CN114762276B

CN114762276B - Channel state information feedback

Info

Publication number: CN114762276B
Application number: CN201980102689.XA
Authority: CN
Inventors: 刘皓; 蔡立羽
Original assignee: Nokia Shanghai Bell Co Ltd; Nokia Solutions and Networks Oy
Current assignee: Nokia Shanghai Bell Co Ltd; Nokia Solutions and Networks Oy
Priority date: 2019-12-01
Filing date: 2019-12-01
Publication date: 2024-04-19
Anticipated expiration: 2039-12-01
Also published as: WO2021108940A1; CN114762276A

Abstract

Embodiments of the present disclosure relate to apparatuses, methods, devices, and computer-readable storage media for CSI feedback. The method includes obtaining a channel matrix of a channel between the first device and the second device based on a reference signal received from the second device. The method also includes determining a scenario for the channel, the scenario indicating a usage environment supporting the channel. The method also includes generating quantized coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being obtained based on a type of scene of the channel, and transmitting the quantized coefficients to a second device. In this way, two sets of parameters will be used for CSI generation and reconstruction to improve CSI feedback efficiency. Meanwhile, the accuracy of the CSI feedback is remarkably improved.

Description

Channel state information feedback

Technical Field

Embodiments of the present disclosure relate generally to the field of telecommunications and, in particular, relate to an apparatus, method, device, and computer-readable storage medium for Channel State Information (CSI) feedback.

Background

In third generation partnership project (3 GPP) release 17 (Rel-17), several key areas have been proposed to further enhance Multiple Input Multiple Output (MIMO). One of the important key areas focuses on compressing Channel State Information (CSI) across the spatial and frequency domains to find the best balance between CSI overhead and accuracy.

In Frequency Division Duplex (FDD) deployments, downlink CSI is reported to a base station, such as a new radio NodeB (or gNB), through an uplink feedback channel. In order to fully exploit the advantages of massive MIMO, CSI feedback should have high quantization accuracy and reasonable feedback overhead. Thus, for example, machine Learning (ML) techniques may be used to enhance CSI feedback.

Disclosure of Invention

In general, example embodiments of the present disclosure provide a solution for CSI feedback.

In a first aspect, a first device is provided. The first device includes at least one processor; at least one memory including computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the first device to at least: acquiring a channel matrix of a channel between the first device and the second device based on a reference signal received from the second device; determining a scene of a channel, the scene indicating a usage environment supporting the channel; generating quantization coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being obtained based on a type of scene of the channel; and transmitting the quantized coefficients to the second device.

In a second aspect, a second device is provided. The second device includes at least one processor; at least one memory including computer program code; the at least one memory and the computer program code are configured to, with the at least one processor, cause the second device to at least: transmitting a reference signal to the first device for measurement of a channel between the first device and the second device; receiving, from a first device, quantized coefficients associated with a channel, the quantized coefficients generated by a model based on a reference signal at the first device; and obtaining a restored channel matrix of the channel by decompressing the quantized coefficients based on the model.

In a third aspect, a method is provided. The method includes obtaining a channel matrix of a channel between the first device and the second device based on a reference signal received from the second device. The method also includes determining a scenario for the channel, the scenario indicating a usage environment supporting the channel. The method also includes generating quantized coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being obtained based on a type of scene of the channel, and transmitting the quantized coefficients to a second device.

In a fourth aspect, a method is provided. The method includes transmitting a reference signal to a first device for measurement of a channel between the first device and a second device. The method also includes receiving, from the first device, quantized coefficients associated with the channel, the quantized coefficients generated by the model based on the reference signal at the first device. The method further includes obtaining a restored channel matrix of the channel by decompressing the quantized coefficients based on the model.

In a fifth aspect, there is provided an apparatus comprising means for acquiring a channel matrix of a channel between a first device and a second device based on a reference signal received from the second device; means for determining a scenario for a channel, the scenario indicating a usage environment supporting the channel; means for generating quantization coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being obtained based on a type of scene of the channel; and means for transmitting the quantized coefficients to the second device.

In a sixth aspect, there is provided an apparatus comprising means for transmitting a reference signal to a first device for measurement of a channel between the first device and a second device; means for receiving, from a first device, quantized coefficients associated with a channel, the quantized coefficients generated by a model based on a reference signal at the first device; and means for obtaining a recovered channel matrix of the channel by decompressing the quantized coefficients based on the model.

In a seventh aspect, there is provided a computer readable medium having stored thereon a computer program which, when executed by at least one processor of a device, causes the device to perform the method according to the third aspect.

In an eighth aspect, there is provided a computer readable medium having stored thereon a computer program which, when executed by at least one processor of a device, causes the device to perform the method according to the fourth aspect.

Other features and advantages of embodiments of the present disclosure will become apparent from the following description of the specific embodiments, taken in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the embodiments of the disclosure.

Drawings

Embodiments of the present disclosure are presented in an exemplary sense, and their advantages are explained in more detail below with reference to the drawings, in which

Fig. 1 illustrates an example architecture of CSI feedback based on machine learning;

FIG. 2 illustrates an example environment in which example embodiments of the present disclosure may be implemented;

Fig. 3 shows a schematic diagram of a CSI feedback process according to an example embodiment of the present disclosure;

Fig. 4 illustrates a flowchart of an example method of CSI feedback according to some example embodiments of the present disclosure;

fig. 5 illustrates a flowchart of an example method of CSI feedback according to some example embodiments of the present disclosure;

FIG. 6 illustrates a simplified block diagram of a device suitable for implementing exemplary embodiments of the present disclosure; and

Fig. 7 illustrates a block diagram of an example computer-readable medium, according to some embodiments of the disclosure.

The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements.

Detailed Description

Principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these example embodiments are described merely for the purpose of illustrating and helping those skilled in the art understand and practice the present disclosure and are not meant to limit the scope of the present disclosure in any way. The disclosure described herein may be implemented in various other ways besides those described below.

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

As used herein, the term "terminal device" or "user equipment" (UE) refers to any terminal device capable of wireless communication with each other or with a base station. Communication may involve the transmission and/or reception of wireless signals using electromagnetic signals, radio waves, infrared signals, and/or other types of signals suitable for conveying information over the air. In some example embodiments, the UE may be configured to transmit and/or receive information without direct human-machine interaction. For example, the UE may transmit information to the base station according to a predetermined schedule when triggered by an internal or external event, or in response to a request from the network side.

Examples of UEs include, but are not limited to, smart phones, wireless enabled tablet computers, laptop embedded devices (LEEs), laptop mounted devices (LMEs), wireless client devices (CPE), sensors, metering devices, personal wearable devices such as watches, and/or vehicles capable of communication. For purposes of discussion, some example embodiments will be described with reference to a UE as an example of a terminal device, and the terms "terminal device" and "user equipment" (UE) may be used interchangeably in the context of this disclosure. The UE may also correspond to a Mobile Termination (MT) portion of an Integrated Access and Backhaul (IAB) node (also referred to as a relay node).

As used herein, the term "network device" refers to a device via which services can be provided to terminal devices in a communication network. As an example, the network device may include a base station. As used herein, the term "base station" (BS) refers to a network device via which services may be provided to terminal devices in a communication network. A base station may comprise any suitable device via which a terminal device or UE may access a communication network. Examples of base stations include relays, access Points (APs), transmission points (TRPs), node bs (nodebs or NB), evolved nodebs (eNodeB or eNB), new Radio (NR) nodebs (gNB), remote radio modules (RRU), radio Headers (RH), remote Radio Heads (RRH), low power nodes such as femto, pico, etc. The relay node may correspond to a Distributed Unit (DU) portion of the IAB node.

As used herein, the term "circuitry" may refer to one or more or all of the following:

(a) A pure hardware circuit implementation (such as an implementation using only analog and/or digital circuitry), and

(B) A combination of hardware circuitry and software, such as (as applicable): (i) A combination of analog and/or digital hardware circuit(s) and software/firmware, and (ii) any portion of hardware processor(s) (including digital signal processor (s)) with software, and memory(s) that work together to cause a device (such as a mobile phone or server) to perform various functions, and

(C) Hardware circuit(s) and/or processor(s), such as microprocessor(s) or a portion of microprocessor(s), that require software (e.g., firmware) to operate, but software may not be present when operation is not required.

The definition of circuitry is applicable to all uses of that term in the present application, including in any claims. As another example, as used in this disclosure, the term circuitry also encompasses hardware-only circuits or processors (or multiple processors), or implementations of a portion of a hardware circuit or processor and its (or their) accompanying software and/or firmware. For example, if applicable to the particular claim element, the term circuitry also encompasses a baseband integrated circuit or processor integrated circuit for a mobile device, or a similar integrated circuit in a server, a cellular base station, or other computing or base station.

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. The term "include" and its variants are to be understood as meaning open terms including, but not limited to. The term "based on" should be understood as "based at least in part on (based at least on)". The terms "one embodiment" and "an embodiment" should be understood as "at least one embodiment". The term "another embodiment (another embodiment)" should be understood as "at least one other embodiment (at least one other embodiment)". Other definitions (explicit and implicit) may be included below.

As used herein, the terms "first," "second," and the like may be used herein to describe various elements, which should not be limited by these terms. These terms are only used to distinguish one element from another element. 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 all combinations of any of the listed terms and one or more.

As described above, machine Learning (ML) techniques are used to enhance CSI feedback. An example architecture of ML-based CSI feedback is shown in fig. 1. In architecture 100 shown in fig. 1, CSI encoder 105 and CSI decoder 110 are jointly designed using convolution NN (CNN). CSI encoder 105 may learn the transformation from the input channel samples to a compressed CSI version. The compressed CSI version is then quantized and reported to CSI decoder 110 via feedback channel 115. CSI decoder 110 may learn to recover from the received CSI to the original channel matrix.

For example, CSI encoder 105 may transform channel matrix H having N coefficients into M-dimensional vector s as CSI using CNN, where M < N. CSI compression ratio γ is γ=m/N. The first layer of CSI encoder 105 may be a convolutional layer that uses a kernel of dimension 3 x 3 to generate two feature maps. The signature may be remodeled and then compressed into a vector s through the full connection layer.

On the other hand, CSI decoder 110 may perform inverse transformation from vector s to original channel matrix H over several layers using CNN. The first layer of CSI decoder 110 may be a fully connected layer that provides an initial estimate of channel matrix H. The initial estimate of the channel matrix H may then be fed to several "refinement network (REFINENET) units", which continually refine the reconstruction, and each unit comprises four layers. After refinement by a number REFINENET of units, the channel matrix H is input to the final convolutional layer to derive the final reconstructed channel matrix H.

After an end-to-end training process based on sufficient channel samples, two sets of parameters related to CSI encoder 105 and CSI decoder 110 may be jointly determined and used jointly to achieve satisfactory CSI feedback and recovery capabilities. The end-to-end NN training procedure may be implemented on the gNB side or the UE side based on a large number of channel samples. Due to the reciprocity of the bi-directional channels in TDD deployments, a large amount of NN training data is easily acquired. However, acquiring a large amount of channel measurement data for NN training in FDD deployments is a significant challenge.

Training of the ML model may be implemented by a terminal device (such as a UE) or a network device (such as a gNB). Some example embodiments of the present disclosure will be discussed in the context of a network device performing training. Training at the network device may provide further benefits because the network device has more NN processing power and more access to channel measurement data for multiple UEs.

FIG. 2 illustrates an example environment 200 in which example embodiments of the present disclosure may be implemented.

The environment 200, which may be part of a communication network, includes two devices 210 and 220 in communication with each other, referred to as a first device 210 and a second device 220, respectively. In this example, the first device 210 is implemented by a terminal device, such as a UE, and the second device 220 is implemented by a network device, such as a base station. The first device 210 and the second device 220 may be implemented by any other suitable device. For example, both the first device 210 and the second device 220 may be implemented by terminal devices communicating via a device-to-device (D2D) link or a side link.

The communication between the first device 210 and the second device 220 may conform to any suitable communication standard or protocol that may already exist or be developed in the future, such as Universal Mobile Telecommunications System (UMTS), long Term Evolution (LTE), LTE-advanced (LTE-a), fifth generation (5G) New Radio (NR), wireless fidelity (Wi-Fi), and Worldwide Interoperability for Microwave Access (WiMAX) standards, and employ any suitable communication technology including, for example, multiple Input Multiple Output (MIMO), orthogonal Frequency Division Multiplexing (OFDM), time Division Multiplexing (TDM), frequency Division Multiplexing (FDM), code Division Multiplexing (CDM), bluetooth, zigBee, machine Type Communication (MTC), enhanced machine type communication (eMTC), enhanced mobile broadband (eMBB), large scale machine type communication (mMTC), ultra Reliable Low Latency Communication (URLLC), carrier Aggregation (CA), dual Connectivity (DC), and new radio unlicensed (NR-U) technologies.

The first device 210 may feed back CSI to the second device 220. In various embodiments of the present disclosure, the first device 210 may measure a reference signal received from the second device 220 and generate a channel matrix that characterizes a channel between the first device 210 and the second device 220. The channel matrix should be quantized for reporting at the first device 210 and the quantized coefficients of the channel matrix should be received at the second device 220 and restored to the original channel matrix. Two sets of parameters will be used for CSI generation and reconstruction to improve CSI feedback efficiency. Meanwhile, the accuracy of the CSI feedback is remarkably improved.

It should be understood that two devices are shown in environment 200 for illustrative purposes only and not to imply any limitations. In some example embodiments, there may be more devices to feed back CSI to the second device 220. Therefore, the second device 220 may acquire more CSI from more devices, thereby improving training efficiency.

The principles and implementations of the present disclosure are described in detail below with reference to fig. 3, which shows a schematic diagram of CSI feedback. For discussion purposes, the process 300 will be described with reference to FIG. 3. The process 300 may involve the first device 210 and the second device 220 as shown in fig. 1.

As previously described, during the end-to-end training process, the NN architecture including the encoder and decoder is learned from sufficient channel samples, then two sets of parameters related to the encoder and decoder of the NN are jointly determined, and used in pairs to ensure satisfactory CSI feedback and recovery capability. End-to-end NN training may be performed at the second device 220 or the first device 210, but the second device 220 is more suitable for training work because NN processing power is greater and channel samples for multiple first devices are easier to access.

On the network side, the second device 220 has trained and maintained different kinds of NN models and corresponding parameter sets, each applied to CSI compression and recovery for a specific type of channel scenario, such as Urban Micro (UMi), urban Macro (UMa), indoor (Indoor), or hybrid type, etc., based on the input channel samples.

As shown in fig. 3, the second device 220 may determine 305 sets of parameters associated with different kinds of NN models for various channel scenarios. In particular, the scenario may indicate a usage environment supporting the channel. The second device 220 may also establish a mapping between the types of various channel scenarios and different kinds of NN models.

As an option, the sets of parameters associated with the heterogeneous NN models may be stored in a further management device or a further management node, such as a cloud, database or server, in addition to the first device 210 and the second device 220. For example, the second device 220 may upload to the server sets of parameters, as well as mappings between the determined types of various channel scenarios and different kinds of NN models.

In the server, a plurality of sets of parameters associated with different kinds of NN models may be indexed according to channel scenarios supporting the NN models. For example, the parameter set of UMi scenes is labeled index 1, the parameter set of uma scenes is labeled index 2, the parameter set of indoor scenes is labeled index 3, and so on. Each parameter set (including encoder and decoder) may be assigned a separate website address for downloading, and the index of the scene may be linked to the corresponding address of the corresponding parameter set.

Further, the second device 220 may update the parameter set of the NN based on the upcoming channel samples, or even generate some different kinds of NN architectures and corresponding parameter sets based on training requirements. The second device 220 can flexibly adjust the index of the NN model and the corresponding website address in RRC signaling.

As another option, sets of parameters associated with different kinds of NN models may also be transmitted 310 from the second device 220 to the first device 210. For example, the sets of parameters may be transmitted through higher layer RRC signaling.

In addition, indications of mappings between types of various channel scenarios and different kinds of NN models may also be transmitted from the second device 220 to the first device 210.

The second device 220 transmits 315 a reference signal to the first device 210 for measurement of a channel between the first device 210 and the second device 220. For example, the reference signal may be referred to as a channel state information reference signal (CSI-RS). After receiving the reference signal, the first device 210 may perform measurements on the reference signal.

Based on the measurement, the first device 210 determines 320 a scenario of a channel between the first device 210 and the second device 220. For example, the first device 210 may determine the characteristics of the channel based on the measurement of the reference signal. For example, the characteristics may include at least multipath effects of the channel and spatial fading correlations of the channel. The first device 210 may determine the scene based on characteristics of the channel.

Based on the determined scenario of the channel, the first device 210 may determine an appropriate NN model for quantization with respect to a channel matrix characterizing the channel. As described above, mappings between multiple types of scenes and multiple candidate models are received from the second device 220. Based on the mapping and the determined scene, the first device 210 may determine an index of the NN model.

Further, in order to classify channel scenarios, another NN may be applied here according to the analyzed channel characteristics, and a mapping from current channel information to an appropriate NN index may be implemented.

As an option, the first device 210 may obtain a set of parameters for the NN encoder 105 of the determined NN model from the server. The set of parameters may include a first set of parameters for compressing coefficients of the channel matrix. For example, the first device 210 may determine a target address for accessing the set of parameters for the NN encoder 105 based on a mapping between an index of the NN model and a corresponding address in the server, and download the set of parameters from the server based on the target address.

As another option, if multiple sets of parameters associated with different classes of NN models have been provided from the second device 220 to the first device 210, the first device 210 may determine models from the different classes of NN models based on the determined indices of the NN models and obtain the set of parameters for the encoder 105 corresponding to the NN models from the multiple sets of parameters.

The first device 210 may configure the encoder 105 of the NN model according to the acquired set of parameters. Based on the reference signals, a channel matrix may be generated to characterize the channel. The first device 210 may quantize the channel matrix based on the model and generate 325 quantized coefficients associated with the channel. In the quantization process, the channel matrix may be transformed and compressed into fewer channel elements by NN encoding 105, and then the coefficients of the channel elements may be quantized on a model. The output of the NN encoder 105 may be a quantized coefficient.

The first device 210 may transmit 330 the quantized coefficients to the second device 220 to report channel state information. If the second device 220 receives the quantized coefficients, the second device 220 may recover the original channel matrix from the quantized coefficients.

Since the encoder 105 and decoder 110 of the NN model should be used in pairs in view of end-to-end training requirements, the second device 220 should use a corresponding decoder 110 with the same NN index as the encoder 105 used by the first device 210.

As an option, the first device 210 may transmit an indication of the model to the second device 220, e.g., to indicate an index of the NN model used to quantize the original channel matrix. For example, in addition to normal CSI feedback, the first device 210 may report an index of the identified channel scene or an index of the NN model with few bits.

As another option, the first device 210 may transmit an uplink sounding or pilot signal to the second device 220 so that the second device 220 may identify a particular channel scenario by analyzing uplink channel characteristics. In general, the second device 220 may determine the common channel type, and thus the common NN index, taking into account the duality of certain characteristics between the uplink and downlink channels.

Thus, the second device 220 may be aware of the NN model for quantizing the original channel matrix. Similar to the first device 210, the second device 220 may obtain a second set of parameters for recovering the original channel matrix from a separate device (such as a server, cloud server, or any suitable network management node) other than the first device 210 and the second device 220.

While the NN model is typically trained in the second device 220, it should be understood that the NN model may also be trained in a server, for example. Thus, after determining the index of the NN model, the set of parameters for recovering the original channel matrix may be obtained from the server to the second device 220. Otherwise, the set of parameters may also be obtained from the second device 220 itself.

The second device 220 may configure the decoder 110 according to the determined NN model. The second device 220 then decompresses 335 the quantized coefficients based on the NN model to obtain a recovered channel matrix for the channel. Specifically, the second device 220 performs an inverse transform on the multi-layered NN decoder 110 and restores an original channel matrix from the received CSI (i.e., quantized coefficients).

In this way, the downloadable NN mechanism may be flexibly deployed through download or signaling instructions and use the NN architecture and corresponding parameter sets, as well as ensure accurate feedback and recovery of the original channel information by utilizing the NN structure in pairs in both the first device 210 and the second device 220.

Fig. 4 shows a flow chart of an example method 400 of CSI feedback. According to some example embodiments of the present disclosure. The method 400 may be implemented at the first device 210 as shown in fig. 1. For discussion purposes, the method 400 will be described with reference to FIG. 1.

As shown in fig. 4, at 410, the first device 210 obtains a channel matrix for a channel between the first device and the second device based on a reference signal received from the second device.

At 420, the first device 210 determines a scenario of a channel. The scenario may indicate the usage environment of the support channel.

In some example embodiments, the first device 210 may determine characteristics of the channel based on the reference signal, the characteristics including at least multipath effects of the channel or spatial fading correlations of the channel, and the first device 210 may determine the scene based on the determined characteristics of the channel.

At 430, the first device 210 generates quantization coefficients by quantizing the channel matrix based on the model. The first set of parameters of the model may be obtained based on the type of scene of the channel.

In some example embodiments, the first device 210 may receive, from the second device 220, an indication of a mapping between a plurality of types of scenes and a plurality of candidate models, and a first set of parameters of at least one candidate associated with the plurality of candidate models, and determine an index of the model based on the mapping and the type of scene of the channel. The first device 210 may also determine a first set of parameters of the candidate from among a first set of parameters of the at least one candidate based on the index as the first set of parameters.

In some example embodiments, the first device 210 may also receive an indication of a mapping of a plurality of types of scenes, a plurality of candidate models, and a set of candidate addresses in the third device from the second device 220. The first device 210 may also determine a target address in the third device for accessing the first set of parameters based on the mapping and the type of scene of the channel. The first device 210 may also obtain a first set of parameters from a third device based on the target address.

At 440, the first device 210 transmits the quantized coefficients to the second device.

In some example embodiments, the first device 210 may transmit an indication of the model to the second device 220.

In some example embodiments, the first device 210 may transmit additional reference signals to the second device 220 to enable the second device 220 to determine the context of the channel.

Fig. 5 illustrates a flowchart of an example method 500 of CSI feedback according to some example embodiments of the present disclosure. The method 500 may be implemented at the second device 220 as shown in fig. 1. For discussion purposes, the method 500 will be described with reference to FIG. 1.

As shown in fig. 5, at 510, the second device 220 transmits a reference signal to the first device for measurement of a channel between the first device and the second device.

At 520, the second device 220 receives quantized coefficients associated with the channel from the first device. The quantized coefficients may be generated by the model at the first device based on the reference signal.

At 530, the second device 220 obtains a restored channel matrix for the channel by decompressing the quantized coefficients based on the model.

In some example embodiments, the second device 220 may determine a plurality of candidate models for a scene of the channel and establish a mapping between a plurality of types of the scene and the plurality of candidate models. The second device 220 may transmit an indication of the mapping and a first set of parameters of at least one candidate associated with the plurality of candidate models to the first device.

In some example embodiments, the second device 220 may determine a plurality of candidate models for the scene of the channel and build a mapping of the plurality of types of the scene, the plurality of candidate models, and a set of candidate addresses in the third device. The second device 220 may transmit an indication of the mapping to the first device.

In some embodiments, the indication may be transmitted via higher layer signaling.

In some example embodiments, the second device 220 may determine a plurality of candidate models for a scene of the channel and provide candidate parameters of the plurality of candidate models to the first device or the third device.

In some example embodiments, the second device 220 may receive an indication of the model from the first device. The second device 220 may also determine a model based on the indication and obtain a second set of parameters of the model for decompressing the quantized coefficients.

In some example embodiments, the second device 220 may receive additional reference signals from the first device and determine a scenario of the channel based on the additional reference signals. The scenario may indicate the usage environment of the support channel. The second device 220 may determine a model based on the type of scene and obtain a second set of parameters of the model for decompressing the quantized coefficients.

In some example embodiments, the second device 220 may determine a target address in the third device for accessing the second set of parameters based on the plurality of types of model scenarios, the plurality of candidate models, and a mapping of a set of candidate addresses in the third device, and obtain the second set of parameters from the third device based on the target address.

In some example embodiments, an apparatus capable of performing the method 400 (e.g., implemented at the first device 210) may include means for performing the respective steps of the method 400. The component may be implemented in any suitable form. For example, the components may be implemented using circuitry or software modules.

In some example embodiments, the apparatus includes means for determining a scenario of a channel between a first device and a second device, the scenario indicating a usage environment supporting the channel; means for obtaining a channel matrix of the channel based on the reference signal received from the second device; means for generating quantization coefficients by quantizing a channel matrix based on a model, a first set of parameters of the model being obtained based on a type of scene of the channel; and means for transmitting the quantized coefficients to the second device.

In some example embodiments, an apparatus capable of performing the method 500 (e.g., implemented at the second device 220) may include means for performing the respective steps of the method 500. The component may be implemented in any suitable form. For example, the components may be implemented using circuitry or software modules.

In some example embodiments, the apparatus includes means for transmitting a reference signal to a first device on a channel between the first device and a second device; means for receiving quantized coefficients of a channel from a first device, the quantized coefficients generated by a model at the first device based on a reference signal; means for decompressing the quantized coefficients based on the model to obtain a recovered channel matrix for the channel; and means for determining a state of the channel based on the recovered channel matrix.

Fig. 6 is a simplified block diagram of a device 600 suitable for implementing embodiments of the present disclosure. The device 600 may be provided to implement a communication device, such as the first device 210 and the second device 220 shown in fig. 1. As shown, device 600 includes one or more processors 610, one or more memories 640 coupled to processors 610, and one or more transmitters and/or receivers (TX/RX) 640 coupled to processors 610.

TX/RX 640 is used for two-way communication. TX/RX 640 has at least one antenna to facilitate communication. The communication interface may represent any interface necessary to communicate with other network elements.

The processor 610 may be of any type suitable to the local technical network and may include, as non-limiting examples, one or more of the following: general purpose computers, special purpose computers, microprocessors, digital Signal Processors (DSPs), and processors based on a multi-core processor architecture. The device 600 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock that is synchronized to the master processor.

Memory 620 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memory include, but are not limited to, read-only memory (ROM) 624, electrically programmable read-only memory (EPROM), flash memory, hard disks, compact Disks (CD), digital Video Disks (DVD), and other magnetic and/or optical storage. Examples of volatile memory include, but are not limited to, random Access Memory (RAM) 622 and other volatile memory that does not persist during power outages.

The computer program 630 includes computer-executable instructions that are executed by the associated processor 610. Program 630 may be stored in ROM 620. Processor 610 may perform any suitable actions and processes by loading program 630 into RAM 620.

Embodiments of the present disclosure may be implemented by means of program 630 such that device 600 may perform any of the processes of the present disclosure as discussed with reference to fig. 3-5. Embodiments of the present disclosure may also be implemented in hardware or a combination of software and hardware.

In some embodiments, program 630 may be tangibly embodied in a computer-readable medium that may be included in device 600 (such as in memory 620) or other storage device accessible to device 600. Device 600 may load program 630 from a computer readable medium into RAM 622 for execution. The computer readable medium may include any type of tangible, non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. Fig. 7 shows an example of a computer readable medium 700 in the form of a CD or DVD. The computer readable medium has stored thereon the program 630.

In general, the various embodiments of the disclosure may be implemented using hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of the embodiments of the disclosure are illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that blocks, apparatus, systems, techniques or methods 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.

The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product comprises computer executable instructions, such as instructions included in a program module, that are executed in a device on a target real or virtual processor to perform the methods 400 and 500 as described above with reference to fig. 4-5. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In various embodiments, the functionality of the program modules may be combined or split between program modules as desired. Machine-executable instructions of program modules may be executed within local or distributed devices. In a distributed device, program modules may be located in both local and remote memory storage media.

Program code for carrying out the methods of the present disclosure may be written in any combination of one or more programming languages. These 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, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the 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.

In the context of this disclosure, computer program code or related data may be carried by any suitable carrier to enable an apparatus, device or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, and the like.

The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is 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 a 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.

Further, while operations are described in a particular order, this should not be construed 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 some cases, multitasking and parallel processing may be advantageous. Also, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the disclosure has been described in language specific to structural features and/or methodological acts, it is to be understood that the 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

1. A first device for channel state information feedback, comprising:

At least one processor; and

At least one memory including computer program code;

the at least one memory and the computer program code are configured to, with the at least one processor, cause the first device to at least:

obtaining a channel matrix of a channel between the first device and a second device based on a reference signal received from the second device;

Determining a scene of a channel, the scene indicating a usage environment supporting the channel;

Generating quantization coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being acquired based on a type of the scene of the channel; and

Transmitting the quantized coefficients to the second device,

Wherein the first device is further caused to:

Receiving, from the second device, an indication of a mapping between a plurality of types of a scene and a plurality of candidate models, and a first set of parameters of at least one candidate associated with the plurality of candidate models;

determining an index of the model based on the mapping and the type of the scene of the channel; and

A first set of parameters of the candidate is determined as the first set of parameters from the at least one first set of parameters of the candidate based on the index.

2. The first device of claim 1, wherein the first device is caused to determine the scene by:

Determining characteristics of the channel based on the reference signal, the characteristics including at least:

multipath effects of the channel, or

Spatial fading correlation of the channel; and

The scene is determined based on the determined characteristics of the channel.

3. The first device of claim 1, wherein the first device is further caused to:

Receiving, from the second device, an indication of a mapping of a plurality of types of scenes, a plurality of candidate models, and a set of candidate addresses in a third device;

Determining a target address in a third device for accessing the first set of parameters based on the mapping and the type of the scene of the channel; and

The first set of parameters is obtained from the third device based on the target address.

4. The first device of claim 1, wherein the first device is further caused to:

Transmitting an indication of the model to the second device.

5. The first device of claim 1, wherein the first device is further caused to:

transmitting a further reference signal to the second device to enable the second device to determine the scene of the channel.

6. The first device of claim 1, wherein the first device is a terminal device and the second device is a network device.

7. A first device as claimed in claim 3, wherein the third device is a server shared by the first device and the second device.

8. A second device for channel state information feedback, comprising:

At least one processor; and

At least one memory including computer program code;

The at least one memory and the computer program code are configured to, with the at least one processor, cause the second device to at least:

transmitting a reference signal to a first device for measurement of a channel between the first device and the second device;

receiving, from the first device, quantized coefficients associated with the channel, the quantized coefficients generated by a model at the first device based on the reference signal; and

Obtaining a restored channel matrix for the channel by decompressing the quantized coefficients based on a second set of parameters of the model,

Wherein the second device is further caused to:

Determining a plurality of candidate models for a scene of the channel;

establishing a mapping between a plurality of types of the scene and the plurality of candidate models; and

An indication of the mapping and a first set of parameters of at least one candidate associated with the plurality of candidate models are transmitted to the first device.

9. The second device of claim 8, wherein the second device is further caused to:

Determining a plurality of candidate models for a scene of the channel;

establishing a mapping of a plurality of types of scenes, a plurality of candidate models and a set of candidate addresses in a third device; and

An indication of the mapping is transmitted to the first device.

10. The second device of claim 8 or 9, wherein the indication is transmitted via higher layer signaling.

11. The second device of claim 8, wherein the second device is further caused to:

determining a plurality of candidate models for a scene of the channel; and

Candidate parameters of the plurality of candidate models are provided to a third device.

12. The second device of claim 8, wherein the second device is further caused to:

receiving an indication of the model from the first device;

Determining the model based on the indication; and

The second set of parameters of the model is obtained for decompressing the quantized coefficients.

13. The second device of claim 8, wherein the second device is further caused to:

receiving a further reference signal from the first device;

determining a context of the channel based on the further reference signal, the context indicating a usage environment supporting the channel;

Determining the model based on the type of the scene; and

14. The second device of claim 12 or 13, wherein the second device is caused to obtain the second set of parameters by:

determining a target address in the third device for accessing the second set of parameters based on the model and a mapping of a plurality of types of scenes, a plurality of candidate models, and a set of candidate addresses in the third device; and

The second set of parameters is obtained from the third device based on the target address.

15. The second device of claim 9, wherein the first device is a terminal device and the second device is a network device.

16. The second device of claim 9 or 11, wherein the third device is a server shared by the first device and the second device.

17. A method for channel state information feedback, comprising:

obtaining a channel matrix of a channel between a first device and a second device based on a reference signal received from the second device;

Transmitting the quantized coefficients to the second device,

Wherein the method further comprises:

18. The method of claim 17, wherein determining the scene comprises:

multipath effects of the channel, or

Spatial fading correlation of the channel; and

The scene is determined based on the determined characteristics of the channel.

19. The method of claim 17, further comprising:

20. The method of claim 17, further comprising:

Transmitting an indication of the model to the second device.

21. The method of claim 17, further comprising:

22. The method of claim 17, wherein the first device is a terminal device and the second device is a network device.

23. The method of claim 19, wherein the third device is a server shared by the first device and the second device.

24. A method for channel state information feedback, comprising:

Transmitting a reference signal to a first device for measurement of a channel between the first device and a second device;

Receiving, from the first device, quantized coefficients associated with the channel, the quantized coefficients generated by a model at the first device based on the reference signal;

Wherein the method further comprises:

Determining a plurality of candidate models for a scene of the channel;

Establishing a mapping between the plurality of candidate models and a plurality of types of the scene; and

25. The method of claim 24, further comprising:

Determining a plurality of candidate models for a scene of the channel;

An indication of the mapping is transmitted to the first device.

26. The method of claim 24 or 25, wherein the indication is transmitted via higher layer signaling.

27. The method of claim 25, further comprising:

determining a plurality of candidate models for a scene of the channel; and

Candidate parameters for the plurality of candidate models are transmitted to the third device.

28. The method of claim 24, further comprising:

receiving an indication of the model from the first device;

Determining the model based on the indication; and

29. The method of claim 24, further comprising:

Receiving a further reference signal from the first device on the channel;

Determining the model based on the type of the scene; and

30. The method of claim 28 or 29, wherein obtaining the second set of parameters comprises:

31. The method of claim 24, wherein the first device is a terminal device and the second device is a network device.

32. The method of claim 25 or 27, wherein the third device is a server shared by the first device and the second device.

33. An apparatus for channel state information feedback, comprising:

Means for obtaining a channel matrix of a channel between a first device and a second device based on a reference signal received from the second device;

means for determining a scenario for a channel, the scenario indicating a usage environment supporting the channel;

means for generating quantization coefficients associated with the channel by quantizing the channel matrix based on a model, a first set of parameters of the model being acquired based on a type of the scene of the channel; and

Means for transmitting the quantized coefficients to the second device,

Wherein the device further comprises means for:

34. An apparatus for channel state information feedback, comprising:

Means for transmitting a reference signal to a first device for measurement of a channel between the first device and a second device;

Means for receiving, from the first device, quantized coefficients associated with the channel, the quantized coefficients generated at the first device based on the reference signal providing model; and

Means for obtaining a restored channel matrix for the channel by decompressing the quantized coefficients based on a second set of parameters of the model,

Wherein the device further comprises means for:

Determining a plurality of candidate models for a scene of the channel;

35. A non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method of any one of claims 17 to 23.

36. A non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method of any one of claims 24 to 32.