the WTRU measures a decrease in the WTRU rate / Doppler effect, the WTRU can determine a TSF type with a lower index (e.g., if the first TSF type is 2, the WTRU can select type 1 for the second TSF type).

[0279] WTRU can determine associated parameters for a given TSF type. For example, associated parameters may include the portion size and quantization information for each part (e.g., one or more quantization parameters). WTRU can determine associated parameters based on one or more of the following, for example.

[0280] Based on the WTRU rate / Doppler effect, the WTRU can determine associated parameters(s), such as part size. For example, if the determined TSF type is type 2, the WTRU can determine the size of a particular part based on the WTRU rate (e.g., such that the size increases with increasing WTRU rate). For example, if the determined TSF type is type 3, the WTRU can determine the size of the common part based on the WTRU rate (e.g., such that the size decreases with decreasing WTRU rate). For example, if the determined TSF type is type 4, the WTRU can determine the sizes of individual parts based on the WTRU rate (e.g., such that the size of the common part decreases and the size of a particular part increases with increasing WTRU rate).

[0281] Based on the WTRU rate / Doppler effect, WTRU can determine one or more associated parameters, such as quantization level. For example, WTRU can determine the quantization level of common parts and specific parts based on the WTRU rate (e.g., such that the quantization level increases with increasing WTRU rate).

[0282] Based on CSI measurements, the WTRU can determine associated parameters(s), such as part size. For example, if the determined TSF type is Type 2, the WTRU can determine the size of a particular part based on the short-term SGCS (e.g., such that the size increases as the short-term SGCS decreases). For example, if the determined TSF type is Type 3, the WTRU can determine the size of the common part based on the long-term SGCS (e.g., such that the size increases as the long-term SGCS decreases). For example, if the determined TSF type is Type 4, the WTRU can determine the sizes of the common part and the particular part based on both the short-term and long-term SGCS (e.g., such that the size of the common part increases as the long-term SGCS decreases and the size of the particular part increases as the short-term SGCS decreases).

[0283] Based on the short-term / long-term SGCS, the WTRU can determine one or more associated parameters, such as the quantization level. The WTRU can determine the quantization level of a common portion based on the long-term SGCS, for example, such that the quantization level of the common portion increases as the long-term SGCS decreases. The WTRU can determine the quantization level of a specific portion based on the short-term SGCS, for example, such that the quantization level of the specific portion increases as the short-term SGCS decreases.

[0284] Based on latent representation measurements, WTRU can determine associated parameters(s), such as part size. For example, if the determined TSF type is type 2 or type 4 (where the common part is variable), (e.g., if the average difference between multiple consecutive latent representation measurements exceeds a threshold), WTRU can reduce the size of the common part.

[0285] Based on latent representation measurements, the WTRU can determine associated parameters(s), such as quantization level. The WTRU can determine the quantization level of a common portion based on latent representation measurements, for example, such that the quantization level increases with the average difference of multiple consecutive latent representation measurements.

[0286] For example, WTRU can represent partial size parameters based on one or more of the following: the actual size of the common and variable parts; the percentage of the common and variable parts relative to the full potential representation size; the incremental size of the variable parts of the potential representation compared to a previously transmitted potential representation; and so on.

[0287] The TSF type and parameters can be indicated (e.g., by WTRU).

[0288] WTRU can report the selected and applied TSF type. WTRU can indicate the supported types (e.g., Type 1, Type 2, Type 3, and Type 4). WTRU can indicate which AI / ML model is applied for TSF compression (e.g., including which TSF type was selected from the available types in the activated AI / ML model). WTRU can report the values ​​of parameters associated with the TSF type (e.g., the number of parts, the size of fixed common parts and specific parts, and the size of variable common parts and specific parts). WTRU can report the size of common parts and specific parts as a percentage, such as a percentage of the size of common parts relative to the potential representation size or a percentage of one or more specific parts relative to the potential representation size.

[0289] For example, if a TSF AIML model has a variable / adaptive compression ratio, WTRU can report the compression ratio chosen by both the common part and the specific part.

[0290] WTRU can indicate the quantization level applied to one (e.g., each) portion of the TSF CSI feedback. WTRU can indicate the quantization function (e.g., uniform or non-uniform) and the quantization level (e.g., quantization bits).

[0291] WTRU can utilize multiple sections (e.g., two separate sections) to report TSF multi-part CSI feedback. WTRU can report common and specific CSI parts (e.g., as described herein) in the first section (e.g., section 1) of the TSF CSI feedback report. The resulting sections can be based on configured TSF parameters (e.g., TSF type and associated parameters). Preferably, the TSF type and associated parameters can be reported in the second section (e.g., section 2) of the TSF CSI feedback report.

[0292] TSF type determination and multipart transfers with controllable part-specific overhead can be performed.

[0293] Figure 13 The illustration shows an example TSF type.

[0294] In some scenarios (e.g., static environments), for a WTRU moving at a specific rate (e.g., a specific WTRU), a TSF model with a fixed-size portion trained based on that rate can be used (e.g., it may be efficient). In other scenarios (e.g., highly dynamic scenarios where the WTRU rate can vary over a wide range), another TSF model that flexibly controls the size of each portion can be used (e.g., it is needed) to address the dynamic nature of the environment. Different TSF types (e.g., four different TSF types) can be used to handle different scenarios, namely fixed-size portions, variable-size portions, one fixed portion and one variable portion. The TSF type and associated parameters can be selected / determined and / or reported (e.g., as per the context of the TSF model). Figure 6 (As shown).

[0295] The WTRU that performs TSF-based CSI compression can determine the TSF type and associated parameters (e.g., the size of long-term and short-term components in the potential space and the quantization associated with each component) based, for example, on channel conditions and / or configured metric thresholds, and can report the determined TSF type and parameters.

[0296] The WTRU can receive configuration information indicating (e.g., configured) one or more parameters to generate CSI feedback, for example, based on time-space-frequency (TSF) compression (e.g., using a two-sided model). TSF-compressed CSI can include multiple parts. TSF-compressed CSI can include a long-term / common part, which captures long-term variations in a given sequence of related samples. The long-term / common part can be sent in periodic CSI feedback transmissions (e.g., once every N CSI feedback transmissions, where N can be configured). The long-term / common part can be stored and reused in subsequent time slots (e.g., consecutive N time slots). The long-term / common part can have a controllable / variable-sized feedback overhead, such as a size range. TSF-compressed CSI can include a short-term / specific part. The short-term / specific part captures short-term variations between each pair of related samples in a given sequence of N related samples. The short-term / specific part can be sent in (e.g., each) CSI feedback transmission. The short-term / specific part can have a controllable / variable-sized feedback overhead, such as a size range.

[0297] The WTRU can receive configuration information indicating one or more configuration parameters associated with TSF compression. These configuration parameters may include one or more of the following: TSF configuration and its parameters; conditions / parameters for determining or selecting potential TSF representations / partial representations; reporting configuration information; and so on.

[0298] Configuration parameters associated with TSF compression may include TSF configuration information and its parameters. Configuration parameters may include TSF type, default type (e.g., TSF type 1), type-specific information (e.g., number of parts, size range of each part, quantization information for each part associated with each type), or input domain type (e.g., EV or full CSI). TSF types (e.g., based on the size of each part, such as fixed or variable) may include one or more of the following: common-fixed and specific-fixed (e.g., TSF type 1); common-fixed and specific-variable (e.g., TSF type 2); common-variable and specific-fixed (e.g., TSF type 3); common-variable and specific-variable (e.g., TSF type 4).

[0299] Configuration parameters associated with TSF compression may include conditions / parameters for determining / selecting potential TSF representations / partial representations. For example, these conditions / parameters may include short-term performance metric thresholds (e.g., short-term SGCS / NMSE thresholds: between every two consecutive CSI samples). Alternatively, these conditions / parameters may include long-term performance metric thresholds (e.g., long-term SGCS / NMSE thresholds: between the current CSI sample and the first CSI sample in the TSF sequence).

[0300] Configuration parameters associated with TSF compression may include report configuration information (e.g., specific reports such as MCS and / or quantization, UL resources).

[0301] The WTRU can receive CSI-RS transmissions. The WTRU can estimate the channel and (optionally) store the measured CSI (e.g., the complete channel).

[0302] For example, based on the configured first TSF type and associated parameters, the WTRU can generate TSF compressed CSI portions (e.g., public and specific). The WTRU can (e.g., optionally) store one or more portions in one or more corresponding buffers (e.g., update long-term buffers or short-term buffers or both).

[0303] Based on pre-configured conditions and measurements, the WTRU can select / recommend a second (e.g., preferred) TSF type and associated parameters (e.g., segment size, quantization associated with each segment). For example, the WTRU can determine the TSF type (e.g., preferred TSF type) based on one or more of the following: Based on measured channel parameters (e.g., Doppler effect, WTRU rate), the WTRU can determine the TSF type (e.g., preferred TSF type). For example, based on the estimated Doppler effect and comparing it to one or more thresholds, the WTRU can determine the type. (e.g., each) Doppler effect range can be mapped to a type (e.g., specific type). For example, TSF type 1 can be used for stable environments (e.g., no variation in WTRU rate). TSF type 4 can be used for dynamic (e.g., highly dynamic) environments (e.g., wide range of rates). Based on CSI measurements, the WTRU can determine the preferred TSF type. For example, the WTRU can compare the measured long-term / short-term SGCS with configured long-term / short-term SGCS thresholds to determine the identification of the long-term / short-term segments (e.g., fixed or variable).

[0304] WTRU can determine one or more parameters (e.g., portion size, portion-specific quantization information) associated with the selected type. The portion size associated with the selected type can be transmitted in one or more of the following formats: a percentage of the full size of the common portion, an increment z for the most recently transmitted overlapping portion. v (For example, it can be fully attached to the common part so that, for example, its size can be increased to z) c + z v Or attach it entirely to a specific part to increase its size to z. s +z v The number of potential representations / elements). Based on one or more of the following, WTRU can determine parameters associated with the selected type: WTRU rate (e.g., for high speed, reduce the common part size and increase the specific part size, and vice versa); CSI measurement (e.g., compare the measured short-term SGCS with the configured long-term SGCS threshold); long-term potential representation measurement (e.g., if there are differences in long-term potential representations generated from multiple consecutive CSI samples, reduce the common part size).

[0305] WTRU can report TSF compression CSI (e.g., compression using a configured first TSF type) and the selected second TSF type and associated parameters. WTRU can also report the TSF type index and associated parameters (e.g., size, number of parts, overlap information).

[0306] Although the features and elements described above are described in a specific combination, each feature or element may be used alone without other features and elements of the preferred embodiment, or in various combinations with or without other features and elements.

[0307] While the implementations described herein may take into account 3GPP-specific protocols, it should be understood that the implementations described herein are not limited to this and are applicable to other wireless systems. For example, while the solutions described herein take into account LTE, LTE-A, New Radio (NR), or 5G-specific protocols, it should be understood that the solutions described herein are not limited to this and are also applicable to other wireless systems.

[0308] The above processes can be implemented in computer programs, software, and / or firmware included in computer-readable media for execution by a computer and / or processor. Examples of computer-readable media include, but are not limited to, electronic signals (transmitted via wired and / or wireless connections) and / or 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, but not limited to, internal hard disks and removable disks), magneto-optical media, and / or optical media (such as CD-ROMs and / or DVDs). The processor associated with the software can be used to implement a radio frequency transceiver for use in WTRUs, terminals, base stations, RNCs, and / or any host computer.

Claims

1. A wireless transmit / receive unit (WTRU), comprising: The processor is configured as follows: Receive configuration information associated with Time-Space-Frequency (TSF) compression; Based on at least the configuration information and the measurements associated with CSI-RS, the first TSF parameter is determined; The second TSF parameter is determined based on at least the configuration information and the measurement values ​​associated with the CSI-RS; Based on the first TSF parameters, the first TSF compressed CSI portion is determined; Based on the second TSF parameter, the second TSF compressed CSI portion is determined; and Send to the network at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter.

2. The WTRU of claim 1, wherein the configuration information associated with TSF compression includes configuration parameters associated with TSF compression, wherein the configuration parameters associated with TSF compression include at least one of the following: the number of TSF compression CSI portions, the minimum CSI portion size, the maximum CSI portion size, or a portion allocation determination and a compression indication.

3. The WTRU as claimed in claim 1, wherein the configuration information associated with TSF compression includes report configuration information.

4. The WTRU of claim 1, wherein at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter is sent based on the report configuration information.

5. The WTRU of claim 1, wherein the first TSF parameter is at least one of a first size, an effective time, or a first quantization parameter, and wherein the second TSF parameter is at least one of a second size or a second quantization parameter.

6. The WTRU of claim 1, wherein the determination of the first TSF parameter is further based on the first measurement channel parameter or the first lookup table, and wherein the determination of the second TSF parameter is further based on the second measurement channel parameter or the second lookup table.

7. The WTRU of claim 1, wherein the first TSF compressed CSI portion is a long-term CSI portion and the first TSF parameter is associated with the long-term CSI portion, and wherein the second TSF compressed CSI portion is a short-term CSI portion and the second TSF parameter is associated with the short-term CSI portion.

8. The WTRU of claim 1, wherein the configuration information associated with TSF compression includes channel conditions determined with respect to the TSF portion, wherein the channel conditions are metric thresholds determined with respect to the TSF portion, and wherein the first TSF compression CSI portion is further determined based on the metric thresholds, and wherein the second TSF compression CSI portion is further determined based on the metric thresholds.

9. The WTRU as described in claim 8, wherein the metric threshold is one of a short-term performance metric threshold, a long-term performance metric threshold, or a combined performance metric threshold.

10. A method comprising: Receive configuration information associated with Time-Space-Frequency (TSF) compression; Based on at least the configuration information and the measurements associated with CSI-RS, the first TSF parameter is determined; The second TSF parameter is determined based on at least the configuration information and the measurement values ​​associated with the CSI-RS; Based on the first TSF parameters, the first TSF compressed CSI portion is determined; Based on the second TSF parameter, the second TSF compressed CSI portion is determined; and Send to the network at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter.

11. The method of claim 10, wherein the configuration information associated with TSF compression includes configuration parameters associated with TSF compression, wherein the configuration parameters associated with TSF compression include at least one of the following: the number of TSF compression CSI portions, the minimum CSI portion size, the maximum CSI portion size, or a portion allocation determination and a compression indication.

12. The method of claim 10, wherein the configuration information associated with TSF compression includes report configuration information.

13. The method of claim 12, wherein at least one of the first TSF compressed CSI portion, the first TSF parameter, the second TSF compressed CSI portion, or the second TSF parameter is sent based on the report configuration information.

14. The method of claim 10, wherein the first TSF parameter is at least one of a first size, an effective time, or a first quantization parameter, and wherein the second TSF parameter is at least one of a second size or a second quantization parameter.

15. The method of claim 10, wherein the determination of the first TSF parameter is further based on a first measurement channel parameter or a first lookup table, and wherein the determination of the second TSF parameter is further based on a second measurement channel parameter or a second lookup table.

16. The method of claim 10, wherein the first TSF compressed CSI portion is a long-term CSI portion and the first TSF parameter is associated with the long-term CSI portion, and wherein the second TSF compressed CSI portion is a short-term CSI portion and the second TSF parameter is associated with the short-term CSI portion.

17. The method of claim 10, wherein the configuration information associated with TSF compression includes channel conditions determined in relation to a TSF portion, wherein the channel conditions are metric thresholds determined in relation to a TSF portion, and wherein the first TSF compression CSI portion is further determined based on the metric thresholds, and wherein the second TSF compression CSI portion is further determined based on the metric thresholds.

18. The method of claim 17, wherein the metric threshold is one of a short-term performance metric threshold, a long-term performance metric threshold, or a combined performance metric threshold.

Images