Differential channel state information feedback

Abstract

Example embodiments of the present disclosure relate to methods, devices, apparatuses and computer readable storage medium for differential channel state information (CSI) feedback. The method comprises: transmitting, to a first apparatus, a configuration of a differential CSI feedback comprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; receiving, from the first apparatus, a CSI report associated with a differential CSI feedback; and reconstructing full channel information at least based on the differential CSI feedback.

Description

DIFFERENTIAL CHANNEL STATE INFORMATION FEEDBACK CROSS-REFERENCE TO RELATED APPLICATION

[0001] The present application claims priority to, and the benefit of, GB Application.No.2401863.2, filed February 12, 2024, the contents of which are hereby incorporated by reference in their entirety. FIELDS

[0002] Various example embodiments of the present disclosure generally relate to thefield of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium for differential channel state information (CSI) feedback. BACKGROUND

[0003] A discussion of Artificial Intelligence (AI) / Machine Learning (ML) for loadbalancing and mobility optimization use cases in next generation radio access network(NG-RAN) is now ongoing in the 3rd Generation Partnership Project (3GPP). For thediscussion of ML-enabled CSI reporting on the air interface, the focus is on the ML-basedchannel information compression. SUMMARY

[0004] In a first aspect of the present disclosure, there is provided a first apparatus. Thefirst apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus atleast to: receive, from a second apparatus, a configuration of a differential CSI feedbackcomprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; determine whether a full CSI feedback or a differential CSI feedback is to be reported to a second apparatus; and in accordance with a determination that the differential CSI feedback is to be reported, transmit, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

[0005] In a second aspect of the present disclosure, there is provided a second apparatus.The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatusat least to: transmit, to a first apparatus, a configuration of a differential CSI feedbackcomprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; receive, from the first apparatus, a channel state information, CSI, report associated with a differential CSI feedback; and reconstruct full channel information at least based on the differential CSI feedback.

[0006] In a third aspect of the present disclosure, there is provided a method. Themethod comprises: receiving, from a second apparatus, a configuration of a differentialCSI feedback comprising at least one or more available transform types associated withthe differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; determining whether a fullCSI feedback or a differential CSI feedback is to be reported to a second apparatus; andin accordance with a determination that the differential CSI feedback is to be reported, transmitting, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

[0007] In a fourth aspect of the present disclosure, there is provided a method. Themethod comprises: transmitting, to a first apparatus, a configuration of a differential CSI feedback comprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; receiving, from the first apparatus, aCSI report associated with a differential CSI feedback; and reconstructing full channelinformation at least based on the differential CSI feedback.

[0008] In a fifth aspect of the present disclosure, there is provided a first apparatus. Thefirst apparatus comprises means for receiving, from a second apparatus, a configurationof a differential CSI feedback comprising at least one or more available transform typesassociated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the secondapparatus compared to a channel state reported in a previous CSI report; means fordetermining whether a full CSI feedback or a differential CSI feedback is to be reportedto a second apparatus; and means for in accordance with a determination that the differential CSI feedback is to be reported, transmitting, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

[0009] In a sixth aspect of the present disclosure, there is provided a second apparatus.The second apparatus comprises means for transmitting, to a first apparatus, aconfiguration of a differential CSI feedback comprising at least one or more availabletransform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; meansfor receiving, from the first apparatus, a CSI report associated with a differential CSIfeedback; and means for reconstructing full channel information at least based on the differential CSI feedback.

[0010] In a seventh aspect of the present disclosure, there is provided a computerreadable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the third aspect.

[0011] In an eighth aspect of the present disclosure, there is provided a computerreadable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourth aspect.

[0012] Other features of the present disclosure will become easily comprehensible throughthe following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Some example embodiments will now be described with reference to theaccompanying drawings, where:

[0014] FIG. 1 illustrates an example communication environment in which exampleembodiments of the present disclosure can be implemented;

[0015] FIG. 2 illustrates a signaling chart for communication according to someexample embodiments of the present disclosure;

[0016] FIG. 3 illustrates a diagram of an example of full / differential CSI reportaccording to some example embodiments of the present disclosure;

[0017] FIG. 4 illustrates a flowchart of a method implemented at a first apparatusaccording to some example embodiments of the present disclosure;

[0018] FIG. 5 illustrates a flowchart of a method implemented at a second apparatusaccording to some example embodiments of the present disclosure;

[0019] FIG. 6 illustrates a simplified block diagram of a device that is suitable forimplementing example embodiments of the present disclosure; and

[0020] Throughout the drawings, the same or similar reference numerals represent thesame or similar element. DETAILED DESCRIPTION

[0021] Principle of the present disclosure will now be described with reference to someexample embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0022] In the following description and claims, unless defined otherwise, all technicaland scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0023] References in the present disclosure to “one embodiment,” “an embodiment,”“an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0024] It shall be understood that although the terms “first,” “second,”…, etc. in frontof noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0025] As used herein, “at least one of the following: ”and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements,or at least any two or more of the elements, or at least all the elements.

[0026] As used herein, unless stated explicitly, performing a step “in response to A”does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0027] The terminology used herein is for the purpose of describing particularembodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0028] As used in this application, the term “circuitry” may refer to one or more or allof the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0029] This definition of circuitry applies to all uses of this term in this application,including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellularnetwork device, or other computing or network device.

[0030] As used herein, the term “communication network” refers to a network followingany suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), the sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0031] As used herein, the term “network device” refers to a node in a communicationnetwork via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such asa satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earthorbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0032] The term “terminal device” refers to any end device that may be capable ofwireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT).The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0033] As used herein, the term “resource,” “transmission resource,” “resource block,”“physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0034] CSI feedback may refer to multiple report quantities such as Link Indicator (LI),Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI) and / or Rank Indicator (RI).

[0035] The PMI values correspond to the different precoder matrix to be chosen fromthe precoder codebook defined by the standards. If PMI reporting is applied, which PMI codebook to be used is configured in the CSI Report Setting. Four codebooks are defined for NR, namely Type I Single-Panel codebook, Type I Multi-Panel codebook, Type IIcodebook and Type II Port Selection codebook.

[0036] The Type I codebooks target Single User Multiple Input Multiple Output (SU-MIMO) operation and offers a “regular” spatial resolution with a relatively low overhead, whereas the Type II codebooks targets Multiple User (MU-MIMO) operation and gives a much finer spatial resolution which is required for intra-cell interference suppression.

[0037] For Type I, Type II, Enhanced Type II and Further Enhanced Type II PortSelection CSI feedback on physical uplink shared channel (PUSCH), a CSI report comprises of two parts. The first part i.e., CSI Part 1 has a fixed payload size and is used to identify the number of information bits in the second part i.e., CSI Part 2. CSI Part 1 may be transmitted entirety before CSI Part 2.

[0038] Encoding format of CSI report depends on the channel and frequency granularityof CSI report. A payload size of CSI may vary with CSI-RS Resource Indicator (CRI) and RI.

[0039] For physical uplink control channel (PUCCH) with sub-band freq.-granularityand PUSCH reporting padding to the worst case (i.e., to the largest possible report size) is too expensive. Thus, CSI content is divided in two parts:- CSI Part 1- fixed payload size (decoding at gNB without prior information);- CSI Part 2- variable payload size, based on information in CSI Part 1.

[0040] The Release 15 codebook may be defined as a two stages CSI codebook. Theprecoder matrix is given by ^ =where ^^ represents the wideband part and ^^the subband part. The ^^matrix identifies an orthogonal set of beams selected, and the ^^matrix identifies the co-phasing factors across polarizations.

[0041] In Release 16, the precoder matrix may further compressed in both spatial andfrequency domain.

[0042] For AI / ML based CSI feedback compression, the study objectives may compriseCSI feedback enhancement. For CSI compression (two-sided model), further study ways to Improve trade-off between performance and complexity / overhead.

[0043] The main idea is to replace Type II CSI feedback with AI / ML solution wherethe channel information (e.g., channel matrix ^^.^ or channel matrix eigenvalues ^^) canbe reconstructed (decoded) at the gNB from the compressed (encoded) information transmitted from the UE.

[0044] There are many alternatives encode-decoder implementations available in theliterature, such as CsiNet, CsiNet-LSTM, CRNet, ACRNet, PolarDenseNet, etc.

[0045] In a solution of full channel matrix compression, the full channel matrix, as it ismeasured and / or processed by the UE is compressed and transmitted to the gNB. The OFDM channel with ^^subcarriers, ^^transmit antennas and ^^receiver antennas canbe denoted by ^ ∈ ^^^×^^×^^.

[0046] For a typical MIMO system with ^^ transmit antennas at the gNB and ^^ receiveantennas at UE side can be considered. Denoting ^ as the number of subbands consistingof ^^^resource blocks (RBs) as the basic feedback granularity, the downlink channel canbe written as ^ =≤ ^ indicates the downlinkchannel of the ^th subband.

[0047] If a single-stream downlink transmission and ideal channel estimation at the UEside are considered, the corresponding eigenvector for the ^th sub-band, denoted as ^^∈ ℂ^^×^with normalization ||^^^||= 1, will be directly used as the downlink precodingvector and can be calculated using eigenvector decomposition as ^^^ ^^^^ = ^^^^, where^^represents the maximum eigenvalue of [^^^^^] and also indicates the precoding powergain obtained from MIMO system. All ^ eigenvectors should be reported to the BS fordownlink precoding. Hence, total ^ × ^^ complex coefficients should be compressed andrecovered for each channel sample using various kinds of neural networks.

[0048] Eigenvector ^^ corresponding to the largest eigenvalue for each sub-band ^ ischosen and all these eigenvalues are collected into a matrix ^, i.e., ^ = [^^, ^^, … , ^^] ∈ℂ^^×^.

[0049] Some agreements relevant to AI / ML CSI reporting format are listed below:Table 1 Agreement In CSI compression using two-sided model use case, further study potential specification impact on CSI report, including at least: ^CSI generation model output and / or CSI reconstruction model input, includingconfiguration(size / format) and / or potential post / pre-processing of CSI generation model output / CSI reconstruction model input. ^CQI determination^ RI determinationTable 2 Agreement In CSI compression using two-sided model use case, further study potential specification impact of the following output-CSI-UE and input-CSI-NW at least for Option 1: ^Option 1: Precoding matrixo 1a: The precoding matrix in spatial-frequency domaino 1b: The precoding matrix represented using angular-delay domainprojection ^Option 2: Explicit channel matrix (i.e., full Tx * Rx MIMO channel)o 2a: raw channel is in spatial-frequency domaino 2b: raw channel is in angular-delay domain^ Note: Whether Option 2 is also studied depends on the performance evaluationsin 9.2.2.1. Note: RI and CQI will be discussed separately Table 3 Agreement The study of AI / ML based CSI compression should be based on the legacy CSI feedback signaling framework. Further study potential specification enhancement on ^CSI-RS configurations (No discussion on CSI-RS pattern design enhancements)^ CSI reporting configurations^ CSI report UCI mapping / priority / omission^ CSI processing procedures.^ Other aspects are not precluded.Agreement In CSI compression using two-sided model use case, for UE-side monitoring, further study potential specification impact on triggering and means for reporting the monitoring metrics, including periodic / semi-persistent and aperiodic reporting, and other reporting initiated from UE. Agreement In CSI compression using two-sided model use case, further study the following aspectsfor CSI configuration and report: ^NW configuration to determine CSI payload size, e.g., possible CSI payload size,possible rank restriction and / or other related configuration. How UE determines / reports the actual CSI payload size and / or other CSI related information within constraints configured by the network. Table 4 Agreement The study of AI / ML based CSI compression should be based on the legacy CSI feedbacksignalling framework. Further study potential specification enhancement on^ CSI-RS configurations (No discussion on CSI-RS pattern design enhancements)^ CSI reporting configurations^ CSI report UCI mapping / priority / omission^ CSI processing procedures.^ Other aspects are not precluded.Agreement In CSI compression using two-sided model use case, for the study of UCI format, consider the legacy CSI reporting principle with CSI Part 1 and Part 2 as a starting point, where Part 1 has a network configured fixed size and Part 2 size is dynamic, determined by information in Part 1. Agreement In CSI compression using two-sided model use case, further study the feasibility of at least the following methods to support codebook subset restriction:^ input-CSI-NW / output-CSI-UE is in angular-delay domain, beam restriction can bebased on legacy SD basis vector-based input CSI in angular domain.^ FFS amplitude restriction^ FFS if input-CSI-NW / output-CSI-UE is in spatial-frequency domainAgreement In CSI compression using two-sided model use case, further study the applicability and potential specification impact for CSI configuration and report:^ For network to indicate CSI reporting related information, gNB can indicate theUE with the one or more of following information: oInformation indicating CSI payload sizeo Information indicating quantization method / granularity.o Rank restrictiono Other payload related aspectsFor UE determination / reporting of the actual CSI payload size, UE reports related information as configured by the NW Table 5 Agreement •In CSI compression using two-sided model use case, for CSI report format, whenoutput-CSI-UE and input-CSI-NW is precoding matrix, CSI part 1 includes at least CQI for first codeword, RI, and information representing the part 2 size. CSI part 2includes at least the content of CSI generation part output.Other CSI report formats are not precluded

[0050] AIML-based CSI feedback considers the compression of either full channel matrixor of the channel matrix eigenvalues (per transmission layer). Even though the overhead of the feedback can be potentially adjusted, e.g., by changing the size of the feedback (i.e., of compression level of the feedback or of the feedback payload size), it is still assumed that the feedback always contains the same type of information, e.g., eigenvalues or the full channel matrix.

[0051] Such extensive CSI feedback could be justified in the scenarios when the channel ischanging dynamically and considerably, e.g., in the scenarios with mobility. However, periodical / frequent full channel CSI feedback will cause unnecessary overhead, e.g., overuse of UL control resources, in the scenarios when the changes in the channel are less considerable with time.

[0052] On the other hand, less frequent CSI feedback may cause channel aging at the NWside, i.e., the feedback might get out of date and inaccurate causing DL performance degradation.

[0053] Therefore, it is expected that the optimum balance in between the signaling load ofAI-ML compressed CSI feedback and timely update of the channel state can be found.

[0054] The present disclosure proposes a mechanism of differential CSI feedback. The UEdetermines whether a full CSI feedback or a differential CSI feedback is to be reported to agNB. The differential CSI feedback may at least indicate a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report. Based on the determination, the UE generates a CSI report and transmits it to the gNB.

[0055] Principles and implementations of the present disclosure will be described in detailbelow with reference to the figures.

[0056] Example embodiments of the present disclosure will be described in detail belowwith reference to the accompanying drawings.

[0057] FIG. 1 shows an example communication network 100 in which embodimentsof the present disclosure may be implemented. As shown in FIG. 1, the communicationnetwork 100 may include a first apparatus 110. Hereinafter the first apparatus 110 mayalso be referred to as a terminal device, e.g., a UE.

[0058] The communication network 100 may further include a second apparatus 120.Hereinafter the second apparatus 120 may also be referred to as a network device, e.g., a gNB or an eNB. The first apparatus 110 may communicate with the second apparatus 120 within a coverage of a cell 102 managed by the second apparatus 120.

[0059] In some example embodiments of the present disclosure, it is to be understoodthat the term “a model” used hereinafter may be referred to an AI / ML based model. A model may be used to achieve a functionality to be required by a device at which the model is deployed, for example, positioning, beam prediction, CSI prediction, and specific load balancing and mobility optimization use cases, etc. The model descried hereinaftermay also be considered as a logical model. It is to be understood that the model may bedeployed at the first apparatus 110 and / or the second apparatus 120 in some example embodiments of the present disclosure.

[0060] It is to be understood that the number of network nodes and terminal devicesshown in FIG.1 is given for the purpose of illustration without suggesting any limitations.The communication network 100 may include any suitable number of network nodes andterminal devices.

[0061] In some example embodiments, links from the second apparatus 120 to the firstapparatus 110 may be referred to as a downlink (DL), while links from the first apparatus110 to the second apparatus 120 may be referred to as an uplink (UL). In DL, the secondapparatus 120 is a transmitting (TX) device (or a transmitter) and the first apparatus 110is a receiving (RX) device (or receiver). In UL, the first apparatus 110 is a TX device (ortransmitter) and the second apparatus 120 is a RX device (or a receiver).

[0062] Communications in the communication environment 100 may be implementedaccording to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future.

[0063] Reference is now made to FIG. 2, which shows a signaling chart 200 forcommunication according to some example embodiments of the present disclosure. Asshown in FIG. 2, the signaling chart 200 involves the first apparatus 110 and the secondapparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 200.

[0064] In some scenarios, at both side or at least one side of the first apparatus 110 andthe second apparatus 120 may be deployed with an AI / ML model, which may have capability for CSI feedback compression / CSI feedback de-compression.

[0065] The first apparatus 110 may report its capability to the second apparatus 120. Forexample, the first apparatus 110 may transmit (202), an indication of differential CSI feedbackcapability to the second apparatus 120 for indicating that the differential CSI feedback issupportable by the first apparatus 110.

[0066] Upon receiving the indication of differential CSI feedback capability, the secondapparatus 120 determine a configuration of the differential CSI feedback. The configuration may include one or more available transform types associated with the differential CSI feedback, one or more supported format for the differential CSI feedback, e.g., a vector, a matrix, scalar, etc. and / or one or more available parametrization types associated with the differential CSI feedback.

[0067] Alternatively, or additionally, the configuration of the differential CSI feedbackmay further indicate an indication of enabling the differential CSI feedback or anindication of disabling the differential CSI feedback. That is, the second apparatus 120may indicate the first apparatus 110 to enable or disable the differential CSI feedback based on the differential CSI feedback capability reported by the first apparatus 110.

[0068] Alternatively, or additionally, the configuration of the differential CSI feedbackmay further include a configuration of prediction horizon T (e.g., in slots) associated withprediction of the change of the channel for the differential CSI feedback, or a periodicityfor reporting the differential CSI feedback.

[0069] Then the second apparatus 120 transmits (204) the configuration of thedifferential CSI feedback to the first apparatus 110. For example, the configuration of thedifferential CSI feedback may be transmitted from the second apparatus 120 to the first apparatus 110 via a higher layer signaling, e.g., a radio resource control (RRC) signaling.

[0070] The second apparatus 120 may transmit (206) a configuration of CSI referencesignal (RS) to the first apparatus 110. The configuration of CSI may include informationassociated with CSI-RS measurement and / or a periodicity for CSI reporting.

[0071] The second apparatus 120 may further transmit (208) a CSI-RS to the firstapparatus. Then, the first apparatus 110 may prepare (210) CSI report for a DL channelbetween the second apparatus 120 and the first apparatus 110 based on the received CSI-RS, i.e., by performing one or more measurements on the CSI-RS based on the receivedCSI-RS configuration.

[0072] Assuming that the first apparatus 110 has not report a full CSI feedback to thesecond apparatus 120 before or a full CSI feedback for a DL channel between the secondapparatus 120 and the first apparatus 110 is required by the second apparatus 120, the firstapparatus 110 may transmit (212) a full CSI report to the second apparatus 120. Then, thesecond apparatus 120 may decode the full CSI report and be aware of the channel state ofthe DL channel.

[0073] It is to be understood that the signaling 208-212 may be repeated several times,e.g., based on a periodicity configured by the second apparatus 120 in the CSI-RS configuration.

[0074] After receiving a CSI-RS, the first apparatus 110 may determine whether thedifferential CSI feedback is to be triggered. In this solution, the differential CSI feedback may be triggered by network or by the UE itself.

[0075] As an option (Option 1), the second apparatus 120 (i.e., at the network side) mayevaluate (216) channel change, for example, by evaluate a level of a dynamic changes ofthe channel and determine whether to trigger the differential CSI feedback. For example, if the level of a dynamic changes is lower than a threshold level, the second apparatus 120 may determine that the differential CSI feedback is to be triggered.

[0076] As an example, the level / degree of the dynamic changes may be determined bythe second apparatus 120 based on a comparison of a current channel state determined by decoding a current full CSI feedback and a previous channel state determined by decoding a previous full CSI feedback. As described above, the CSI feedback may be reported from the first apparatus 110 to the second apparatus 120 several times, e.g., based on a periodicity configured by the second apparatus 120 in the CSI-RS configuration. Therefore, the second apparatus 120 may be aware of the dynamic changes of the channel.

[0077] In this case, the second apparatus 120 may transmit (218) a CSI-RS to the firstapparatus 110. Upon determining the differential CSI feedback is to be triggered, thesecond apparatus 120 may transmit (220) an indication for triggering a reporting of thedifferential CSI feedback at the first apparatus 110. For example, the indication fortriggering the reporting of the differential CSI feedback may be transmitted from the second apparatus 120 to the first apparatus 110 via a medium access control-control element (MAC CE) or via downlink control information (DCI).

[0078] Upon receiving the indication for triggering the reporting of the differential CSIfeedback, the first apparatus 110 may prepare (222) the differential CSI report based onthe measurement on CSI-RS and a configuration of differential CSI received from the second apparatus 120.

[0079] The differential CSI feedback may indicate changes of a DL between the firstapparatus 110 and the second apparatus 120 compared to a channel state reported in a previous CSI report. In some embodiments, the changes may be represented by at least one set of transformation or rotation parameters. A set of transformation or rotationparameters may be one or more transformation or rotation matrices, one or moretransformation or rotation vectors and / or one or more transformation or rotation scalars. These are gradually introduced and removed from the scenario, as in any realistic conditions.

[0080] Consider that a UE sends CSI feedback at time t =0 with the set of eigenvectorsrepresented by the matrix ^ or the entire channel matrix ^. Assuming that UE is in a lowmobility scenario or stationery, the wireless channel may be considered as is fairly stable i.e., other obstacles or mobile reflectors do not phase in and out of the scenario rapidly.

[0081] Given that the first apparatus 110 frequently (on the scale of few 10s ofmilliseconds) reports its CSI feedback to the second apparatus, for example, by signaling exchange in signaling 208-212, the overall channel matrix in subsequent time steps (not too far into the future) can be represented as a transformation of the original channelmatrix. In this scenario, the channel measurement at the first apparatus 110 for futurechannel state may be denoted as ^^^^^ or ^^^^^ .For example, the first apparatus 110may be capable to represent / factorize a future channel state withor

[0082] This transformation can be expressed as either a rotation matrix or any othertransformation matrix ^, or ^, or ^. That is, the ^ / ^ / ^ each may be considered as a setof transformation or rotation parameters.

[0083] For example, ^ / ^ / ^ may be a rotation matrix or some other type of sparsematrix representing a known transformation over the previously measured andreported ^^^^ or ^^^^. That is, ^ / ^ / ^ may indicate changes of a DL between the firstapparatus 110 and the second apparatus 120 compared to a channel state reported in a previous CSI report.

[0084] For example, ^ / ^ / ^ can be expressed as follows:^ ^^^^= ^^^^^ (1)^ ^^^^= ^^^^^ (2)

[0085] The (^^ × ^^) channel matrix ^ is a fat matrix, i.e., ^^ < ^^, and if it is not fullrank, then no equivalence relation can be found between the transforms in (1) and (2). On the other hand, when we have full rank channel, a direct relationship between the matrix^ and ^ can be obtained. Concretely,is the Moore-Penrose inverseof the fat full rank channel matrix. Furthermore, the matrix ^ will have lower dimensionsas compared to the matrix ^, which might also be exploited in implementations depending on requirements and scenario.

[0086] For the case where the UE does not transmit the entire channel matrix and insteadjust uses the right eigenvectors from the singular value decomposition of the channel matrix, through equation (2): ^^^^^ =^^^^^ (3)where ^ = ^^.

[0087] Moreover, it can be easily shown that in the full rank case ^ =whereagain ^ = ^^. Considering that the matrices ^, ^, ^ represent a transformation operationsuch as unitary or oblique rotation, reflection, etc., the overall information needed to becompressed by a neural autoencoder or in that case any compression method will be far less than in the currently used procedure as this matrix can be parametrized with fewer variables. From now on, by “rotation”, we mean either a unitary matrix as an element of the unitary group (a matrix whose columns are mutually orthogonal and of unit norm), or an oblique rotation (non-unitary) as an element of the oblique manifold (a matrix whose columns are non-orthogonal, but still unit norm).

[0088] Specifically, considering that the right singular vectors and the complex channelmatrix ^ is of dimensions NxN, then the number of parameters to be sent for the fullchannel matrix feedback will be 2^^. On the other hand, if consider sending only the right sided eigenvectors then to represent an NxN unitary matrix we would need ^^parameters. Subsequently, these right singular vectors can be further compressed by choosing a transformation, such as that from the Stiefel manifold or the Grasmann manifold. TheStiefel manifold, St(N, l) provides a parameterization of 2^^ − ^^, while the Grassmanmanifold, Gr(N,l) provides a parameterization of ^^ − ^^ , thus increasing thecompression ratio for the channel feedback.

[0089] As an example, if a hypothetical 2x2 channel matrix is considered and if the firstapparatus 110 utilizes two layers, i.e., the channel is full rank, then the number ofcoefficients to be transmitted / compressed would be 8 if the entire channel matrix or the eigenvectors are to be sent. On the other hand, if for example the transform is a rotation,it can be parameterized by just four parameters This represents a 50% reduction in theamount of data to be transmitted / compressed.

[0090] FIG. 3 illustrates a diagram of an example of full / differential CSI reportaccording to some example embodiments of the present disclosure. Rotation / transformation matrix compression / encoding as against full rank channel matrix compression / encoding for CSI feedback from the first apparatus 110 to second apparatus can be shown by FIG.3.

[0091] As shown, for full rank channel matrix compression / encoding, the first apparatus110 may encode the entire channel matrix ^^^^ (i.e., for a full CSI feedback) and thesecond apparatus 120 may decode ^^^^to obtain the channel state.

[0092] If the differential CSI report is used, a further channel matrix ^^^^^ may be represented by ^^^^^. The first apparatus 110 may encode P, which may represent a channel change from t=0 to t=0+as a differential CSI report. The second apparatus 120may decode ^^ and reconstruct the channel state based on ^^ and ^^^^ obtained previously.

[0093] Additionally, the rotation / transformation matrix may also evolve graduallyovertime thus allowing for a differential between subsequent rotation / transformation matrices to be sent instead of the entire matrix. Hence, this can present additional gains. For example. It can be the case that the transform matrix at a given time instance is the mthpower of the base transformation matrix P, R, Q. Hence, the value of the power can be communicated instead of the transformation matrix in this scenario.

[0094] As another example, ^ / ^ / ^ may be also represented in a vector format (e.g., inthe case of diagonal or highly sparse matrix transform or parametrized by less parameters than its number of dimensions) or further compressed / transformed before transmitting the feedback to the second apparatus 120.

[0095] It is also possible that a set of matrices / vectors, instead of only one matrix^ / ^ / ^, may also be used for differential feedback, e.g., when ^^s may be used per sub-band or MIMO layer.

[0096] In some example embodiments, differential feedback ^ / ^ / ^ may not representthe result of actual instantaneous channel measurements but prediction of the change of the channel for time horizon T based on the prediction model / algorithm implement in the first apparatus 110. In this case, a value of a prediction time horizon value may be included in the CSI reported together with the differential feedback.

[0097] Based on the at least one set of transformation or rotation parameters, e.g.,^ / ^ / ^, the first apparatus 110 may generate the differential CSI report.

[0098] For example, the P, R, Q may be reported in CSI Part 1. As another example,the P, R, Q may be reported in CSI Part 2, and information about P is included in CSI Part 1.

[0099] Specifically, the rotation / transformation matrix, depending on its actual size caneither be sent in the fixed CSI Part 1 or in the variable length CSI Part 2. Moreover, the first apparatus 110 may indicate in CSI part 1 via three (or more) fields the existence of the rotation / transformation matrix or the full feedback. These three more fields will indicate the transform type, parameterization type depending on the transform type and lastly the differential or the non-differential nature of the transform. This will be essential to let the second apparatus 120 know what it will receive and how it should estimate the channel matrix as seen on the first apparatus 110.

[0100] Furthermore, if the first apparatus 110 or the second apparatus 120 observes highmobility conditions, the first apparatus 110 can switch back to the full feedback, or if the age of information starts to become too old, the second apparatus 120 may itself requestfor full feedback. Another scenario where such a toggle to full feedback can be thought of is when the second apparatus 120 notices that the actual network performance towards the first apparatus 110 is degrading and the recent past CSI feedback have been with the rotation / transformation matrices.

[0101] In addition, P, R, Q can be compressed or non-compressed. For example, P, R,Q may be additionally compressed with AI / ML algorithm, e.g., AI / ML mode deployed at the first apparatus 110. As another example, P, R, Q may be compressed by sending the values of the non-zero indices if it is sparse or in subsequent time steps by just specifying the power, i.e., m, if it is the mthpower of the transformation matrix P, R, Q. It is also possible that P, R, Q may be compressed in subsequent time steps by just sending the differential matrix or the non-zero indices of the differential matrix.

[0102] After generating the differential CSI report, the first apparatus 110 may transmit(224) the differential CSI report to the second apparatus 120.

[0103] In some example embodiments, besides the at least one set of transformation orrotation parameters indicating the channel change, the differential CSI report may includeat least one of: a transform type used for the differential CSI feedback, a format of thedifferential CSI feedback (e.g., a vector, a matrix, scalar), a parametrization type used forthe differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or aprediction horizon (e.g., represented by T in slots) used for the differential CSI feedback.

[0104] The second apparatus 120 may decode (226) the received differential CSI report.and reconstruct full channel information at least based on the differential CSI feedback.

[0105] For example, the second apparatus 120 may obtain a full CSI feedback from theprevious CSI report and reconstruct the full channel information based on the full CSI feedback and the change of the downlink channel indicated in the differential CSI feedback.

[0106] As another option (Option 2), the first apparatus 110 may determine (230)whether the differential CSI feedback is to be reported by itself. For example, the firstapparatus 110 may evaluate how fast the channel change or the movement speed of thefirst apparatus 110. For example, if the first apparatus 110 determines a level of a dynamic changes of the channel is lower than a threshold level, the first apparatus 110 may determine that the differential CSI feedback is to be triggered. As another example, if thefirst apparatus 110 is in a low mobility scenario or stationery, the first apparatus 110 maydetermine that the differential CSI feedback is to be triggered.

[0107] It is also possible that the first apparatus 110 determines whether the differentialCSI feedback is to be triggered based on how accurate the new channel can be represented by P, R, Q and previous full channel feedback, i.e., with ^^^^^or ^^^^^or ^^^^^, at the first apparatus 110.

[0108] For example, the first apparatus 110 may perform new channel measurements,derive ^^^^^and compare it with the representation ^^^^^. If the difference in between the factorized and measured matrices is above the threshold, then full CSI feedback is to be used. Otherwise, differential CSI feedback is to be used.

[0109] The first apparatus 110 may determine to report the differential CSI feedbackbased on an evaluation of an accuracy of representing the change of the downlink channel with at least one set of transformation or rotation parameters.

[0110] Optionally or additionally, the first apparatus 110 may determine whether thedifferential CSI feedback is to be triggered based on changes in the UL channel (e.g., inthe case of TDD) and / or performance of the DL data channels, e.g., throughput or numberof retransmissions. For example, if the first apparatus 110 finds the performance of DLdata channels is getting worse, the first apparatus 110 may determine a full CSI feedback is to be reported.

[0111] If the first apparatus 110 determines that the differential CSI feedback is to bereported, the first apparatus 110 may prepare (232) the differential CSI report. The preparation of the differential CSI report at the first apparatus 110 has been described above (with Option 1), which may be omitted here.

[0112] Similarly, the first apparatus 110 may transmit (234) the differential CSI reportto the second apparatus 120. The second apparatus 120 may decode (226) the received differential CSI report. and reconstruct full channel information at least based on the differential CSI feedback.

[0113] It is to be understood that the first apparatus 110 and the second apparatus 120may trigger a fallback to a full differential CSI report. For example, if the first apparatus 110 / the second apparatus 120 observes high mobility conditions, or the age of information starts to become too old, the full CSI feedback may be required.

[0114] In this way, the CSI reporting overhead can be significantly reduced when thereis no significant change in the channel, or the changes can be well represented with matrix / transform ^ / ^ / ^.

[0115] Furthermore, Since P is expected to be sparse and considerably lower in sizethan the full CSI report, the signalling load associated with its reporting is lower.

[0116] FIG. 4 shows a flowchart of an example method 400 implemented at a firstdevice in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 400 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0117] At block 410, the first apparatus 110 receives, from a second apparatus, aconfiguration of a differential CSI feedback comprising at least one or more availabletransform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report.

[0118] At block 420, the first apparatus 110 determines whether a full CSI feedback ora differential CSI feedback is to be reported to a second apparatus.

[0119] At block 430, in accordance with a determination that the differential CSIfeedback is to be reported, at block 440, the first apparatus 110 transmits, to the secondapparatus, a CSI report generated based on the configuration of the differential CSI feedback.

[0120] In some example embodiments, the method 400 further comprises: reporting, tothe second apparatus, an indication that the differential CSI feedback is supportable by the first apparatus and / or addition information including at least one of: one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

[0121] In some example embodiments, the configuration of the differential CSIfeedback further comprises at least one of the following: one or more pre-determined type of transformation or rotation for the differential CSI feedback, one or more supported format for the differential CSI feedback, one or more available parametrization types associated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSI feedback, or a periodicity for reporting the differential CSI feedback.

[0122] In some example embodiments, the method 400 further comprises: in accordancewith a determination that the differential CSI feedback is triggered by the second apparatus, determining that the differential CSI feedback is to be reported.

[0123] In some example embodiments, the method 400 further comprises: receiving,from the second apparatus, an indication for triggering a reporting of the differential CSI feedback via a medium access control-control element, MAC CE, or via downlink controlinformation, DCI.

[0124] In some example embodiments, the method 400 further comprises: determiningwhether the differential CSI feedback is to be reported based on at least one of the following: an evaluation of an accuracy of representing the change of the downlink channel with at least one set of transformation or rotation parameters, a movement speed the first apparatus, changes of an uplink channel between the first apparatus and the second apparatus, or a performance of data transmission on the downlink channel.

[0125] In some example embodiments, the method 400 further comprises: transmitting,to the second apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

[0126] In some example embodiments, the differential CSI feedback indicates thechange of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

[0127] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a first part of the CSI report.

[0128] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

[0129] In some example embodiments, the at least one set of transformation or rotationparameters are compressed by at least one of the following: a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

[0130] In some example embodiments, the differential CSI feedback is differential to afull channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning based compressed CSI feedback mechanism.

[0131] In some example embodiments, the first apparatus comprises a terminal deviceand the second apparatus comprises a network device.

[0132] FIG. 5 shows a flowchart of an example method 500 implemented at a seconddevice in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0133] At block 510, the second apparatus 120 transmits, to a first apparatus, aconfiguration of a differential CSI feedback comprising at least one or more availabletransform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report.

[0134] At block 520, the second apparatus 120 receives, from the first apparatus, a CSIreport associated with a differential CSI feedback.

[0135] At block 530, the second apparatus 120 reconstructs full channel information atleast based on the differential CSI feedback.

[0136] In some example embodiments, the method 500 further comprises: receiving,from the first apparatus, an indication that the differential CSI feedback is supportable by the first apparatus and / or addition information including at least one of: one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

[0137] In some example embodiments, the configuration of the differential CSIfeedback further comprises at least one of the following: one or more pre-determined type of transformation or rotation for the differential CSI feedback. one or more supportedformat for the differential CSI feedback, one or more available parametrization typesassociated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSI feedback, or a periodicity for reporting the differential CSI feedback.

[0138] In some example embodiments, the method 500 further comprises: determiningthat a dynamic change level of the downlink channel exceeds a threshold level; and based on the determination, transmitting, to the first apparatus, an indication for triggering a reporting of the differential CSI feedback.

[0139] In some example embodiments, the indication for triggering the reporting of thedifferential CSI feedback is transmitted via a medium access control-control element, MAC CE, or via downlink control information, DCI.

[0140] In some example embodiments, the method 500 further comprises: receiving,from the first apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

[0141] In some example embodiments, the differential CSI feedback indicates thechange of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

[0142] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a first part of the CSI report.

[0143] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

[0144] In some example embodiments, the at least one set of transformation or rotationparameters are compressed by at least one of the following: a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

[0145] In some example embodiments, the method 500 further comprises: obtaining afull CSI feedback from the previous CSI report; and reconstructing the full channel information based on the full CSI feedback and the change of the downlink channel indicated in the differential CSI feedback.

[0146] In some example embodiments, the differential CSI feedback is differential to afull channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning based compressed CSI feedback mechanism.

[0147] In some example embodiments, the first apparatus comprises a terminal deviceand the second apparatus comprises a network device.

[0148] In some example embodiments, a first apparatus capable of performing any ofthe method 400 (for example, the first apparatus 110 in FIG.1) may comprise means forperforming the respective operations of the method 400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG.1.

[0149] In some example embodiments, the first apparatus comprises means forreceiving, from a second apparatus, a configuration of a differential CSI feedbackcomprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; means for determining whether a full CSI feedback or a differential CSI feedback is to be reported to a second apparatus; and means for in accordance with a determination that the differential CSI feedback is to be reported, transmitting, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

[0150] In some example embodiments, the first apparatus further comprises: means forreporting, to the second apparatus, an indication that the differential CSI feedback is supportable by the first apparatus and / or addition information including at least one of: one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

[0151] In some example embodiments, the configuration of the differential CSIfeedback further comprises at least one of the following: one or more pre-determined type of transformation or rotation for the differential CSI feedback, one or more supportedformat for the differential CSI feedback, one or more available parametrization typesassociated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSI feedback, or a periodicity for reporting the differential CSI feedback.

[0152] In some example embodiments, the first apparatus further comprises: means forin accordance with a determination that the differential CSI feedback is triggered by the second apparatus, determining that the differential CSI feedback is to be reported.

[0153] In some example embodiments, the first apparatus further comprises: means forreceiving, from the second apparatus, an indication for triggering a reporting of the differential CSI feedback via a medium access control-control element, MAC CE, or via downlink control information, DCI.

[0154] In some example embodiments, the first apparatus further comprises: means fordetermining whether the differential CSI feedback is to be reported based on at least one of the following: an evaluation of an accuracy of representing the change of the downlink channel with at least one set of transformation or rotation parameters, a movement speed the first apparatus, changes of an uplink channel between the first apparatus and the second apparatus, or a performance of data transmission on the downlink channel.

[0155] In some example embodiments, the first apparatus further comprises: means fortransmitting, to the second apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

[0156] In some example embodiments, the differential CSI feedback indicates thechange of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

[0157] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a first part of the CSI report.

[0158] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

[0159] In some example embodiments, the at least one set of transformation or rotationparameters are compressed by at least one of the following: a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

[0160] In some example embodiments, the differential CSI feedback is differential to afull channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning based compressed CSI feedback mechanism.

[0161] In some example embodiments, the first apparatus comprises a terminal deviceand the second apparatus comprises a network device.

[0162] In some example embodiments, the first apparatus further comprises means forperforming other operations in some example embodiments of the method 400 or the first apparatus 110. In some example embodiments, the means comprises at least one processor;and at least one memory storing instructions that, when executed by the at least oneprocessor, cause the performance of the first apparatus.

[0163] In some example embodiments, a second apparatus capable of performing anyof the method 500 (for example, the second apparatus 120 in FIG.1) may comprise means for performing the respective operations of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG.1.

[0164] In some example embodiments, the second apparatus comprises means fortransmitting, to a first apparatus, a configuration of a differential CSI feedback comprisingat least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; means for receiving, from the first apparatus, a CSI report associated with a differential CSI feedback; and means for reconstructing full channel information at least based on the differential CSI feedback.

[0165] In some example embodiments, the second apparatus further comprises: meansfor receiving, from the first apparatus, an indication that the differential CSI feedback is supportable by the first apparatus and / or addition information including at least one of: one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

[0166] In some example embodiments, the configuration of the differential CSIfeedback further comprises at least one of the following: one or more pre-determined type of transformation or rotation for the differential CSI feedback. one or more supportedformat for the differential CSI feedback, one or more available parametrization typesassociated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSI feedback, or a periodicity for reporting the differential CSI feedback.

[0167] In some example embodiments, the second apparatus further comprises: meansfor determining that a dynamic change level of the downlink channel exceeds a thresholdlevel; and means for based on the determination, transmitting, to the first apparatus, an indication for triggering a reporting of the differential CSI feedback.

[0168] In some example embodiments, the indication for triggering the reporting of thedifferential CSI feedback is transmitted via a medium access control-control element, MAC CE, or via downlink control information, DCI.

[0169] In some example embodiments, the second apparatus further comprises: meansfor receiving, from the first apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

[0170] In some example embodiments, the differential CSI feedback indicates thechange of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

[0171] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a first part of the CSI report.

[0172] In some example embodiments, the at least one set of transformation or rotationparameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

[0173] In some example embodiments, the at least one set of transformation or rotationparameters are compressed by at least one of the following: a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

[0174] In some example embodiments, the second apparatus further comprises: meansfor obtaining a full CSI feedback from the previous CSI report; and means for reconstructing the full channel information based on the full CSI feedback and the change of the downlink channel indicated in the differential CSI feedback.

[0175] In some example embodiments, the differential CSI feedback is differential to afull channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning basedcompressed CSI feedback mechanism.

[0176] In some example embodiments, the first apparatus comprises a terminal deviceand the second apparatus comprises a network device.

[0177] In some example embodiments, the second apparatus further comprises meansfor performing other operations in some example embodiments of the method 500 or the second apparatus 120. In some example embodiments, the means comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the second apparatus.

[0178] FIG. 6 is a simplified block diagram of a device 600 that is suitable forimplementing example embodiments of the present disclosure. The device 600 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1. As shown, the device 600 includes one or more processors 610, one or more memories 620 coupled to the processor 610, and one or more communication modules 640 coupled to the processor 610.

[0179] The communication module 640 is for bidirectional communications. Thecommunication module 640 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 640 may include at least one antenna.

[0180] The processor 610 may be of any type suitable to the local technical networkand may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 600 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0181] The memory 620 may include one or more non-volatile memories and one ormore volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 624, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 622 and other volatile memories that will not last in the power-down duration.

[0182] A computer program 630 includes computer executable instructions that areexecuted by the associated processor 610. The instructions of the program 630 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 630 may be stored in the memory, e.g., the ROM 624. The processor 610 may perform any suitable actions and processing by loading the program 630 into the RAM 622.

[0183] The example embodiments of the present disclosure may be implemented bymeans of the program 630 so that the device 600 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 5. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0184] In some example embodiments, the program 630 may be tangibly contained in acomputer readable medium which may be included in the device 600 (such as in the memory 620) or other storage devices that are accessible by the device 600. The device600 may load the program 630 from the computer readable medium to the RAM 622 forexecution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0185] Generally, various embodiments of the present disclosure may be implementedin hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0186] Some example embodiments of the present disclosure also provide at least onecomputer program product tangibly stored on a computer readable medium, such as a non- transitory computer readable medium. The computer program product includes computer- executable instructions, such as those included in program modules, being executed in adevice on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries,objects, classes, components, data structures, or the like that perform particular tasks orimplement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0187] Program code for carrying out methods of the present disclosure may be writtenin any combination of one or more programming languages. The program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0188] In the context of the present disclosure, the computer program code or relateddata may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0189] The computer readable medium may be a computer readable signal medium ora computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] Further, although operations are depicted in a particular order, this should notbe understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may beadvantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[0191] Although the present disclosure has been described in languages specific tostructural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:

1. A first apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from a second apparatus, a configuration of a differential channel state information, CSI, feedback comprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback atleast indicates a change of a downlink channel between the first apparatus and the secondapparatus compared to a channel state reported in a previous CSI report; determine whether a full CSI feedback or a differential CSI feedback is to be reported to a second apparatus; and in accordance with a determination that the differential CSI feedback is to be reported, transmit, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

2. The first apparatus of claim 1, wherein the first apparatus is caused to: report, to the second apparatus, an indication that the differential CSI feedback issupportable by the first apparatus and / or addition information including at least one of:one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

3. The first apparatus of claim 1, wherein the configuration of the differential CSIfeedback further comprises at least one of the following:one or more pre-determined type of transformation or rotation for thedifferential CSI feedback, one or more supported format for the differential CSI feedback, one or more available parametrization types associated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSIfeedback, or a periodicity for reporting the differential CSI feedback.

4. The first apparatus of any of claims 1-3, wherein the first apparatus is caused to: in accordance with a determination that the differential CSI feedback is triggered by the second apparatus, determine that the differential CSI feedback is to be reported.

5. The first apparatus of claim 4, wherein the first apparatus is cause to: receive, from the second apparatus, an indication for triggering a reporting of the differential CSI feedback via a medium access control-control element, MAC CE, or via downlink control information, DCI.

6. The first apparatus of any of claims 1-3, wherein the first apparatus is caused to: determine whether the differential CSI feedback is to be reported based on at least one of the following: an evaluation of an accuracy of representing the change of the downlinkchannel with at least one set of transformation or rotation parameters, a movement speed the first apparatus, changes of an uplink channel between the first apparatus and the second apparatus, or a performance of data transmission on the downlink channel.

7. The first apparatus of any of claims 1-6, wherein the first apparatus is caused to: transmit, to the second apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

8. The first apparatus of any of claims 1-7, wherein the differential CSI feedback indicates the change of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

9. The first apparatus of claim 8, wherein the at least one set of transformation or rotation parameters are reported in a first part of the CSI report.

10. The first apparatus of claim 8, wherein the at least one set of transformation or rotation parameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

11. The first apparatus of any of claims 8-10, wherein the at least one set of transformation or rotation parameters are compressed by at least one of the following: a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

12. The first apparatus of any of claims 1-11, wherein the differential CSI feedback is differential to a full channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning based compressed CSI feedback mechanism.

13. The first apparatus of any of claims 1-11, wherein the first apparatus comprises a terminal device and the second apparatus comprises a network device.

14. A second apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to:transmit, to a first apparatus, a configuration of a differential channel state information, CSI, feedback comprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; receive, from the first apparatus, a CSI report associated with a differentialCSI feedback; and reconstruct full channel information at least based on the differential CSI feedback.

15. The second apparatus of claim 14, wherein the second apparatus is caused to: receive, from the first apparatus, an indication that the differential CSI feedback issupportable by the first apparatus and / or addition information including at least one of:one or more supported transform types for the differential CSI feedback, or one or more supported format for the differential CSI feedback.

16. The second apparatus of claim 14 or 15, wherein the configuration of the differential CSI feedback further comprises at least one of the following: one or more pre-determined type of transformation or rotation for thedifferential CSI feedback. one or more supported format for the differential CSI feedback, one or more available parametrization types associated with the differential CSI feedback, a compression level or feedback size associated with the differential CSI feedback, an indication of enabling or disabling the differential CSI feedback, a configuration of prediction horizon associated with the differential CSI feedback, or a periodicity for reporting the differential CSI feedback.

17. The second apparatus of any of claims 14-16, wherein the second apparatus is caused to: determine that a dynamic change level of the downlink channel exceeds a threshold level; andbased on the determination, transmit, to the first apparatus, an indication fortriggering a reporting of the differential CSI feedback.

18. The second apparatus of claim 17, wherein the indication for triggering the reporting of the differential CSI feedback is transmitted via a medium access control- control element, MAC CE, or via downlink control information, DCI.

19. The second apparatus of any of claims 14-18, wherein the second apparatus is caused to: receive, from the first apparatus, the CSI report associated with the differential CSI feedback including at least one of the following: a transform type used for the differential CSI feedback, a format of the differential CSI feedback, a parametrization type used for the differential CSI feedback, a compression level or feedback size of the differential CSI feedback, an indication that the differential CSI feedback is used for the CSI report, or a prediction horizon used for the differential CSI feedback.

20. The second apparatus of any of claims 14-19, wherein the differential CSI feedback indicates the change of the downlink channel by at least one set of transformation or rotation parameters including one or more transformation or rotation matrices, one or more transformation or rotation vectors and / or one or more scalars.

21. The second apparatus of claim 20, wherein the at least one set of transformation or rotation parameters are reported in a first part of the CSI report.

22. The second apparatus of claim 20, wherein the at least one set of transformation or rotation parameters are reported in a second part of the CSI report, and wherein indication associated with the at least one set of transformation or rotation parameters is included in a first part of the CSI report.

23. The second apparatus of any of claims 20-22, wherein the at least one set of transformation or rotation parameters are compressed by at least one of the following:a machine learning operation, sending non-zero value, specifying a power associated with the at least one set of transformation or rotation parameters, or sending a differential part of the at least one set of transformation or rotation parameters.

24. The second apparatus of any of claims 20-23, wherein the second apparatus is caused to: obtain a full CSI feedback from the previous CSI report; and reconstruct the full channel information based on the full CSI feedback and the change of the downlink channel indicated in the differential CSI feedback.

25. The second apparatus of any of claims 14-23, wherein the differential CSI feedback is differential to a full channel matrix reported using two-sided machine learning model based compressed CSI feedback, or differential to eigenvalues reported again with a machine learning based compressed CSI feedback mechanism.

26. The second apparatus of any of claims 14-23, wherein the first apparatus comprises a terminal device and the second apparatus comprises a network device.

27. A method comprising: receiving, at a first apparatus from a second apparatus, a configuration of a differential channel state information, CSI, feedback comprising at least one or more available transform types associated with the differential CSI feedback, wherein the differential CSI feedback at least indicates a change of a downlink channel between the first apparatus and the second apparatus compared to a channel state reported in a previous CSI report; determining whether a full CSI feedback or a differential CSI feedback is to be reported to a second apparatus; and in accordance with a determination that the differential CSI feedback is to be reported, transmitting, to the second apparatus, a CSI report generated based on the configuration of the differential CSI feedback.

Images