Methods and apparatuses for variable length channel state information feedback obtained through compression with an encoder and output masks

Abstract

In an embodiment, a method, implemented in a WTRU for CSI comprises: receiving, from a network node, a first message comprising information for compression configuration indicating AIML model to generate a CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property; receiving, from the network node, a second message comprising information indicating a masking configuration and a post processing configuration; generating a latent vector with N parts; determining k parts out of the N parts of the latent vector for CSI feedback; performing post processing for the k parts according to the preconfigured association between each of the k parts and the corresponding post processing configuration; and transmitting, to the network node, a third message comprising the CSI feedback with k selected parts of the latent vector.

Description

METHODS AND APPARATUSES FOR VARIABLE LENGTH CHANNEL STATE INFORMATION FEEDBACK OBTAINED THROUGH COMPRESSIONWITH AN ENCODER AND OUTPUT MASKSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims the benefit of US Provisional Patent Application No. 63 / 525,413 filed July 7, 2023, which is incorporated herein by reference.FIELD OF THE INVENTION

[0002] The present disclosure is generally directed to the fields of communications, software and encoding, including, for example, to methods, architectures, apparatuses, systems directed to variable rate compression and variable length feedback. More particularly, the present disclosure relates to methods for a user equipment to enable variable length feedback for resource constrained transmission.BACKGROUND

[0003] In channel state information (CSI) autoencoder setup, the output of an encoder may be unstructured. For example, all the elements of latent vector may be equally important from a reconstruction perspective. This may lead to inflexibility for adapting the compressed CSI, e.g., to variable payload size, inefficient quantization, inefficient error protection.

[0004] There is a need to improve methods for CSI compression.SUMMARY

[0005] In an embodiment, a method, implemented in a wireless transmit / receive unit, WTRU, for compressing channel state information, CSI, may comprise a step of receiving, from a network node, a first message comprising information for compression configuration indicating artificial intelligence / machine learning, AIML, model to generate a CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. The method may further comprise a step of receiving, from the network node, a second message comprising information indicating a masking configuration and a post processing configuration. The method may further comprise a step of generating a latent vector with N parts. The method may further comprise a step of determining k parts out of the N parts of the latent vector for CSI feedback. The method may further comprise a step of performing post processing for the k parts according to the preconfigured association between each of the k parts and the corresponding post processing configuration; and a step of transmitting, to the network node, a third message comprising the CSI feedback with k selected parts of the latent vector.

[0006] In an embodiment, a method, implemented in a wireless transmit / receive unit (WTRU) for compressing channel state information (CSI), may comprise a step of receiving, from a networknode, a first message comprising information for compression configuration indicating artificial intelligence / machine learning, AIML, model to generate CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. The method may further comprise a step of receiving, from the network node, a second message comprising information indicating a masking configuration including a base mask and additional masks. The method may further comprise a step of generating a latent vector with N parts. The method may further comprise a step of determining k parts of the latent vector to be included in a first CSI report by applying the base mask on the latent vector. The method may further comprise a step of receiving an aperiodic CSI trigger including an implicit / explicit indication of a linked periodic CSI report and an additional mask. The method may further comprise a step of determining m parts of the latent vector to be included in a second CSI report by applying the addition al mask. On condition that the aperiodic CSI reporting resource may collide with the linked periodic CSI reporting resource, and on condition that the aperiodic CSI reporting resource size may fit with the m parts, the method may comprise a step of transmitting, to the network node, the m parts associated with the linked CSI report in a single CSI report.

[0007] In another embodiment, a method, implemented in a wireless transmit / receive unit (WTRU) the method may comprise a step of receiving, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations. The method may further comprise a step of selecting one masking configuration from the plurality of masking configurations. The method may further comprise a step of generating, by the encoder, a vector comprising a set of parts based on the selected masking configuration. The method may further comprise a step of determining a first subset of parts out of the set of parts of the vector. The method may further comprise a step of performing at least one or more post processing of the first subset of parts using at least one or more post processing configurations; wherein each post processing configuration of the at least one or more post processing configurations is associated with each part of the first subset of parts. The method may further comprise a step of generating a CSI feedback based on the post processed first subset of parts; and a step of transmitting, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration. The vector may be a latent vector.

[0008] The selection of one masking configuration may be based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback. The at least one or more post processingconfigurations may indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts. Performing at least one or more post processing of the first subset of parts may comprise performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of the first subset of parts. Performing quantization on each part of the first subset of parts may comprise a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts. Post processing of the first subset of parts may comprise using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts. The masking configuration may include any of a masking type, a masking domain, a mask length, and mask sets. Determining the first subset of parts may comprise selecting the subset of parts out of the set of parts based on UL resources.

[0009] The set of parts may satisfy preconfigured one or more properties. The preconfigured one or more properties may include any of an additive property, an ordering property, and associated performance threshold preconfigured for each part of the set of parts.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] A more detailed understanding may be had from the detailed description below, given by way of example in conjunction with drawings appended hereto. Figures in such drawings, like the detailed description, are examples. As such, the Figures (FIGs.) and the detailed description are not to be considered limiting, and other equally effective examples are possible and likely. Furthermore, like reference numerals ("ref.") in the FIGs. indicate like elements, and wherein:

[0011] FIG. 1 A is a system diagram illustrating an example communications system;

[0012] FIG. IB is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1 A;

[0013] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A;

[0014] FIG. ID is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1 A;

[0015] FIG. 2 is a block diagram illustrating an example of a two-sided artificial intelligence / machine learning (AI / ML) based channel state information compression framework according to an embodiment;

[0016] FIG. 3 is a block diagram illustrating an example of a pictorial representation of the variable bottleneck training according to an embodiment;

[0017] FIG. 4 is a block diagram illustrating an example of a pictorial representation of the variable bottleneck inference according to an embodiment;

[0018] FIG. 5 is a graph showing an example of a comparison between the effectiveness of the variable bottleneck method and the effectiveness multiple model switching;

[0019] FIG. 6 is a flow chart diagram illustrating an example of a NW-WTRU beam alignment method according to an embodiment;

[0020] FIG. 7 is a block diagram illustrating an example of two different options for a bit level masking according to an embodiment;

[0021] FIG. 8 is a block diagram illustrating an example of an end-to-end training performed to train an encoder, decoder and fully connected layers (Fl, F2) according to an embodiment;

[0022] FIG. 9 is a block diagram illustrating an example of an iterative nodes training according to one embodiment;

[0023] FIG. 10 is a flow chart diagram illustrating an example of a method, implemented in a WTRU for compressing channel state information according to an embodiment;

[0024] FIG. 11 is a flow chart diagram illustrating another example of a method, implemented in a WTRU, for compressing channel state information according to another embodiment; and

[0025] FIG. 12 is another flow chart illustrating another example of a method, implemented in a WTRU, for compressing channel state information according to another embodiment.DETAILED DESCRIPTION

[0026] In the following detailed description, numerous specific details are set forth to provide a thorough understanding of embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples may be practiced without some or all of the specific details set forth herein. In other instances, well-known methods, procedures, components and circuits have not been described in detail, so as not to obscure the following description. Further, embodiments and examples not specifically described herein may be practiced in lieu of, or in combination with, the embodiments and other examples described, disclosed or otherwise provided explicitly, implicitly and / or inherently (collectively "provided") herein. Although various embodiments are described and / or claimed herein in which an apparatus, system, device, etc. and / or any element thereof carries out an operation, process, algorithm, function, etc. and / or any portion thereof, it is to be understood that any embodiments described and / or claimed herein assume that any apparatus, system, device, etc. and / or any element thereof is configured to carry out any operation, process, algorithm, function, etc. and / or any portion thereof.

[0027] Hereinafter, ‘a’ and ‘an’ and similar phrases are to be interpreted as ‘one or more’ and ‘at least one’ . Similarly, any term which ends with the suffix ‘(s)’ is to be interpreted as ‘one or more’ and ‘at least one’. The term ‘may’ is to be interpreted as ‘may, for example’.

[0028] A sign, symbol, or mark of forward slash 7’ is to be interpreted as ‘and / or’ unless particularly mentioned otherwise, where for example, ‘A / B’ may imply ‘A and / or B’.

[0029] The methods, apparatuses and systems provided herein are well-suited for communications involving both wired and wireless networks. An overview of various types of wireless devices and infrastructure is provided with respect to FIGs. 1A-1D, where various elements of the network may utilize, perform, be arranged in accordance with and / or be adapted and / or configured for the methods, apparatuses and systems provided herein.

[0030] FIG. 1A is a system diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), singlecarrier FDMA (SC-FDMA), zero-tail (ZT) unique-word (UW) discreet Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block- filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0031] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a "station" and / or a "STA", may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi- Fi device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / oran automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0032] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, e.g., to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the networks 112. By way of example, the base stations 114a, 114b may be any of a base transceiver station (BTS), a Node-B (NB), an eNode-B (eNB), a Home Node-B (HNB), a Home eNode-B (HeNB), a gNode-B (gNB), a NR Node-B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0033] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in an embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0034] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0035] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal MobileTelecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink Packet Access (HSDPA) and / or High-Speed Uplink Packet Access (HSUPA).

[0036] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE- Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0037] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access, which may establish the air interface 116 using New Radio (NR).

[0038] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., an eNB and a gNB).

[0039] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 IX, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0040] The base station 114b in FIG. 1 A may be a wireless router, Home Node-B, Home eNode- B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish any of a small cell, picocell or femtocell.As shown in FIG. 1 A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106 / 115.

[0041] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 / 115 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1 A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing an NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing any of a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or Wi-Fi radio technology.

[0042] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 / 114 or a different RAT.

[0043] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0044] FIG. IB is a system diagram illustrating an example WTRU 102. As shown in FIG. IB, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130,removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0045] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. IB depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, e.g., in an electronic package or chip.

[0046] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0047] Although the transmit / receive element 122 is depicted in FIG. IB as a single element, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0048] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11, for example.

[0049] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquidcrystal display (LCD) display unit or organic light-emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), readonly memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0050] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, and the like.

[0051] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0052] The processor 118 may further be coupled to other elements / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality and / or wired or wireless connectivity. For example, the elements / peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (e.g., for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, and the like. The elements / peripherals 138 may include one or more sensors, the sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocation sensor; an altimeter, a lightsensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0053] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for both the uplink (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 via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the uplink (e.g., for transmission) or the downlink (e.g., for reception)).

[0054] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0055] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0056] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the uplink (UL) and / or downlink (DL), and the like. As shown in FIG. 1C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0057] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements are depicted as part of the CN 106, it will be appreciated that any one of these elements may be owned and / or operated by an entity other than the CN operator.

[0058] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an SI interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function forswitching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0059] The SGW 164 may be connected to each of the eNode-Bs 160a, 160b, 160c in the RAN 104 via the SI interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0060] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0061] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0062] Although the WTRU is described in FIGs. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0063] In representative embodiments, the other network 112 may be a WLAN.

[0064] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have an access or an interface to a distribution system (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA. The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to-peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802. l ie DLS or an 802.1 Iz tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not havean AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an "ad-hoc" mode of communication.

[0065] When using the 802.1 lac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width via signalling. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier sense multiple access with collision avoidance (CSMA / CA) may be implemented, for example in in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0066] High throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadj acent 20 MHz channel to form a 40 MHz wide channel.

[0067] Very high throughput (VHT) STAs may support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two non-contiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse fast Fourier transform (IFFT) processing, and time domain processing, may be done on each stream separately. The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above-described operation for the 80+80 configuration may be reversed, and the combined data may be sent to a medium access control (MAC) layer, entity, etc.

[0068] Sub 1 GHz modes of operation are supported by 802.1 laf and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.1 laf and 802.1 lah relative to those used in 802.1 In, and 802.1 lac. 802.1 laf supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV white space (TVWS) spectrum, and 802.1 lah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.1 lah may support meter type control / machine-type communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g., only support for) certain and / or limited bandwidths. TheMTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0069] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.1 In, 802.1 lac, 802.11af, and 802.1 lah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.1 lah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode), transmitting to the AP, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0070] In the United States, the available frequency bands, which may be used by 802.1 lah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.1 lah is 6 MHz to 26 MHz depending on the country code.

[0071] FIG. ID is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0072] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP)technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0073] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., including a varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0074] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non-standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b, 102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0075] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards user plane functions (UPFs) 184a, 184b, routing of control plane information towards access and mobility management functions (AMFs) 182a, 182b, and the like. As shown in FIG. ID, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0076] The CN 115 shown in FIG. ID may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one session management function (SMF) 183a, 183b, and at least one Data Network (DN) 185a, 185b. While each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0077] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of NAS signalling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b, e.g., to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and / or the like. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0078] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP -based, non-IP based, Ethernet-based, and the like.

[0079] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, e.g., to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multihomed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, and the like.

[0080] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local DataNetwork (DN) 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0081] In view of FIGs. 1 A-1D, and the corresponding description of FIGs. 1 A-1D, one or more, or all, of the functions described herein with regard to any of WTRUs 102a-d, base stations 114a- b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a- b, SMFs 183a-b, DNs 185a-b, and / or any other element(s) / device(s) described herein, may be performed by one or more emulation elements / devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0082] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation device (e.g., a network node) may be directly coupled to another device for purposes of testing and / or may performing testing using over-the-air wireless communications.

[0083] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a network node (e.g., wired and / or wireless communication network). For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0084] Referring to Fig. 2, an artificial intelligence / machine learning (AI / ML) framework for CSI compression may consist of a two-sided model, where the CSI compression may be performed at the WTRU side, the compressed CSI may be fed back to the network (NW) and decompressed (restored) at the NW-side. The WTRU side processing for CSI compression may consist of a ML encoder (possibly preceded by a pre-processing stage); similarly, the NW side processing may consist of a ML decoder (possibly followed by a post-processing stage if pre-processing is employed at the WTRU). The ML encoder operating in conjunction with a corresponding ML decoder may be referred to as an autoencoder (AE).

[0085] The ML encoder and ML decoder part of the AE may be trained either separately or jointly, using a training dataset. Typically, training of the ML models may be performed offline, prior to deploying the models at the nodes (WTRUs and / or gNB). During regular operation (e.g., at inference time), it is possible that depending on the available bandwidth the number of bits allocated for the feedback associated with the CSI maybe changed by the WTRU or the network. To accommodate for such settings, typical systems rely on having multiple models, each of which operate with a different feedback length. The current invention may propose method and signaling mechanisms to reduce the need for having multiple models for variable length feedback and may introduce strategies to accomplish the task with a single AI / ML model.

[0086] In various embodiments described below, CSI feedback may be used as an example. More generally, the various embodiments may be applicable to any transmission, including data transmission or any other feedback, reports, measurement results or the likes. In the various embodiments described below, AIML is used as an example. More generally, the various embodiments may be applicable to any non-AIML based transmissions.

[0087] In an embodiment, training may be masked. Embodiments relative to the training are not limited to a specific model architecture, it can be applied to any AIML model architecture. Any model may take advantage of a variable rate compression scheme by applying a training process principles described herein.

[0088] Configuration aspects for the training process may be as follows: (i) encoder and decoder model architectures. The models maybe initialized with some pre-training or may need to be trained from scratch, (ii) Training Data and the required loss function, (iii) The set of training masks and the corresponding probability with each mask. The training masks may define the granularity at which the compression rate and the feedback can be varied. All masks have at least one element as 1. Thus, allowing information to pass through, (iv) For example, one set of training masks for a 4 dimensional latent may look like (1,0, 0,0), (1, 1,0,0), (1,1, 1,0), (1,1, 1,1) with equal probability to each mask. In all these masks, the 1 st element may be ‘ L indicating that irrespective of the mask being selected, 1st element of z is the most important and most informative, an example, the 1st element can be considered to be ‘ L in each of indicating that irrespective of the mask being selected, 1st element of z is the most important and most informative. Similarly, the 2nd element may have the next highest occurrence, thus ensuring it’ s the next most informative element, followed by the 3rd and 4th element, (v) At each training iteration, for each CSI in the training batch, a mask from the given set of training masks may be selected with the associated probability. The selected mask may be applied to the latent vector received as the output of the encoder, for example by element wise multiplication between the latent vector and the mask.

[0089] Referring to Fig. 3, during training, masks may be randomly selected and may be applied to the latent variable z. Referring to Fig. 4, during inference, as per available feedback overhead, elements may be selected from the most important to the last important (as didacted by the masking).

[0090] Referring to Fig. 5, the effectiveness of the variable bottleneck method may be compared to multiple model switching. The combined model, represented by the square symbol curve, shows the inference performance of a single model trained with the variable bottleneck approach for different bottleneck or latent dimensions. The circle symbol curve indicates the performance of multiple individual models trained specifically and independently for each bottleneck dimension.

[0091] Referring to Fig. 6, masking and training at bit level is shown. Accordingly, a post quantization masking is processed: quantize fist and then perform masking in bit space. Referring to Fig. 6, masking may be done after quantization step in the bit space.

[0092] Regarding bit-level granularity. In the embodiment shown at Fig. 6, the priority of bits may be explicitly indicated via the masks. Highest priority bits may be transmitted with highest priority. Different masking formats may result in different performances, even if the model is same.

[0093] Referring to Fig. 7, at least two different options for the bit level masking may be possible. In the ‘right’ setup, since the masking is spread across the vector, it may (e.g., potentially) better leverage the weights in the last layer of the encoder towards the compression task.

[0094] For an incremental training, configuration aspects for the training process may be as follow: (i) encoder and decoder model architectures. The models maybe initialized with some pretraining or may need to be trained from scratch, (ii) Training Data and the required loss function.

[0095] A two incremental stage training may be as follow:

[0096] Referring to Fig. 8, at the first stage, two fully connected layers, each with N nodes, may be added between the encoder and decoder models. Where N is the maximum dimensionality of the latent vector. For this model structure, end-to-end training is performed.

[0097] At a second stage: (i) The encoder and decoder models may be frozen (no weight updates possible). The two fully connected layers may be scrapped, (ii) Two fully connected layers, with number of nodes equivalent to minimum possible length of latent, may be added one after the ‘frozen’ encoder and one before the ‘frozen’ decoder, (iii) The training may be performed to update the two fully connected layers with the encoder and decoder kept frozen, (iv) Once the training completes, the trained nodes in the fully connected layers may be frozen, (v) New nodes may be incrementally introduced to the two fully connected layers based on the desired increment in the latent vector dimension. Steps (iii), (iv) and (v) may be repeated until the fully connected layers reach the desired maximum dimension N.

[0098] Referring to Fig. 9, at the second stage, training may be performed to iteratively train the nodes in (Fl, F2) layers and the encoder and decoder models may be kept frozen. As an example, in (a) only a single node is trained; in (b) the first trained node is frozen, and the second node is trained; and in (c) all nodes trained earlier are frozen and only the newly added fourth node is trained.

[0099] In an embodiment, CSI compression may comprise ordered CSI compression for variable length feedback. A latent vector generated by a baseline encoder for CSI compression may not offer any flexibility in terms of partial transmission and decoding e.g., the latent vector can only be decoded if the entire latent vector is available, if only a few elements of the latent vector are available, then it is not decodable. Having the flexibility offered by a solution that enables a WTRU to generate a compressed CSI with N ordered parts where the decoder can reconstruct the CSI with k parts (k<N), may be highly beneficial.

[0100] In an embodiment, the WTRU side AIML model (encoder) may compress the CSI into N ordered parts and selects k out of N parts based on pre-defined configurations or conditions. It may further apply post processing on the selected parts and may transmit the k parts.

[0101] In an embodiment, a WTRU may be configured with an AIML model (encoder) to generate a CSI feedback, wherein the AIML model may take in a channel matrix of dimensions NtX NrX Nswhere, Ntrepresent the number of transmit antennas, Nrrepresent the number of receive antennas and Nsrepresent the number of sub-carriers or sub-bands or resource blocks (RBs). The model may then output a latent vector with N parts, where each part may have multiple elements, or a single element and each element maybe represented by one or more bits.

[0102] In a solution, the N part latent may satisfy some preconfigured properties making the CSI feedback conducive for variable bottleneck or variable length feedback, wherein for a given estimated channel, the channel can be compressed such that the N part latent may be partially and independently decodable.

[0103] In an embodiment, a preconfigured property in the N part latent maybe related to a relationship between the N parts. The N parts may be correlated, uncorrelated or independent of each other in their raw form or in a mapped form w.r.t to a non-linear function. In an embodiment, the pre-configured property may be related to specific reconstruction loss function for example NMSE, SGCS, etc. such that the each latent may satisfy a minimum performance threshold w.r.t to reconstruction loss function.

[0104] Additionally, in an embodiment, the WTRU maybe configured to generate a latent which may satisfy additional pre-configured properties. The N part latent may satisfy an ordering property w.r.t the reconstruction, such that given N parts of the latent vector, reconstruction performance (defined by any cost function for example MSE, NMSE, SGCS, etc. ) of the latentvector with ithpart may be greater than reconstruction performance of jthpart, wherein i<j . Thus enabling ranking of the latent and ensuring that some parts of the latent maybe more important than other parts.

[0105] In an embodiment, the pre-configured property of the N part latent maybe required to satisfy an additive property, such that the reconstruction performance may be monotonically increased with addition of more parts of latent for reconstruction by the decoder AIML model. The increase in performance with addition of new parts for reconstruction may or may not be linear. Additionally, the ordering of N parts may or may not be required to satisfy the additive property.

[0106] To enable the training and inference of such an ordered, variable length feedback additional configurations may be necessary. These configurations may include, but are not limited to :

[0107] (i) Masking: To enable training and inference of a AIML model capable of variable length feedback, and that satisfies the required pre-configured properties, the required structural configuration needs to be induced into the model. This can be enabled through the use of masks. Without loss of generality, the N part latent can be considered as an N-length vector, wherein each part maybe represented with 1 or more elements. Thus, in a solution, the mask is also a N part binary vector or 0 or 1 values. In a solution, this mask may be element wise multiplied with the latent vector to mask some elements of the latent. The masked elements or the elements which were multiplied with 0 values from the mask vector, do not have to be transmitted as part of the feedback, thus effectively reducing the feedback.

[0108] (ii) Masking Configuration: In a solution the type of masks utilized for training may be the same or different from the ones utilized for inference. In a solution, the set of inference masks maybe a subset of the training masks. In a solution the masking configuration parameter may thus additionally be signaled to define the training Masks and inference masks.

[0109] (iii) Training Masks: During training, a larger set of masks may be typically utilized to ensure every combination of the N part latent that may be encountered during inference time has been utilized in training. In a solution, the training masks may be additionally accompanied with a probability distribution, which indicates the probability associated with selection of each mask at training. In a solution, during training, the masks are selected with the specified probability distribution to enforce the required pre-configured properties. In a different solution, the masks can be expressed as the length of the latent vector to be transmitted, this would assume a predefined and explicit ordering of the parts, such that just the number of parts to be transmitted (k) can uniquely identify which parts need to be transmitted.

[0110] (iv) Inference / Transmission masks: During the inference stage the UE may be configured with the transmission masks associated with potential transmission formats. During each reporting,one of these masks, as signaled by NW or as determined by UE maybe applied to get a reduced dimensional representation of the latent. In a solution, instead of explicitly defining masks associated with the variable length feedback, just the value, k, which is the number of parts to be transmitted maybe defmed / estimated / configured. Similarly, in another solution, training masks could also leverage the length-based training / masking. Thus, instead of defining individual masks, just the first k-parts maybe transmitted and other parts maybe masked.

[0111] (v) Masking Domain: As defined so far, a N length masking vector is utilized wherein each part can either be completely masked or not. In a solution, the masking operation could be more granular, such that even within each part, some bits maybe masked while others not being masked. Thus, the masking maybe performed at a part level or a bit level, for finer granularity.

[0112] (vi) Mask Length- In a solution, the mask length maybe equivalent to the number of parts. In another solution, the mask length maybe smaller than the number of parts, where in by default the mask could be extended to N length by adding Os to the top or to the bottom of the mask vector as specified by an offset parameter. In another solution, the mask extension maybe performed based on some other heuristic or function based on some other properties of the model (if multiple models are available, each model may have a specific rule associated with it) or CSI (based on some properties of the CSI like doppler, delay-spread, etc. and each part associated with a specific property).

[0113] (vii) Mask Sets: Each mask set contains multiple masks. In a solution, the masks may be defined specifically for training or for inference or for both. The training masks maybe a superset of the inference masks. In another solution the mask set maybe defined as a base mask with other masks defined in relation with the base mask. For example, other masks maybe relative shifted version of the base mask or relative masked version of the same mask. In another solution, the mask set may have N or more than N or less than N masks, where each mask results in a different subset of the latent being masked. No two masks within a set may result in the same latent for transmission. In a solution, the mask set maybe closely tied to a given encoder-decoder model. Thus, if the encoder -decoder pair is changed, the mask set may need to be changed. In another solution, the mask set may be tied to the loss function or reconstruction performance criterion. For a given model different masks sets may be associated with different performance criterion.

[0114] For a setting with N = 4, some example mask sets are given as :

[0115] (i) First mask set may contain: maskl(l, 0,0,0), mask2(0, 1,0,0), mask3(0, 0,1,0), mask4 (0,0,0, 1). Here, each mask may enable transmission of only 1 element.

[0116] (ii) Second mask set may contain: maskl (1,0, 0,0), mask2 (1, 1,0,0), mask 3 (1,1, 1,0), mask4 (1,1, 1,1). Here the masks progressively increase the length of feedback.

[0117] (iii) Third mask set may contain: maskl (1, 1,0,0), mask2 (1,1, 1,1). The mask set can be of length smaller than or larger than N.

[0118] (iv) Fourth mask set may contain: maskl (1, 1,0,0), mask2 (0,0, 1,1). The mask sets may have masks with overlapping Is or non-overlapping Is.

[0119] In an embodiment, wherein a WTRU may be configured with an AIML based encoderdecoder pair capable of variable length feedback, the encoder model may be assumed to take as an input a channel matrix and output a latent vector with N parts, where each part may have multiple elements, or a single element and each element maybe represent by 1 or more bits. The WTRU may select k parts (where, k<N) for post processing and data transmission. The determination of the k part can be done based on several different methods.

[0120] In an embodiment, the value of k may be specifically defined by the gNB or more than 1 options for k maybe defined by gNB, and the WTRU maybe allowed to select from these options.

[0121] In an embodiment, the WTRU may use the information based on available uplink resources to determine the value of k. The WTRU may select k such that the transmission overhead is less than the available uplink resources. In another embodiment, k value may be determined by the priority of the CSI report. If a CSI report has a high priority associated with it, a large value of k may be utilized and if the priority associated with the CSI report is low, a low value of k maybe utilized for reconstruction.

[0122] In another embodiment, the compression factor or compression ratio as indicated by the gNB or as determined by the WTRU maybe utilized to select the value of k. In another solution, a statistically derived function mapping the value of k to a performance criterion (NMSE, SGCS, throughput, etc.) may be utilized to select k based on the required level of performance. In another solution the ACK / NACK count or the link performance can be utilized to increase or decrease the values of k during CSI transmission.

[0123] In an embodiment, the WTRU may determine the value of k based on implicit SU- MIMO / MU-MIMO determination via DMRS configuration (RE muting).

[0124] In an embodiment, the determination of k can be based on the parameters associated with the channel (dimensionality, rank, etc.) or based on explicit features extracted from the channel (delay spread, doppler, variability of these parameters, etc.) or implicit features derived based on a machine learning or deep learning function. Further a machine learning or deep learning function may utilize these features to predict / estimate k or the parts of the latent vector to be transmitted.

[0125] Based on the derived value of k, the WTRU may identify the appropriate mask to select the best k out of N parts. It then may apply this mask to the latent vector and may determine the k part of the latent most suited for transmission.

[0126] In an embodiment, wherein a WTRU is configured with an AIML based encoder-decoder pair capable of variable length feedback, the encoder model may be assumed to take as an input a channel matrix and output a latent vector with N parts, where each part may have multiple elements, or a single element and each element maybe represent by one or more bits. The WTRU may select k parts (where, k<N) for post processing and data transmission. The determination of the k part can be done based on several different methods.

[0127] In an embodiment, the value of k may be specifically defined by the gNB or more than one options for k maybe defined by gNB, and the WTRU maybe allowed to select from these options.

[0128] In an embodiment, the WTRU may use the information based on available uplink resources to determine the value of k. The WTRU may select k such that the transmission overhead is less than the available uplink resources. In another embodiment, k value may be determined by the priority of the CSI report. If a CSI report has a high priority associated with it, a large value of k may be utilized and if the priority associated with the CSI report is low, a low value of k maybe utilized for reconstruction.

[0129] In another embodiment, the compression factor or compression ratio as indicated by the gNB or as determined by the WTRU maybe utilized to select the value of k. In another embodiment, a statistically derived function mapping the value of k to a performance criterion (NMSE, SGCS, throughput, etc.) may be utilized to select k based on the required level of performance. In another embodiment the ACK / NACK count or the link performance can be utilized to increase or decrease the values of k during CSI transmission.

[0130] In an embodiment, the WTRU may determine the value of k based on implicit SU- MIMO / MU-MIMO determination via DMRS configuration (RE muting).

[0131] In an embodiment, the determination of k can be based on the parameters associated with the channel (dimensionality, rank, etc.) or based on explicit features extracted from the channel (delay spread, doppler, variability of these parameters, etc.) or implicit features derived based on a machine learning or deep learning function. Further a machine learning or deep learning function may utilize these features to predict / estimate k or the parts of the latent vector to be transmitted.

[0132] Based on the derived value of k the WTRU may identify the appropriate mask to select the best k out of N parts. It then applies this mask to the latent vector and determines the k part of the latent most suited for transmission.

[0133] In an embodiment, the WTRU may be configured to indicate one or more parameters associated with AIML models (encoder / decoder) used for CSI processing. The indication of parameters relates to one or more aspects associated with the output dimension, also referred to as latent vector, of the AIML encoder used for the CSI generation part, wherein the latent vector maybe composed of a maximum of N parts, where each part may represent a bit or multiple bits, or one or more floating-point or fixed-point number possibly quantized using a number of bits.

[0134] The parameters associated with the latent vector may include one or more of the following: (i) the number of selected parts (fc < IV) to indicate from the latent vector, (ii) the post processing (e.g., quantization method) applied to each of the k parts, (iii) encoding information associated with each of the k parts, and (iv) the generated CSI associated with the k selected parts. The indication of the latent vector parameters may be done using implicit signaling, explicit signalling, or a combination of both.

[0135] In another embodiment, the WTRU may report the parameters associated with each of the k parts, which may include any of the number of bits associated with each of the k parts, the number of bits utilized to quantize each parts, and the number of error correction bits for each of the k parts.

[0136] In an embodiment, the indication of the AI / ML encoder parameters may be done using implicit signaling. For example, the WTRU may have reserved UL resources in the time-frequency grid for reporting the generated CSI, wherein the number of available UL resources may implicitly be used for indicating the number of selected parts (k). In another embodiment, the WTRU may be configured with PUCCH resource sets, possibly with multiple PUCCH resource configurations with different formats and time / frequency locations. Upon receiving a DCI triggering PUCCH transmission (e.g., aperiodic CSI report), the WTRU may select a certain format to implicitly indicate the preferred parameters associated with the latent vector.

[0137] In another embodiment, the WTRU may be configured to report preferred / updated latent vector parameters upon receiving an explicit request from the network. For example, the WTRU may be configured with a CSI reporting format associated with one set of latent vector parameters. For example, the WTRU may receive an aperiodic CSI report trigger from the NW. For example, as a response the WTRU may transmit the preferred latent vector parameters. In a solution, the aperiodic request trigger may indicate what latent vector parameters can be indicated in the report.

[0138] In an embodiment, a WTRU may be configured to report the preferred latent vector parameters periodically. For example, the WTRU may be configured with periodic UL resources to report the latent vector parameters. In another embodiment, the WTRU may be configured with PUCCH resources for reporting the latent vector parameters. In an embodiment, the WTRU may be configured to report the latent vector parameters as part of CSI feedback reporting, probably transmitted on multiple parts. For example, the first part may be used to indicate the latent vector parameters including the number of selected parts (fc), the postprocessing information, and the encoding information while the second part may contain the generated CSI information associated with the selected k parts.

[0139] In another embodiment, a WTRU may be configured to report the latent vector parameters based on one or more trigger conditions. For example, the WTRU may be preconfigured with a defined mapping between a set of latent vector parameters each indexed with a logical ID. For example, parameters including a specific k along with specific quantization and encoding methods may be defined by a logical ID. The WTRU may report the preferred latent vector parameters by selection and / or indication of one of the preconfigured latent vector parameters from the preconfigured set. In an embodiment, the WTRU may indicate a new set of the latent vector parameters if the performance (e.g., BLER or a number of consecutive ACK / NACKs) does not meet a preconfigured threshold condition.

[0140] Currently, a latent vector generated by a baseline encoder for CSI compression may not offer any flexibility e.g., partial latent may not be decodable. According to an embodiment, a WTRU may be configured to 1) generate CSI with N ordered parts (which is compatible with the decoder), 2) select k out of N parts based on a condition, 3) apply post processing based on selected parts, 4) transmit k parts. Even if it is assumed completely offline training, for interoperability, the specification and / or gNB may have to define the latent structure and any subsequent behavior with respect to differentiated handling of different parts of this latent vector. More particularly, in a embodiment, the WTRU may perform any of the following streps:

[0141] The WTRU may be configured to generate CSI feedback with AIML model (e.g., encoder); wherein the AIML model may output a latent vector with N parts that satisfy a preconfigured property. The preconfigured property may be expressed as model performance with reference to ordered parts of the latent vector. The WTRU may be configured with an association between N parts of the latent vector and N performance thresholds (e.g., SGCS thresholds).

[0142] The WTRU may receive one or more of the following configurations. A masking configuration and a set of post-processing configuration.

[0143] The masking configuration may comprise masking type, masking domain (element level and / or bit level), mask length, and mask sets.

[0144] For masking type, (1) masks with a training mask type may be applied during the AIML model training. A mask set with training mask type may be associated with additional conditions e.g., priority / probability of selection during the training procedure.

[0145] For masking type, (2) masks with a transmission mask type may be applied during CSI feedback generation / transmission. Alternately instead of a transmission mask, the size and / or latent vector part to be transmitted can be configured explicitly (to accommodate the incremental training procedure).

[0146] For mask length (<=N), by default, mask length may be equaled to a maximum latent vector length. Some rules to determine the mask length may be based on latent vector dimension (model switching) / input dimension (scalability).

[0147] For mask sets, each mask set may have a plurality of masks according to preconfigured pattern. E.g., first mask set may contain: maskl(l, 0,0,0), mask2(0, 1,0,0), mask3(0, 0,1,0), mask4 (0,0,0, 1) (where N=4 in this example). E.g., second mask set may contain: maskl (1,0, 0,0), mask2 (1, 1,0,0), mask 3 (1,1, 1,0), mask4 (1,1, 1,1). E.g., third mask set may contain: maskl (1, 1,0,0), mask2 (1,1, 1,1). E.g., fourth mask set may contain: maskl (1, 1,0,0), mask2 (0,0, 1,1). A Mask set may be configured as training mask type or transmission mask type or both. A mask set may have a base mask, each element in the set may be defined as shifts of the base mask. Each of the transmission mask sets may have up to N masks and each mask may correspond to different viable parts of the latent that can be independently transmitted. Masks determination may be as function of gNB decoder model availability / capability. The WTRU may have multiple encoders - mask specific. E.g., functionality based.

[0148] In various embodiment, mask may be expressed as the length of the latent vector to be transmitted can be configured (assumes consecutive ordering of the parts).

[0149] For a set of post-processing configuration (<=N), an association between each latent vector part and a (e.g., specific) post processing configuration corresponding to the part may be processed, wherein the post-processing configuration may include quantization configuration, encoding configuration etc.

[0150] The WTRU may generate latent vector with N parts - wherein the N parts may satisfy one or more of the following:

[0151] (i) The N parts may satisfy a first property / additive property. E.g., given N parts of the latent vector, reconstruction performance of the latent vector with i+1 parts are greater than reconstruction performance with i parts.

[0152] (ii) The N parts may satisfy a second property / ordering property. E.g., given N parts of the latent vector, reconstruction performance of the latent vector with ithpart is greater than reconstruction performance of jthpart, wherein i<j .

[0153] (iii) Each part in the N part latent vector may satisfy the associated performance threshold (e.g., squared generalized cosine similarity (SGCS)) preconfigured for that part.

[0154] The WTRU may determine k parts out of N part latent vector for CSI feedback, wherein the determination may be based on implicit methods, explicit methods or hybrid methods.

[0155] For implicit methods: (i) E.g, rules may be based on available UL resources, wherein the selection of a maximum number of parts is lower than the available resources, (ii) E.g., prioritization rules wherein a number of parts as a function of priority of CSI report (i.e., higher kvalue for high priority CSI report and low k value for low priority CSI report), the first part (within k ordered parts) may be higher priority than second part (within k ordered parts) and so on. (iii) E.g., input / latent dimension comprising mapping between input and / or latent dimension to the number of parts k. (iv) E.g., compression factor wherein the number of parts may be as a function of compression factor, (v) E.g., performance metric comprising any of reconstruction performance, distance metric, link performance, ACK / NACK count, etc... (vi) E.g., based on (implicit) single user multiple input multiple output (SU-MIMO) / multiple user multiple input multiple output (MU-MIMO) determination via demodulation reference signal (DMRS) configuration (RE muting), (vii) E.g., based on rank (in case of EV - masks can be configured per layer), (viii) Based on one or more of the implicit methods, wherein the WTRU may determine a transmission-mask- type mask and may apply the mask on latent vector for transmission.

[0156] Explicit methods may comprise any of CSI reporting configuration and masking configuration (e.g., transmission mask set and / or mask thereof)

[0157] For hybrid method, the WTRU may apply implicit method to determine ki and then may apply explicit method to determine k.

[0158] The WRU may apply different post processing for each of the k parts according to the preconfigured association between each of the k parts and the corresponding post processing configuration. As an example, the WTRU may apply a first quantization for the first part, second quantization for the second part etc. Since the 1stpart is the most important, it may be quantized with the highest bits and the kthpart may be quantized with the lowest number of bits. As another example, the WTRU may apply a first encoding configuration for the first part, second encoding configuration for second part etc. The first encoding configuration may include better error protection (more redundancy) than the second encoding configuration.

[0159] The WTRU may transmit CSI feedback with k selected parts of the latent vector. The CSI feedback may indicate the number of parts (k) of latent vector contained in CSI report.

[0160] Currently, a latent vector generated by a baseline encoder for CSI compression does not offer any flexibility in terms of incremental transmission e.g., sending additional parts of latent vector may not improve the quality of reconstruction. In an embodiment, the structure of the latent may be predefined or preconfigured for the WTRU. Possibly one or more WTRU behavior may be configured as a function of the structure of the latent. In an embodiment, the WTRU may be configured to transmit CSI with progressively increasing resolution. For example, different parts of latent may contribute to different reconstruction performance. This solution may enable the WTRU to generate CSI with N parts that are additive (which is compatible with the decoder), to initially send k parts. The WTRU may receive a trigger to transmit additional parts for a linkedCSI report (e.g., for scheduling or performance monitoring), and to send k+1 to k+m parts associated with linked CSI report.

[0161] In an embodiment, the WTRU may be configured to transmit more than one CSI report associated with the same CSI-RS reference resource. Possibly different CSI report associated with the same CSI-RS reference resource may carry different parts of the latent vector.

[0162] A WTRU may be configured to transmit CSI feedback as a function of generated latent vector, wherein the latent vector may satisfy one or more preconfigured property. In an embodiment, the latent vector may be an output of an encoder AIML model. The encoder AIML model may be designed and / or trained such that the generated latent vector may satisfy one or more preconfigured property. In a solution the preconfigured property may enable generation of latent vector with N parts. In a solution, the value of N may be preconfigured for a WTRU. In another embodiment, the value of N may be a function of input dimension, channel bandwidth, sub band size, carrier frequency range, etc. In another embodiment, the value of N may be a function of AIML model type, size, complexity and / or WTRU capability etc. In another embodiment, the value of N may be a function of decoder AIML model, configuration received from gNB and / or UL feedback resource configuration / availability etc.

[0163] In an embodiment, the preconfigured property may be expressed as model performance with reference to different parts of the latent vector. In an embodiment, the preconfigured property may be associated with ordering of the different parts of the latent vector. For example, the preconfigured property may ensure that the generated parts of the latent vector are ordered. In an embodiment, the preconfigured property may ensure that the different parts of the latent vector may be additive. For example, the preconfigured property may ensure that the performance of reconstruction may degrade (e.g., gracefully) as a function of the size and / or number of transmitted parts of the latent vector.

[0164] In an embodiment, the WTRU may be configured with association between different parts of the latent vector and the model performance requirement (e.g., reconstruction performance when using those parts for feedback). The WTRU may be configured to generate latent vector such that different parts of the latent vector satisfy the model performance requirement. Possibly the association between the one or more parts of N part latent vector and the performance threshold. Possibly the performance threshold may be expressed as SGCS difference between uncompressed channel state information and the reconstructed channel state information. Possibly the performance threshold may be expressed as minimum mean square error (MMSE) between uncompressed channel state information and the reconstructed channel state information. Possibly the performance threshold may be expressed as throughput difference between baseline channel state information feedback and the latent vector-based channel state information.

[0165] In an embodiment, the WTRU may be configured with one or more mask configuration associated with generation of CSI feedback from the latent vector. For example, the WTRU may determine the different parts of the latent vector based on the mask configuration. For example, the WTRU may apply the mask on the AIML model output to get the different parts of latent vector.

[0166] In an embodiment, the WTRU may be configured with a first mask and second mask. For example, the first mask may be base mask and the second mask may be an additional mask. For example, the base mask may be applied on the latent vector to generate a CSI feedback that meets minimum performance requirements. For example, the WTRU may apply a first mask on the latent vector to generate a first CSI report and apply a second mask on the same latent vector to generate a second CSI report. For example, the additional mask may be applied on the latent vector to generate a CSI feedback that may enhance the performance of CSI feedback in addition to the performance achieved with CSI feedback with base mask.

[0167] In an embodiment, the WTRU may receive mask configuration in a RRC signaling (e.g., RRC setup, RRC reconfiguration, RRC resume etc.). For example, the mask configuration may be a part of CSI-MeasConfig. For example, the WTRU may receive a first CSI reporting configuration with base mask and a second reporting configuration with an additional mask. For example, the WTRU may be configured with a first set of trigger conditions upon which the WTRU may transmit a CSI feedback according to the first CSI reporting configuration. For example, the WTRU may be configured with a second set of trigger conditions upon which the WTRU may transmit a CSI feedback according to the second CSI reporting configuration.

[0168] In an embodiment, the base mask may be associated with periodic CSI reporting configuration and additional mask may be associated with aperiodic CSI reporting configuration. In another embodiment, the base mask may be associated with semi-persistent CSI reporting configuration and additional mask may be associated with aperiodic CSI reporting configuration. In another embodiment, the base mask may be associated with a periodic CSI reporting configuration and additional mask may be associated with semi-persistent CSI reporting configuration.

[0169] In an embodiment, the WTRU may determine a linkage between the first CSI report and the second CSI report based on explicit configuration. For example, the WTRU may receive a CSI-MeasConfig containing explicit linkage information. For example, the explicit linkage information may include an information element (IE) indicating that the first and second report configuration identifiers (IDs) are linked, wherein the first report configuration ID may be associated with base mask and second report configuration ID may be associated with additional mask. For example, the explicit linkage information may include an IE indicating that a first set ofmasks and a second set of masks, and one or more masks from the first set may be linked to one or more masks from the second set. Possibly the first set of masks may be associated with base masks and second set of masks may be associated with additional masks.

[0170] The WTRU may be configured to determine and / or report one or more parameters associated with the AIML model (e.g., encoder) output, also referred to as latent vector, wherein the latent vector may be composed of N ordered parts and may be satisfying one or more property. For example, the N parts may satisfy a first property - additive property - e.g., given N parts of the latent vector, reconstruction performance of the latent vector with i+1 parts are greater than reconstruction performance with i parts. For example, the N parts may satisfy a second property / ordering property, e.g., given N parts of the latent vector, reconstruction performance of the latent vector with Ithpart is greater than reconstruction performance of jthpart, wherein i < j.

[0171] In an embodiment, the WTRU may be configured to determine and / or generate multiple linked CSI reports, wherein the linked CSI reports correspond to the same input CSI (e.g., full channel matrix) but transmitted at different time stamps. For example, a first CSI report may compose of the first k parts of the latent vector and transmitted at TTI n0while a second CSI report may compose of additional m parts (e.g., from k+1 to k+m) and transmitted at TTI n^, and the channel may be assumed to be roughly the same between n0and n1. The WTRU may be configured to determine and / or report the parameters (e.g., size of the latent, postprocessing info, generated CSI values, encoding info, etc.) associated with the first and / or the second CSI reports.

[0172] In an embodiment, the WTRU may be configured to determine and / or report the parameters associated with the first / base CSI report based on a first set of conditions, and the parameters associated with the second / additional CSI report(s) based on a second set of conditions. For example, the WTRU may determine the size of the first report, e.g., k, based on channel measurements (e.g., Doppler and delay spread) which reflect the correlation of the channel across time and frequency. Higher correlation may indicate a higher compression capability, e.g., low size (fc), while lower correlation may indicate a higher report size. In an embodiment, the WTRU may be configured with a mapping between a measured channel quantity (e.g., ratio between Doppler and delay spread) and the corresponding first report size. The WTRU may select and report the size associated with the measured channel quantity.

[0173] In an embodiment, the WTRU may be configured to determine and / or report the parameters associated with the second / additional linked CSI report based on implicit methods or explicit methods or a combination of both. For example, the WTRU may be indicated that the current CSI report is linked with the previous CSI report through a higher layer parameter (e.g., CSIReportLinkage) which is a one bit indicating whether the current report is new / first or linked to a previously reported one. If configured as linked, the WTRU may implicitly determine theparameters associated with the additional linked reports based on one or more of the following: (i) preconfigured rules; for example, based on the number of available UL resource, the WTRU may determine the additional report size (m) if the number of available uplink resources is less than the number of parts (k) transmitted in the first CSI report by a preconfigured factor, (ii) priority rules; for example, the number of parts m may be determined based on a priority index associated with the second / additional linked CSI report, (iii) performance metric; for example, a mapping between the additional report size (m) and the number of consecutive NACKs.

[0174] In an embodiment, the WTRU may determine and may report the additional linked CSI report parameters in an explicit way. For example, the WTRU may be directly configured with the latent vector parameters associated with the additional linked reports. In another embodiment, the WTRU may be configured with a set of transmission masks along with the mask index needed to derive the additional CSI report.

[0175] In an embodiment, the WTRU may determine and may report the additional linked CSI report parameters based on WTRU measurements and one or more configured thresholds. For example, the WTRU may measure the change in the channel (e.g., using cosine similarity metric) corresponding to two linked reports, e.g., between the one received at the first CSI report and the one received at the second CSI report, and may determine the additional report size by comparing the measured change one or more preconfigured threshold(s). In another embodiment, the WTRU may determine the linked report size based on signaled performance indicator associated with the reconstruction quality of the first report. For example, the WTRU may be indicated with the maximum eigenvalue of the reconstructed channel of the first CSI report, and the WTRU may measure / determine the delta in the maximum eigenvalue of the raw channel of the first report and the received eigenvalue of the reconstructed one and may determine the size of the additional report depending on the gap between the eigenvalues. The higher the gap in eigenvalues, the larger the size of the additional linked CSI report.

[0176] For a NW-side determination of the parameters of the linked CSI reports, in an embodiment, the WTRU may transmit the additional linked CSI report parameters as a response to an explicit request from the NW. For example, the NW may determine the need for an additional linked CSI report based on the reconstruction performance from multiple parts in the first CSI repot. For example, since the received latent vector (of size fc) from the first report exhibits the additive property and the reconstruction performance associated with all received k parts is better than the reconstruction from the first k-1 parts, the NW may determine if an additional linked CSI report is needed by measuring the gap in reconstruction performance between two subsets of parts in the receive latent vector. For example, the NW may measure the gap between reconstructionperformance associated with the first k-1 parts (say fffc-1and the entire k parts (say Hk), where Hkshould be close to the true channel H more thanand the gap in reconstruction performance between_ II fife ~ fifc-i Hr k Il Hfc-l IlF

[0177] The NW may determine if an additional report is needed and the associated parameters (e.g., size) based on the measured gap ak. Higher akmay imply that an additional linked report is required as adding more parts improve the reconstruction performance while lower akmay imply that adding more parts does not help and additional report may not be needed. The NW may then configure the WTRU to indicate additional linked report parameters based on the measured gap ot / c-

[0178] In an embodiment solution, the WTRU may receive an aperiodic trigger that is preconfigured for transmission of second CSI report. For example, the aperiodic trigger may include reception of CSI Request field within PDCCH downlink control information with a preconfigured format (e.g., format 0 1). In one or more solutions here, the aperiodic trigger may carry an indication of additional marks that should be applied to obtain the second CSI report. In an embodiment, the aperiodic trigger may carry an index to one or more mask sets and / or masks preconfigured for the WTRU thereof. In various embodiments, the WTRU may override any prior configuration of additional masks if aperiodic trigger carries an indication of additional marks that should be applied to obtain the second CSI report.

[0179] The WTRU may be configured to transmit a second CSI report upon receiving an aperiodic trigger where the aperiodic trigger may indicate that the second CSI report is linked to a first CSI report. In an embodiment, the WTRU may transmit the first CSI report at time tl, and the WTRU may receive aperiodic trigger at time t2, and the WTRU may transmit the second CSI report at time t3, wherein tl<t2<t3. In another embodiment, the WTRU may receive aperiodic trigger for second CSI report at time tl, the UL resource for transmission of the first CSI report at time t2 and the UL resource for transmission of second CSI report at time t3. The WTRU may determine that the progressive CSI feedback is requested if t2 is equal to t3. In another embodiment, the WTRU may determine that the progressive CSI feedback is requested if the difference between t3 - 12 is below a preconfigured threshold.

[0180] In an embodiment, the WTRU may determine to transmit a second CSI report based on the status of semi-persistent resource and / or reporting. For example, the WTRU may be preconfigured with a semi-persistent resource and / or CSI reporting configuration associated with a second CSI report, wherein the second CSI report may be linked to a first CSI report. In anembodiment, the WTRU may trigger transmission of second CSI report upon receiving an MAC control element that activates semi-persistent CSI reporting on physical uplink control channel (PUCCH). In another embodiment, the WTRU may trigger transmission of second CSI report upon receiving CSI Request field within physical downlink control channel (PDCCH) downlink control information with a preconfigured format (e.g., format 0 1).

[0181]

[0182] In an embodiment, the WTRU may be configured to perform one or more actions associated with transmission of progressive CSI feedback wherein the WTRU may perform more than one CSI feedback transmission based on a single latent vector and / or CSI reference resource. For example, the WTRU may apply the mask on the AIML model output to get the different parts of latent vector. For example, the WTRU may apply a first mask on the latent vector to generate a first CSI report and apply a second mask on the same latent vector to generate a second CSI report.

[0183] In various embodiments, the term progressive CSI feedback may refer to transmission of CSI report in multiple stages. For example, the WTRU may generate / transmit a first CSI report and then transmit a second CSI report, wherein the second CSI report may be linked to the first CSI report. For example, the first CSI report and second CSI report may be associated with the same reference CSI-RS and / or CSI- interference measurement (CSI-IM) resource. For example, the first CSI report and second CSI report may be associated with the same latent vector generated from the Al model. For example, the second CSI report may enhance the first CSI report by providing additional information. For example, the compressed CSI may consist of N parts, the first CSI report may carry k parts and the second CSI report may carry m parts, wherein k+m <= N.

[0184] The WTRU may be configured to transmit a first CSI report and a second CSI report wherein the first CSI report may carry k parts of the N part latent vector and the second CSI report may carry m parts of the N part latent vector. In an embodiment, the k parts in the first CSI report may satisfy a first performance criterion. For example, the k parts in the first report may contain the most important k parts of the latent vector from the reconstruction perspective. For example, the k parts may correspond to the first k parts of the latent vector. In an embodiment, the m parts in the second CSI report may satisfy a second performance criterion. For example, the m parts in the second CSI report may contain the next most important m parts. For example, the m parts in the second CSI report may contain the k+1 to k+m parts where the k parts are included in the first CSI report.

[0185] In various embodiments, the WTRU may send multiple parts of the latent vector in a CSI report, wherein the number of parts may be a function of type of CSI report e.g., first CSI report, second CSI report, combine CSI report etc. The WTRU may be configured to indicate the numberof parts contained in the CSI report. For example, the WTRU may transmit an indication that the CSI report contains k parts, m parts or k+m parts.

[0186] The WTRU may be configured with one or more actions related to progressive CSI feedback as a function of aperiodic CSI reporting resource and / or aperiodic CSI-RS resource.

[0187] In an embodiment, the WTRU may be configured to apply a base mask on the latent vector to obtain the first k parts and apply the additional mask on the same latent vector to obtain the m parts, herein the m parts are the parts from k+1 to k+m. In an embodiment, the WTRU may be configured to transmit the first k parts of the latent vector in a first CSI report on a preconfigured periodic or semi-persistent resource. Possibly the resource may be a PUCCH resource. The WTRU may transmit the m parts of the latent vector in a second CSI report upon receiving an aperiodic trigger, wherein the aperiodic trigger may implicitly or explicitly indicate that the second CSI report is linked to the first CSI report.

[0188] In an embodiment, the WTRU may determine a linkage between the first CSI report and the second CSI report based on implicit rules. For example, the WTRU may determine that the first CSI report and second CSI report are linked if the reference RS resources configured for the two reports are the same. For example, the WTRU may determine that the first CSI report and second CSI report are linked if the AperiodicTriggerStateList includes a reference to a report configuration IDs associated with periodic or semi-persistent CSI reporting. For example, the WTRU may determine that the first CSI report and second CSI report are linked if the reportSlotOffset coincides with a periodic or semi-persistent CSI reporting occasion.

[0189] In an embodiment, the WTRU may be configured to apply a base mask on the latent vector to obtain the first k parts and apply the additional mask on the same latent vector to obtain the m parts (from k+1 to k+m). In an embodiment, the WTRU may be configured to transmit the first k parts of the latent vector in a first CSI report on a preconfigured periodic resource. Possibly the resource may be a PUCCH resource. In an embodiment, the WTRU may transmit the m parts of the latent vector in a second CSI report upon receiving an MAC control element that activates semi-persistent CSI reporting on PUCCH. In an embodiment, the WTRU may transmit the m parts of the latent vector in a second CSI report upon receiving activation of a semi-persistent CSI reporting. For example, the WTRU may be preconfigured with semi -persistent CSI report setting. For example, the WTRU may determine the activation of semi-persistent CSI reporting based on reception of a DCI carrying CSI request scrambled with SP-CSI RNTI wherein the SP-CSI RNTI may be preconfigured for second CSI report. In an embodiment, the configuration for semi- persistent CSI report may implicitly or explicitly indicate that the semi-persistent report is associated with a second CSI report linked to a first CSI report. In an embodiment, the WTRUmay suspend transmission of second CSI report upon receiving an indication in MAC CE and / or DCI signaling which deactivates the semi-persistent CSI report.

[0190] The various embodiments for linkage, activation and / or deactivation may also be applicable for different combination of periodicity and / or trigger conditions for first and second CSI report. For example, the first and second CSI report both may be semi-persistent CSI reports. For example, the first and second CSI report both may be periodic CSI reports. For example, the first and second CSI report both may be aperiodic CSI reports.

[0191] In an embodiment, the WTRU may be configured with one or more actions when there is collision between the UL resources for the first CSI report and second CSI report. For example, the WTRU may detect a collision based on the allocation and / or configuration of UL feedback resources for first and second CSI report. For example, the WTRU may detect a collision if the offset between the allocation and / or configuration of UL feedback resources for the first and second CSI reporting is less than a preconfigured threshold. For example, the WTRU may detect a collision when the allocation and / or configuration of UL feedback resources for first and second CSI report in the same slot. For example, the WTRU may detect a collision when the allocation and / or configuration of UL feedback resources for first and second CSI report overlaps partially and / or completely in terms of time and / or frequency resources. For example, the WTRU may detect a collision when the UL feedback resources allocated and / or configured for the second CSI report supports a payload size for k+m parts.

[0192] In an embodiment, the WTRU may transmit a single combined CSI report that contains both k parts and m parts upon determining collision between first CSI report and second CSI report. In an embodiment, the WTRU may transmit a single CSI report that contains first k+m parts upon determining collision between first CSI report and second CSI report. In an embodiment, the WTRU may be configured to transmit the combined CSI report on the resources allocated for second CSI report. In an embodiment, the WTRU may be configured to transmit the combined CSI report on the resources allocated for the second CSI report, on condition that the resource supports a payload size of k+m parts. The WTRU may be configured to drop the transmission of the first CSI report, if the WTRU transmits the combined CSI in the second CSI report.

[0193] Currently, the latent vectors generated by the baseline encoder for CSI compression do not offer any flexibility in terms of incremental transmission e.g., sending additional parts of latent vector may not improve the quality of reconstruction. The specification and / or gNB may have to define the latent structure and any subsequent behavior with respect to progressive CSI transmission. In the embodiments above, the WTRU may generate CSI with N additive parts (which is compatible with the decoder), initially may send k parts, may receive a trigger to transmitadditional parts for a linked CSI report (e.g., for scheduling or performance monitoring), and may send k+1 to k+m parts associated with linked CSI report.

[0194] In an embodiment, a WTRU may be configured to generate CSI feedback with AIML model (e.g., encoder), wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. More particularly, the preconfigured property may be expressed as model performance with respect to ordered parts of the latent vector. The WTRU may be configured with an association between N parts of the latent vector and N performance thresholds (e.g., SGCS thresholds).

[0195] The WTRU may be configured with mask configuration, including a base mask and then one or more additional masks. A first CSI reporting format may contain a CSI report using base mask. A second CSI reporting format may use additional masks; e.g., base mask may be associated with a first CSI report (periodic / semi-persistent CSI trigger / configuration) and then additional mask may be associated with a second CSI report (e.g., aperiodic trigger / configuration).

[0196] There are different way of linking a first CSI report with a second CSI report. E.g., explicit linkage in CSIMeasconfig, linkage of the report config ID of two CSI reports, linkage in AperiodicTriggerStateList etc; e.g., explicit linkage of the base and additional masks, e.g., implicit linkage via the timing and / or resource associated with aperiodic CSI trigger, e.g., implicit linkage based on offset between first CSI report and second CSI report etc.

[0197] The WTRU may generate latent vector with N parts, wherein the N parts may satisfy one or more of the following: the N parts may satisfies a first property / additive property, e.g., given N parts of the latent vector, reconstruction performance of the latent vector with i+1 parts are greater than reconstruction performance with i parts.

[0198] Each part in the N part latent vector may satisfy the associated performance threshold (e.g., SGCS) preconfigured for that part.

[0199] The WTRU may apply the base mask on the latent vector, may derive k parts of the latent vector to be included in a first CSI report.

[0200] The WTRU may receive an aperiodic CSI trigger that may contain an implicit / explicit indication of the linked CSI report and additional mask, e.g., the aperiodic CSI trigger may also include an implicit / explicit configuration of aperiodic CSI reporting resources to be used for transmission of a second CSI report; e.g., the WTRU may determine that the linked CSI report corresponds to the first CSI report.

[0201] The WTRU may apply the additional mask on the latent vector and may determine the m parts (k+1) to k+m)) to be included in the second CSI report.

[0202] If the aperiodic CSI reporting resource collides with the linked periodic CSI reporting resource and if the aperiodic CSI reporting resource size can fit k+m parts, then the WTRU maysend k+m parts associated with linked CSI report in a single CSI report, e.g., the WTRU may drop the linked CSI report, e.g., the first CSI report if it is not yet transmitted.

[0203] Otherwise, the WTRU may send k parts in the first CSI report (e.g., in a periodic CSI reporting resource). The WTRU may send m parts (k+1) to k+m)) associated with linked CSI report in the second CSI report (e.g., in a aperiodic CSI reporting resource).

[0204] Referring to Fig. 10, in an embodiment, a method 1000, implemented in WTRU, for compressing channel state information, may comprise a step of receiving 1010, from a network node, a first message comprising information for compression configuration indicating AIML model to generate CSI feedback. The AIML model may output a latent vector with N parts that satisfy a preconfigured property. The preconfigured property may be expressed as a model performance with reference to ordered parts of the latent vector. The method 1000, may comprise a step of further receiving 1020, from the network node, a second message comprising information indicating a masking configuration and a post processing configuration. The masking configuration may include any of a masking type, a masking domain, a mask length, and mask sets. The post processing configuration may indicate an association between each latent vector part and a specific post processing configuration corresponding to the part. The method 1000 may further comprise a step of generating 1030 a latent vector with N parts such that the method 1000 may comprise a step of determining 1040 k parts out of the N parts of the latent vector for CSI feedback. The method 1000 may comprise a step of performing 1050 post processing for the k parts according to a preconfigured association between each of the k parts and a corresponding post processing configuration; and a step of transmitting 1060, to the network node, a third message comprising the CSI feedback with k selected parts of the latent vector.

[0205] Referring to Fig. 11, in another embodiment, a method 1100, implemented in a WTRU, for compressing CSI may comprise a step of receiving 1110, from a network node, a first message comprising information for compression configuration indicating artificial intelligence / machine learning, AIML, model to generate CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. The preconfigured property may be expressed as model performance with reference to ordered parts of the latent vector. The method 1100 may further comprise a step of receiving 1120, from the network node, a second message comprising information indicating a masking configuration including a base mask and additional masks. The base mask may be associated with a first CSI report and the additional masks may be associated with a second CSI report. The method 1100 may comprise a step of generating 1130 a latent vector with N parts. The method 1100 may comprise a step of determining 1140 k parts of the latent vector to be included in a first CSI report by applying the base mask on the latent vector. The method 1100 may further comprise a step of receiving 1150 an aperiodic CSI trigger including animplicit / explicit indication of a linked periodic CSI report and an additional mask. The method 1100 may further comprise a step of determining 1160 m parts of the latent vector to be included in a second CSI report by applying the additional mask. On condition that the aperiodic CSI reporting resource may collide with the linked periodic CSI reporting resource, and on condition that the aperiodic CSI reporting resource size may fit with the m parts, the method 1100 may comprise a step of transmitting 1170, to the network node, the m parts associated with the linked CSI report in a single CSI report.

[0206] Referring to FIG. 12, a method 1200, implemented in a wireless transmit / receive unit (WTRU) may comprise a step wherein the WTRU may receive 1210, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder (e.g. a AI / ML model) to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations. The at least one or more post processing configurations may indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts. The masking configuration may include any of a masking type, a masking domain, a mask length, and mask sets.

[0207] The method 1200 may comprise a step wherein the WTRU may select 1220 one masking configuration from the plurality of masking configurations. The selection of one masking configuration may be based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback.

[0208] The method 1200, may comprise a step wherein the WTRU may generate 1230, by the encoder, a vector comprising a set of parts based on the selected masking configuration. The vector may be a latent vector. The set of parts may satisfy preconfigured one or more properties. The preconfigured one or more properties may include any of an additive property, an ordering property, and associated performance threshold preconfigured for each part of the set of parts.

[0209] The method 1200 may comprise a step wherein the WTRU may determine 1240 a first subset of parts out of the set of parts of the vector. Determining the first subset of parts may comprise selecting the subset of parts out of the set of parts based on UL resources.

[0210] The method 1200 may comprise a step of performing 1250 at least one or more post processing of the first subset of parts using at least one or more post processing configurations, wherein each post processing configuration of the at least one or more post processing configurations may be associated with each part of the first subset of parts. Performing at least one or more post processing of the first subset of parts may comprise performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of thefirst subset of parts. Performing quantization on each part of the first subset of parts may comprise a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts. Post processing of the first subset of parts may comprise using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts.

[0211] The method 1200, may comprise a step wherein the WTRU may generate 1260 a CSI feedback based on the post processed first subset of parts; and the method 1200 may comprise a step wherein the WTRU may transmit 1270, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration.

[0212] Although features and elements are provided above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. The present disclosure is not to be limited in terms of the particular embodiments described in this application, which are intended as illustrations of various aspects. Many modifications and variations may be made without departing from its spirit and scope, as will be apparent to those skilled in the art. No element, act, or instruction used in the description of the present application should be construed as critical or essential to the invention unless explicitly provided as such. Functionally equivalent methods and apparatuses within the scope of the disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing descriptions. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure is to be limited only by the terms of the appended claims, along with the full scope of equivalents to which such claims are entitled. It is to be understood that this disclosure is not limited to particular methods or systems.

[0213] The foregoing embodiments are discussed, for simplicity, with regard to the terminology and structure of infrared capable devices, i.e., infrared emitters and receivers. However, the embodiments discussed are not limited to these systems but may be applied to other systems that use other forms of electromagnetic waves or non-electromagnetic waves such as acoustic waves.

[0214] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the term "video" or the term "imagery" may mean any of a snapshot, single image and / or multiple images displayed over a time basis. As another example, when referred to herein, the terms "user equipment" and its abbreviation "UE", the term "remote" and / or the terms "head mounted display" or its abbreviation "HMD" may mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of a number of embodiments of a WTRU; (iii) a wireless-capable and / or wired-capable (e.g.,tetherable) device configured with, inter alia, some or all structures and functionality of a WTRU; (iii) a wireless-capable and / or wired-capable device configured with less than all structures and functionality of a WTRU; or (iv) the like. Details of an example WTRU, which may be representative of any WTRU recited herein, are provided herein with respect to FIGs. 1 A-1D. As another example, various disclosed embodiments herein supra and infra are described as utilizing a head mounted display. Those skilled in the art will recognize that a device other than the head mounted display may be utilized and some or all of the disclosure and various disclosed embodiments can be modified accordingly without undue experimentation. Examples of such other device may include a drone or other device configured to stream information for providing the adapted reality experience.

[0215] In addition, the methods provided herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer- readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0216] Variations of the method, apparatus and system provided above are possible without departing from the scope of the invention. In view of the wide variety of embodiments that can be applied, it should be understood that the illustrated embodiments are examples only, and should not be taken as limiting the scope of the following claims. For instance, the embodiments provided herein include handheld devices, which may include or be utilized with any appropriate voltage source, such as a battery and the like, providing any appropriate voltage.

[0217] Moreover, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices that include processors are noted. These devices may include at least one Central Processing Unit ("CPU") and memory. In accordance with the practices of persons skilled in the art of computer programming, reference to acts and symbolic representations of operations or instructions may be performed by the various CPUs and memories. Such acts and operations or instructions may be referred to as being "executed," "computer executed" or "CPU executed."

[0218] One of ordinary skill in the art will appreciate that the acts and symbolically represented operations or instructions include the manipulation of electrical signals by the CPU. An electricalsystem represents data bits that can cause a resulting transformation or reduction of the electrical signals and the maintenance of data bits at memory locations in a memory system to thereby reconfigure or otherwise alter the CPU's operation, as well as other processing of signals. The memory locations where data bits are maintained are physical locations that have particular electrical, magnetic, optical, or organic properties corresponding to or representative of the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs and that other platforms and CPUs may support the provided methods.

[0219] The data bits may also be maintained on a computer readable medium including magnetic disks, optical disks, and any other volatile (e.g., Random Access Memory (RAM)) or non-volatile (e.g., Read-Only Memory (ROM)) mass storage system readable by the CPU. The computer readable medium may include cooperating or interconnected computer readable medium, which exist exclusively on the processing system or are distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories and that other platforms and memories may support the provided methods.

[0220] In an illustrative embodiment, any of the operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer-readable instructions may be executed by a processor of a mobile unit, a network element, and / or any other computing device.

[0221] There is little distinction left between hardware and software implementations of aspects of systems. The use of hardware or software is generally (but not always, in that in certain contexts the choice between hardware and software may become significant) a design choice representing cost versus efficiency tradeoffs. There may be various vehicles by which processes and / or systems and / or other technologies described herein may be effected (e.g., hardware, software, and / or firmware), and the preferred vehicle may vary with the context in which the processes and / or systems and / or other technologies are deployed. For example, if an implementer determines that speed and accuracy are paramount, the implementer may opt for a mainly hardware and / or firmware vehicle. If flexibility is paramount, the implementer may opt for a mainly software implementation. Alternatively, the implementer may opt for some combination of hardware, software, and / or firmware.

[0222] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of block diagrams, flowcharts, and / or examples. Insofar as such block diagrams, flowcharts, and / or examples include one or more functions and / or operations, it will be understood by those within the art that each function and / or operation within such block diagrams, flowcharts, or examples may be implemented, individually and / or collectively, by a wide range ofhardware, software, firmware, or virtually any combination thereof. In an embodiment, several portions of the subject matter described herein may be implemented via Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), digital signal processors (DSPs), and / or other integrated formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein, in whole or in part, may be equivalently implemented in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and / or writing the code for the software and or firmware would be well within the skill of one of skill in the art in light of this disclosure. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein may be distributed as a program product in a variety of forms, and that an illustrative embodiment of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually carry out the distribution. Examples of a signal bearing medium include, but are not limited to, the following: a recordable type medium such as a floppy disk, a hard disk drive, a CD, a DVD, a digital tape, a computer memory, etc., and a transmission type medium such as a digital and / or an analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).

[0223] Those skilled in the art will recognize that it is common within the art to describe devices and / or processes in the fashion set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least a portion of the devices and / or processes described herein may be integrated into a data processing system via a reasonable amount of experimentation. Those having skill in the art will recognize that a typical data processing system may generally include one or more of a system unit housing, a video display device, a memory such as volatile and non-volatile memory, processors such as microprocessors and digital signal processors, computational entities such as operating systems, drivers, graphical user interfaces, and applications programs, one or more interaction devices, such as a touch pad or screen, and / or control systems including feedback loops and control motors (e.g., feedback for sensing position and / or velocity, control motors for moving and / or adjusting components and / or quantities). A typical data processing system may be implemented utilizing any suitable commercially available components, such as those typically found in data computing / communication and / or network computing / communication systems.

[0224] The herein described subject matter sometimes illustrates different components included within, or connected with, different other components. It is to be understood that such depictedarchitectures are merely examples, and that in fact many other architectures may be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively "associated" such that the desired functionality may be achieved. Hence, any two components herein combined to achieve a particular functionality may be seen as "associated with" each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated may also be viewed as being "operably connected", or "operably coupled", to each other to achieve the desired functionality, and any two components capable of being so associated may also be viewed as being "operably couplable" to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and / or physically interacting components and / or wirelessly interactable and / or wirelessly interacting components and / or logically interacting and / or logically interactable components.

[0225] With respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.

[0226] It will be understood by those within the art that, in general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as "open" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "includes" should be interpreted as "includes but is not limited to," etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, where only one item is intended, the term "single" or similar language may be used. As an aid to understanding, the following appended claims and / or the descriptions herein may include usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim including such introduced claim recitation to embodiments including only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an" (e.g., "a" and / or "an" should be interpreted to mean "at least one" or "one or more"). The same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number (e.g., the bare recitation of "two recitations," without other modifiers, means at least two recitations, or twoor more recitations). Furthermore, in those instances where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). In those instances where a convention analogous to "at least one of A, B, or C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase "A or B" will be understood to include the possibilities of "A" or "B" or "A and B." Further, the terms "any of' followed by a listing of a plurality of items and / or a plurality of categories of items, as used herein, are intended to include "any of," "any combination of," "any multiple of," and / or "any combination of multiples of the items and / or the categories of items, individually or in conjunction with other items and / or other categories of items. Moreover, as used herein, the term "set" is intended to include any number of items, including zero. Additionally, as used herein, the term "number" is intended to include any number, including zero. And the term "multiple", as used herein, is intended to be synonymous with "a plurality".

[0227] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0228] As will be understood by one skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily recognized as sufficiently describing and enabling the same range being broken down into at least equal halves, thirds, quarters, fifths, tenths, etc. As a non-limiting example, each range discussed herein may be readily broken down into a lower third, middle third and upper third, etc. As will also be understood by one skilled in the art all language such as "up to," "at least," "greater than," "less than," and the like includes the number recited and refers to ranges which can be subsequently broken down into subranges as discussed above. Finally, as will be understood by one skilled in the art, a range includes each individual member. Thus, for example, a group having 1-3 cells refers to groupshaving 1, 2, or 3 cells. Similarly, a group having 1-5 cells refers to groups having 1, 2, 3, 4, or 5 cells, and so forth.

[0229] Moreover, the claims should not be read as limited to the provided order or elements unless stated to that effect. In addition, use of the terms "means for" in any claim is intended to invoke 35 U.S.C. §112, 6 or means-plus-function claim format, and any claim without the terms "means for" is not so intended.

Claims

CLAIMS1. A method, implemented in a wireless transmit / receive unit (WTRU) the method comprising: receiving, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations; selecting one masking configuration from the plurality of masking configurations; generating, by the encoder, a vector comprising a set of parts based on the selected masking configuration; determining a first subset of parts out of the set of parts of the vector; performing at least one or more post processing of the first subset of parts using at least one or more post processing configurations; wherein each post processing configuration of the at least one or more post processing configurations is associated with each part of the first subset of parts; generating a CSI feedback based on the post processed first subset of parts; and transmitting, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration.

2. The method of claim 1, wherein the selection of one masking configuration is based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback.

3. The method of any of the claims 1 and 2, wherein the at least one or more post processing configurations indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts.

4. The method of any of the claims 1 and 2, wherein performing at least one or more post processing of the first subset of parts comprises performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of the first subset of parts.

5. The method of claim 4, wherein performing quantization on each part of the first subset of parts comprises a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts.

6. The method of any of the preceding claims, wherein post processing of the first subset of parts comprises using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts.

7. The method of any of the preceding claims, wherein the masking configuration includes any of a masking type, a masking domain, a mask length, and mask sets.

8. The method of any of the preceding claims, wherein determining the first subset of parts comprises selecting the subset of parts out of the set of parts based on UL resources.

9. The method of any of the preceding claims, wherein the set of parts satisfy preconfigured one or more properties.

10. The method of claim 9, wherein the preconfigured one or more properties include any of an additive property, an ordering property, and associated performance threshold preconfigured for each part of the set of parts.

11. The method of any of the preceding claims, wherein the vector is a latent vector.

12. A wireless transmit / receive unit (WTRU) comprising a processor, a transmitter, a receiver and memory, configured to: receive, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations; select one masking configuration from the plurality of masking configurations; generate, by the encoder, a vector comprising a set of parts based on the selected masking configuration; determine a first subset of parts out of the set of parts of the vector; perform at least one or more post processing of the first subset of parts using at least one or more post processing configurations; wherein each post processing configuration of the at least one or more post processing configurations is associated with each part of the first subset of parts; generate a CSI feedback based on the post processed first subset of parts; and transmit, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration.

13. The WTRU of claim 12, wherein the selection of one masking configuration is based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback.

14. The WTRU of any of the claims 12 and 13, wherein the at least one or more post processing configurations indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts.

15. The WTRU of any of the claims 12 and 13, wherein performing at least one or more post processing of the first subset of parts comprises performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of the first subset of parts.

16. The WTRU of claim 12, wherein performing quantization on each part of the first subset of parts comprises a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts.

17. The WTRU of any of the claims 12 to 16, wherein post processing of the first subset of parts comprises using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts.

18. The WTRU of any of the claims 12 to 17, wherein the masking configuration includes any of a masking type, a masking domain, a mask length, and mask sets.

19. The WTRU of any of the claims 12 to 18, wherein determining the first subset of parts comprises selecting the subset of parts out of the set of parts based on UL resources.

20. The WTRU of any of the claims 12 to 19, wherein the set of parts satisfy preconfigured one or more properties.

21. The WTRU of claim 20, wherein the preconfigured one or more properties include any of an additive property, an ordering property, and associated performance threshold preconfigured for each part of the set of parts.

22. The WTRU of any of the claims 12 to 21, wherein the vector is a latent vector.

Images