Apply uplink channel information to determine a data processing model deployed for downlink use

Abstract

Example embodiments of the present disclosure relate to applying uplink channel information to determine a data processing model deployed for downlink use. According to an embodiment, a solution for channel information reporting for applying uplink channel information to determine a data processing model deployed for downlink use has been proposed. A data processing model is determined using an uplink data set (e.g., uplink reference signal), and then the data processing model is used to process downlink CSI. In this way, compared with high-resolution CSI feedback for training, it is more accurate and does not require additional CSI feedback, which significantly reduces the overhead. Since complex CSI processing is not required, this also reduces the implementation work on the terminal device side.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of telecommunications, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for applying uplink channel information to determine a data processing model deployed for downlink use. Background Art

[0002] In wireless communication, channel information (e.g., channel state information (CSI)) refers to the known channel attributes of a communication link. This information describes how a signal propagates from a transmitter to a receiver, and represents, for example, the combined effects of scattering, fading, and power attenuation over distance. CSI makes it possible to adapt transmissions to current channel conditions, which is crucial for reliable communication at high data rates in multi-antenna systems. Therefore, how to obtain CSI is very important for communication performance. Summary of the Invention

[0003] Generally, example embodiments of the present disclosure provide a solution for applying uplink channel information to determine a data processing model deployed for downlink use.

[0004] In a first aspect, a first device is provided. The first device includes 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, together with the at least one processor, cause the first device to receive a reference signal from a second device on an uplink channel. The first device is further caused to determine first channel information about the uplink channel at least in part based on the received reference signal. The first device is further caused to extract second channel information about the uplink channel from the first channel information, the second channel information being generated based on the first channel information. The first device is further caused to train a data processing model based on the first channel information and the second channel information, the data processing model to be used to recover channel information about the downlink channel between the first device and the second device.

[0005] In a second aspect, a second device is provided. The second device includes 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, together with the at least one processor, cause the second device to transmit a reference signal to the first device on an uplink channel, the reference signal being used to determine first channel information about the uplink channel, and the first channel information being used to determine a data processing model, the data processing model to be used to recover channel information about the downlink channel between the first device and the second device.

[0006] In a third aspect, a method is provided. The method includes receiving, at a first device, a reference signal from a second device on an uplink channel. The method further includes determining, at least in part based on the received reference signal, first channel information regarding the uplink channel. The method further includes extracting, from the first channel information, second channel information regarding the uplink channel, the second channel information being generated based on the first channel information. The method further includes training, based on the first channel information and the second channel information, a data processing model to be used for recovering channel information regarding a downlink channel between the first device and the second device.

[0007] In a fourth aspect, a method is provided. The method includes transmitting, at a second device, a reference signal to a first device on an uplink channel, the reference signal being used for determining first channel information regarding the uplink channel, and the first channel information being used for determining a data processing model to be used for recovering channel information regarding a downlink channel between the first device and the second device.

[0008] In a fifth aspect, an apparatus is provided. The apparatus includes means for receiving, at a first device, a reference signal from a second device on an uplink channel; means for determining, at least in part based on the received reference signal, first channel information regarding the uplink channel; means for extracting, from the first channel information, second channel information regarding the uplink channel, the second channel information being generated based on the first channel information; and means for training, based on the first channel information and the second channel information, a data processing model to be used for recovering channel information regarding a downlink channel between the first device and the second device.

[0009] In a sixth aspect, an apparatus is provided. The apparatus includes means for transmitting, at a second device, a reference signal to a first device on an uplink channel, the reference signal being used for determining first channel information regarding the uplink channel, and the first channel information being used for determining a data processing model to be used for recovering channel information regarding a downlink channel between the first device and the second device.

[0010] In a seventh aspect, a computer-readable medium is provided. The computer-readable medium includes program instructions for causing an apparatus to perform at least the method according to any one of the third aspect and the fourth aspect described above.

[0011] It should be understood that the summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become readily apparent through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0013] Figure 1 Illustrates an example communication environment in which example embodiments of the present disclosure may be implemented;

[0014] Figure 2 Illustrates a simplified block diagram of a training model according to some example embodiments of the present disclosure;

[0015] Figure 3 Illustrates a signaling flow for applying uplink channel information to determine a data processing model deployed for downlink use according to some example embodiments of the present disclosure;

[0016] Figure 4 Illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;

[0017] Figure 5 Illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;

[0018] Figure 6 Illustrates a flowchart of a method implemented at a second device according to some other example embodiments of the present disclosure;

[0019] Figure 7 Illustrates a simplified block diagram of a device suitable for implementing example embodiments of the present disclosure;

[0020] Figure 8 Illustrates a block diagram of an example computer-readable medium according to some example embodiments of the present disclosure; and

[0021] Figures 9A - 9D Illustrates a graph of simulation results according to some example embodiments of the present disclosure.

[0022] Throughout the drawings, the same or similar reference numerals denote the same or similar elements. Detailed Description

[0023] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that the description of these embodiments is only for the purpose of illustration and to assist those skilled in the art in understanding and implementing the present disclosure, and does not represent any limitation on the scope of the present disclosure. The embodiments described herein may be implemented in various other ways than those described below.

[0024] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure pertains.

[0025] In this disclosure, references to "one embodiment", "an embodiment", "example embodiment", etc., indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment must include 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 within the knowledge of those in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0026] It should be understood that although terms such as "first" and "second" 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. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the example embodiment. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0027] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the example embodiments. The singular forms "a", "an", and "the" as used herein also include the plural forms unless the context clearly dictates otherwise. Further understood, the terms "comprises", "comprising", "has", "having", "includes", and / or "including" when used herein specify the presence of the 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 all of the following:

[0029] (a) A pure hardware circuit implementation (such as an implementation using only analog and / or digital circuitry), and

[0030] (b) A combination of hardware circuitry and software, such as, where applicable:

[0031] (i) A combination of (one or more) analog and / or digital hardware circuitry with software / firmware, and

[0032] (ii) Any portion of (one or more) hardware processors (including (one or more) digital signal processors), software, and (one or more) memories with software that work together to cause a device (such as a mobile phone or a server) to perform various functions, and

[0033] (c) one or more hardware circuits and / or one or more processors, such as one or more microprocessors or a portion of one or more microprocessors, which require software (e.g., firmware)

[0034] to operate, but the software may not be present when operation is not required.

[0035] The definition of the circuitry is suitable for all uses of the term in this application, including in any claims. As another example, as used in this application, the term circuitry also encompasses implementations of only hardware circuits or processors (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. For example, if applicable to a particular claim element, the term circuitry also encompasses a baseband integrated circuit or a processor integrated circuit for a mobile device, or a similar integrated circuit in a server, a cellular network device, or other computing or network devices.

[0036] As used herein, the term "communication network" refers to a network that follows any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), NarrowBand Internet of Things (NB-IoT), etc. Additionally, the communication between a terminal device and a network device in a communication network can be performed according to any suitable generation of communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, future fifth generation (5G) communication protocol, and / or any other protocol currently known or to be developed in the future. Embodiments of the present disclosure can be applied to various communication systems. Considering the rapid development of communication, of course, there will also be future types of communication technologies and systems that can embody the present disclosure. The scope of the present disclosure should not be limited to the above systems.

[0037] As used herein, the term "network device" refers to a node in a communication network through which a terminal device accesses the network and receives services from the network. The network device can refer to a base station (BS) or an access point (AP), for example, Node B (NodeB or NB), evolved Node B (eNodeB or eNB), NR NB (also known as gNB), Remote Radio Unit (RRU), Radio Header (RH), Remote Radio Head (RRH), relay, Integrated and Access Backhaul (IAB) node, low-power node (such as femto, pico), Non-Terrestrial Network (NTN) or non-terrestrial network device (such as satellite network device, Low Earth Orbit (LEO) satellite, and Geostationary Earth Orbit (GEO) satellite), aircraft network device, etc., depending on the terms and technologies applied.

[0038] The term "terminal device" refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices may include, but are not limited to, mobile phones, cellular phones, smart phones, IP voice (VoIP) phones, wireless local loop phones, tablet computers, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image capture terminal devices (such as digital cameras), game terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEE), laptop in-vehicle devices (LME), USB dongles, smart devices, wireless customer premises equipment (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automation processing chain), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. In the following description, the terms "terminal device", "communication device", "terminal", "user equipment", and "UE" may be used interchangeably.

[0039] As described above, how to obtain CSI is very important for communication performance. Machine learning (ML)-based multiple-input multiple-output (MIMO) has attracted great attention and shown its advantages in physical layer solutions such as beamforming and channel state information (CSI) acquisition. ML-based massive MIMO schemes can provide performance enhancement and reduce computational complexity, overhead, and latency.

[0040] For analysis purposes, many ML schemes for CSI acquisition (e.g., including channel estimation, feedback, etc.) and beamforming can use statistical channel models, ray tracing-generated data, or measurement data to offline train a neural network (NN). Since the data sets used in pre-training cannot fully represent the real environment, when such a neural network is deployed in practice, additional training is required to update the weights of the pre-trained NN. In some other cases, the NN can also be directly trained in the real deployed scenario. For example, in CSI feedback and channel estimation applications, the training of the NN requires paired data sets (e.g., real or "reference" CSI and compressed CSI), however, it is difficult to obtain real CSI in practice. Some traditional techniques only assume that accurate CSI can be obtained to train or update the NN in deployment.

[0041] A conventional solution is to apply high-resolution CSI feedback to train the NN in actual deployment. However, data collection incurs very large overhead. Even though it is high-resolution, it is still far from the exact value because the UE needs to quantize the estimated CSI. This CSI quantization with high resolution, which is considered as the reference CSI, also degrades the performance of the NN.

[0042] In a TDD system, due to reciprocity, the uplink CSI can be directly used to train the NN for the downlink. However, in an FDD system, when reciprocity does not hold, this concept cannot be applied.

[0043] According to an embodiment, a solution for channel information reporting has been proposed, which is used to apply uplink channel information to determine a data processing model deployed for downlink use. The data processing model is determined using an uplink data set (e.g., uplink reference signal), and then the data processing model is used to process the downlink CSI. In this way, compared with the high-resolution CSI feedback for training, it is more accurate and does not require additional CSI feedback, which significantly reduces the overhead. Since complex CSI processing is not required, this also alleviates the implementation work on the terminal device side.

[0044] Figure 1 A schematic diagram of a communication environment 100 in which embodiments of the present disclosure can be implemented is shown. The communication environment 100 includes a first device 110. The communication environment 100 (which is part of a communication network) also includes devices 120-1, 120-2, ……, 120-N (which can be collectively referred to as “(multiple) second devices 120”). The first device 110 and the second device 110 can communicate with each other.

[0045] The communication environment 100 can include any suitable number of devices and cells. In the communication environment 100, the first device 110 and the second device 120 can transmit data and control information to each other. In the case where the first device 110 is a network device and the second device 120 is a terminal device, the link from the second device 120 to the first device 110 is called the uplink (UL), and the link from the first device 110 to the second device 120 is called the downlink (DL). The second device 120 and the first device 110 are interchangeable.

[0046] It should be understood that Figure 1 The number of the first devices and cells shown and their connections are given for illustrative purposes without any limitation. The communication environment 100 can include any suitable number of devices and networks suitable for implementing the embodiments of the present disclosure.

[0047] Communication in the communication environment 100 can be implemented according to any suitable communication protocol(s), including but not limited to cellular communication protocols such as the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), and fifth generation (5G), wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol known currently or to be developed in the future. In addition, the communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplexing (FDD), Time Division Duplexing (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiplexing (OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), and / or any other technology known currently or to be developed in the future.

[0048] Figure 2 A simplified block diagram of an apparatus 200 for training a model according to some example embodiments of the present disclosure is shown. The apparatus 200 can be implemented at the first device 110. Alternatively, the apparatus 200 can be implemented at the second device 120. It should be noted that the embodiments of the present disclosure are not limited thereto.

[0049] The apparatus 200 can include a module 210 that can be used to compress a first CSI to obtain a second CSI. The second CSI can have less information than the first CSI. The apparatus can also include a module 220 that can be used to train a data processing model based on the first CSI and the second CSI. In this way, by using the data processing model, the downlink CIS can be obtained more accurately. In addition, it does not require additional CSI feedback, which significantly reduces the overhead. Since complex CSI processing is not required, this also reduces the implementation work on the terminal device side.

[0050] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Now refer to Figure 3 , Figure 3 A signaling flow 300 for training a downlink data processing model using uplink channel information according to an example embodiment of the present disclosure is shown. For ease of discussion, the signaling flow 300 will be described with reference to Figure 1 The signaling flow 300 can involve the first device 110 and the second device 120-1.

[0051] For illustrative purposes, by way of example, a clustering model can be applied to characterize the channel between the first device 110 and the second device 120-1, which is written as

[0052]

[0053] where α ijis the complex channel gain of the i-th cluster and the l-th path, and follows a complex normal distribution The number of clusters is denoted by N c and the number of rays / paths within a cluster is N p . The angle of arrival / departure (AoA / AoD) φ il , θ il is uniformly distributed within [0, 2π]. a R (φ il ) and a T (θ il ) are the array response vectors of the second device 120-1 and the first device 110 at angles φ il , θ il respectively.

[0054] The second device 120-1 transmits a 3005 reference signal to the first device 110 on the uplink channel. The reference signal can be any suitable signal that can be used for channel estimation. For example, the reference signal can be a sounding reference signal (SRS). Alternatively, a demodulation reference signal can be used.

[0055] In some example embodiments, the second device 10-1 may compensate the reference signal before transmission. For example, the compensation parameter can be determined based on the frequency of the uplink channel (hereinafter referred to as "the first frequency") and the frequency of the downlink channel (hereinafter also referred to as "the second frequency"). The second device 120-1 may apply the compensation parameter to the reference signal. For example, the phase of the reference signal can be compensated based on the compensation parameter. From the antenna perspective: the antenna array response depends on the carrier frequency. Taking a uniform linear array (ULA) with N antenna elements as an example, its array response at an incident angle of θ can be expressed in a general form as

[0056]

[0057] where f c is the carrier frequency, c is the speed of light, d represents the distance between two adjacent antenna elements (assumed to be the same for both the uplink and downlink), C N represents that the dimension of the matrix is N*1. If the relationship between the first frequency (f UL ) and the second frequency (f DL ) is expressed as f DL = f UL +Δf, then Δf is called the uplink / downlink frequency duplex distance. Therefore, the antenna responses of the n-th element in the uplink and downlink can be obtained by the following formula:

[0058]

[0059]

[0060] where f c is the carrier frequency, c is the speed of light, and d represents the distance between two adjacent antenna elements (assumed to be the same for both uplink and downlink).

[0061] It can be seen that the difference in the antenna array between the uplink and the downlink lies in the term Therefore, from the perspective of the antenna response, there is a difference between the uplink and the downlink due to the frequency duplex distance. To use the uplink data to train the downlink data processing model, it is necessary to compensate the antenna array manifold.

[0062] For the sake of illustration, the channel model can be simplified to a cluster-based model as follows

[0063]

[0064] where ρ is the normalization factor. This expression can be represented by a matrix

[0065]

[0066] where is the vector representing the composite gain of the clusters, and are the concatenations of the array response vectors of all the clusters from the second device 120-1 and the first device 110, respectively.

[0067] According to equations (3) and (4), the compensation matrix for the downlink array response vector using the dimension N of the uplink counterpart can generally be expressed as:

[0068]

[0069] where f c is the carrier frequency, c is the speed of light, d represents the distance between two adjacent antenna elements (assumed to be the same for both uplink and downlink), and the dimension of this matrix is N*N.

[0070] Therefore, the transition from the uplink to the downlink can be obtained by the following formula

[0071] A DL = PA UL (8)

[0072] where A DL represents the response vector of the downlink channel, A UL represents the response vector of the uplink channel, and P represents the compensation matrix of the downlink array response vector.

[0073] For example, the reference signal to be transmitted at the second device 120-1 can be represented as s. Therefore, the compensated reference signal can be represented as where the transmission compensation matrix at the second device 121-1 can be obtained by Equation 7.

[0074] In some example embodiments, the first device 110 may also compensate the received reference signal. For example, the compensation parameter can be determined based on the first frequency and the second frequency, and can be applied to the received reference signal. The first device 110 can compensate the phase of the received reference signal based on the compensation parameter. In some example embodiments, the received reference signal can be represented as:

[0075]

[0076] where s represents the original reference signal, is the uplink CSI, and n is the additive white Gaussian noise. The transmission compensation at the second device 120-1 is performed by A according to Equation (8) R，DL = P R A R，UL to achieve.

[0077] In some example embodiments, the compensated received reference signal can be represented as:

[0078]

[0079] where refers to the received compensation matrix at the first device 110 achieved by A according to Equation (9) T，DL = P T A T，UL s represents the original reference signal, is the uplink CSI, n is the additive white Gaussian noise, represents the received reference signal.

[0080] The first device 110 determines the first channel information regarding the uplink channel based on the reference signal. For example, the first device 110 can determine the original reference signal transmitted by the second device 120-1 (e.g., represented as "s" in Equation (9)). Since the uplink channel between the first device 110 and the second device 120-1 is not an ideal channel, the reference signal transmitted at the second device 120-1 and the reference signal received at the first device 110 may not be the same. The original reference signal refers to the reference signal without any attenuation, interference, or noise. In some example embodiments, the original reference signal can be predetermined so that the first device 110 can obtain the original reference signal. In some example embodiments, the first channel information can be represented as:

[0081]

[0082] wherein refers to the receive compensation matrix at the first device 110 implemented by A T，DL =P T A T，UL and is the uplink CSI is the uplink CSI

[0083] Alternatively, the first device 110 may monitor the uplink channel to receive reference signals during a predetermined time period. The first device 110 may receive any suitable number of reference signals. The first channel information may be determined based on the reference signals received during the predetermined time period. For example, the first device 110 may receive one or more reference signals within a predetermined duration. Alternatively, if the number of data bursts received by the first device 110 is below a threshold number, the first device 110 may continue to monitor the uplink channel and receive (multiple) reference signals

[0084] The first device 110 extracts 3015 second channel information from the first channel information. The second channel information is generated based on the first channel information. The second channel information may have less information than the first channel information. In some example embodiments, the second channel information may be generated by compressing the first channel information. Alternatively or additionally, the first channel information may be quantized to obtain the second channel information. In other embodiments, the second channel information may be codebook-based information. The second channel information may be capable of representing the first channel information but is more concise than the first channel information. It should be noted that the second channel information may be obtained using any suitable processing. Embodiments of the present disclosure are not limited thereto. In some example embodiments, the second channel information may be obtained in a manner similar to how a UE generates processed UL-CSI. For example, the first device 110 and the second device 120-1 may utilize the same processing to respectively obtain the second channel information and the processed UL-CSI

[0085] The first device 110 trains 3020 a data processing model based on the first channel information and the second channel information. In some example embodiments, the second channel information may be recovered using the data processing model. The first device 110 may compare the recovered second channel information with the first channel information. The first device 110 may update the data processing model based on this comparison. If the difference exceeds a threshold, it indicates that the recovered second channel information does not include sufficient channel information. The first device 110 may continue to train the data processing model. Alternatively, if the difference between the recovered second channel information and the first channel information is below the threshold, the parameters of the current data processing model may be used for the downlink. The first device 110 may stop training the data processing model

[0086] Figure 4 FIG. 400 is a flowchart showing an example method for training a data processing model. The first device 110 may use the first channel information and the second channel information to train the data processing model. It should be noted that method 400 is only an example and not a limitation. The data processing model may be determined in any suitable manner.

[0087] At block 410, the first device 110 may use the data processing model to recover the second channel information. At block 420, the first device 110 may apply a loss function to train the data processing model. In some example embodiments, the loss function may be the mean square error (MSE) of channel estimation. For example, the MSE may be expressed as:

[0088]

[0089] where the mapping function of the data processing model is represented by Θ represents the parameters to be adjusted in the data processing model N d is the number of training samples, i represents the i-th training sample, represents the first channel information, represents the second channel information. When the training is completed, the parameters Θ of the data processing model can be obtained.

[0090] Since the first channel information can represent the distribution of the accurate downlink channel information (H DL ), the trained data processing model can be directly applied to the CSI acquisition process. Thus, in the estimation phase, the input of the trained data processing model is the CSI feedback and the data processing model can recover the downlink CSI

[0091] According to an embodiment of the present disclosure, the data processing model is trained using the uplink channel information and can be applied to recover the downlink channel information. Compared with the traditional technology, it is more accurate. It does not require additional CSI feedback, thus significantly reducing the overhead.

[0092] Referring again to Figure 3 , the first device 110 may transmit 3025 additional reference signals to the second device 120-1 on the downlink channel. For example, the additional reference signal may be a CSI reference signal. Alternatively, a demodulation reference signal may be transmitted.

[0093] The second device 120-1 may determine 3030 channel information regarding the downlink channel based on additional reference signals. For example, the second device 120-1 may estimate the channel information regarding the downlink channel. The second device 120 may further extract the channel information regarding the downlink channel. For example, the channel information may be compressed. Alternatively, the second device 120-1 may quantize the channel information regarding the downlink channel.

[0094] The second device 120-1 may generate 3035 feedback on the additional reference signals. The feedback may include the extracted channel information regarding the downlink channel. The second device 120-1 may transmit 3040 the feedback to the first device 110.

[0095] The first device 110 may use a trained data processing model to recover 3045 the channel information regarding the downlink channel from the feedback. In this way, the downlink channel information may be recovered without additional overhead.

[0096] In some example embodiments, the first device 110 may monitor whether the data processing model is appropriate. For example, the second device 120-1 may transmit uplink CSI, and the first device 110 may use the data processing model to recover the uplink CSI. The first device 110 may compare the recovered uplink CSI with the accurate uplink CSI. If the comparison indicates that the recovered uplink CSI includes most of the information in the accurate uplink CSI, the data processing model is still applicable. If the recovered uplink CSI does not meet the requirement, the data processing model needs to be retrained.

[0097] Figure 5 A flowchart of an example method 500 implemented at the first device 110 according to some example embodiments of the present disclosure is shown. For the purpose of discussion, method 500 will be described from the perspective of the first device 110.

[0098] In block 510, the first device 110 receives a reference signal from the second device 120 on an uplink channel. The reference signal may be any suitable signal that can be used for channel estimation. For example, the reference signal may be an SRS. Alternatively, a demodulation reference signal may be used.

[0099] In some example embodiments, the first device 110 may also compensate the received reference signal. For example, the compensation parameter may be determined based on a first frequency and a second frequency.

[0100] At block 520, the first device 110 determines first channel information regarding an uplink channel based on reference signals. Alternatively, the first device 110 may monitor the uplink channel to receive reference signals during a predetermined time period. The first device 110 may receive any suitable number of reference signals. The first channel information may be determined based on the reference signals received during the predetermined time period. For example, the first device 110 may receive one or more reference signals within a predetermined duration. Alternatively, if the number of data bursts received by the first device 110 is below a threshold number, the first device 110 may continue to monitor the uplink channel and receive the reference signals.

[0101] At block 530, the first device 110 extracts second channel information from the first channel information. The second channel information is generated based on the first channel information. In some example embodiments, the second channel information may be obtained by compressing the first channel information. Alternatively, the first channel information may be quantized to obtain the second channel information. The second information may have less information than the first channel information. In some example embodiments, the second channel information may be obtained in a manner similar to how a UE generates processed UL-CSI.

[0102] At block 540, the first device 110 trains a data processing model based on the first channel information and the second channel information. In some example embodiments, the second channel information may be recovered using the data processing model. The first device 110 may compare the recovered second channel information with the first channel information. The first device 110 may update the data processing model based on the comparison. If the difference exceeds a threshold, it indicates that the recovered second channel information does not include sufficient channel information. The first device 110 may continue to train the data processing model. Alternatively, if the difference between the recovered second channel information and the first channel information is below the threshold, the parameters of the current data processing model may be used for the downlink. The first device 110 may stop training the data processing model.

[0103] In some example embodiments, the first device 110 may transmit additional reference signals to the second device 120-1 on a downlink channel. For example, the additional reference signals may be CSI reference signals. Alternatively, demodulation reference signals may be transmitted. The first device 110 may receive feedback from the second device 120-2, the feedback including the extracted channel information regarding the downlink channel. The first device 110 may use the trained data processing model to recover the channel information regarding the downlink channel from the feedback. In this way, the downlink channel information may be recovered without additional overhead.

[0104] In some example embodiments, the first device 110 may monitor whether the data processing model is appropriate. For example, the second device 120-1 may transmit uplink CSI, and the first device 110 may use the data processing model to recover the uplink CSI. The first device 110 may compare the recovered uplink CSI with the accurate uplink CSI. If the comparison indicates that the recovered uplink CSI includes most of the information in the accurate uplink CSI, the data processing model is still applicable. If the recovered uplink CSI is not satisfied, the data processing model needs to be retrained.

[0105] Figure 6 FIG. 4 shows a flowchart of an example method 600 implemented at the second device 120 according to some example embodiments of the present disclosure. For the purpose of discussion, method 600 will be described from the perspective of the second device 120. It should be noted that the dashed boxes are optional.

[0106] Optionally, in an example embodiment, at block 605, the second device 10-1 may compensate the reference signal before transmission. For example, the compensation parameter may be determined based on a first frequency and a second frequency.

[0107] At block 610, the second device 120-1 transmits a reference signal to the first device 110 on the uplink channel. The reference signal may be any suitable signal that can be used for channel estimation. For example, the reference signal may be a sounding reference signal (SRS). Alternatively, a demodulation reference signal may be used.

[0108] In some example embodiments, at block 620, the second device 120-1 may receive an additional reference signal from the first device 110 on the downlink channel. For example, the additional reference signal may be a CSI reference signal. Alternatively, a demodulation reference signal may be transmitted. At block 630, the second device 120-1 may generate feedback on the additional reference signal. The feedback may include the extracted channel information about the downlink channel. In some example embodiments, at block 640, the second device 120-1 may transmit the feedback to the first device 110.

[0109] In some example embodiments, a first apparatus (e.g., the first device 110) capable of performing any method 500 may include components for performing the corresponding operations of method 500. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The first apparatus may be implemented as the first device 110 or included in the first device 110. In some example embodiments, the components may include 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 cause the operation of the apparatus together with the at least one processor.

[0110] In some example embodiments, the apparatus includes components for receiving a reference signal from a second device on an uplink channel at a first device; components for determining first channel information regarding the uplink channel based at least in part on the received reference signal; components for extracting second channel information regarding the uplink channel from the first channel information, the second channel information being generated based on the first channel information; and components for training a data processing model based on the first channel information and the second channel information, the data processing model being for recovering channel information regarding a downlink channel between the first device and the second device.

[0111] In some example embodiments, the components for training the data processing model include components for iteratively performing the following operations: recovering the second channel information using the data processing model; comparing the recovered second channel information with the first channel information; and updating the data processing model based on the comparison until the difference between the recovered second channel information and the first channel information is less than a threshold.

[0112] In some example embodiments, the apparatus further includes components for determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; and components for compensating the phase of the received reference signal based on the compensation parameter.

[0113] In some example embodiments, the components for determining the first uplink channel information include components for determining an original reference signal transmitted by the second device; and components for determining the first channel information based on the original reference signal and the received reference signal.

[0114] In some example embodiments, the apparatus further includes components for transmitting an additional reference signal to the second device on the downlink channel; components for receiving feedback from the second device regarding the additional reference signal, the feedback including extracted channel information regarding the downlink channel; and components for recovering channel information regarding the downlink channel from the feedback using the data processing model.

[0115] In some example embodiments, the components for receiving the reference signal include components for monitoring the uplink channel to receive the reference signal during a predetermined time period.

[0116] In some example embodiments, the first device includes a network device and the second device includes a terminal device.

[0117] In some example embodiments, a second apparatus (e.g., the second device 120) capable of performing any method 600 may include components for performing the corresponding operations of method 600. The components may be implemented in any suitable form. For example, the components may be implemented in circuitry or software modules. The first apparatus may be implemented as or included in the second device 120. In some example embodiments, the components may include 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 cause the operation of the apparatus together with the at least one processor.

[0118] In some example embodiments, the apparatus includes components for transmitting a reference signal on an uplink channel at the second device to the first device, the reference signal being for determining first channel information regarding the uplink channel, and the first channel information being for determining a data processing model, the data processing model being to be used to recover channel information regarding a downlink channel between the first device and the second device.

[0119] In some example embodiments, the components for transmitting the reference signal include: components for determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; and components for compensating the phase of the reference signal based on the compensation parameter.

[0120] In some example embodiments, the apparatus further includes components for receiving an additional reference signal from the first device on the downlink channel; components for determining channel information regarding the downlink channel based on the additional reference signal; components for generating feedback on the additional reference signal, the feedback including the extracted channel information regarding the downlink channel; and components for transmitting the feedback to the first device.

[0121] In some example embodiments, the first device includes a network device and the second device includes a terminal device.

[0122] Figure 7 is a simplified block diagram of a device 700 suitable for implementing example embodiments of the present disclosure. The device 700 may be provided to implement a communication device, such as Figure 1 the first device 110 or the second device 120 shown. As shown, the device 700 includes one or more processors 710, one or more memories 720 coupled to the processors 710, and one or more communication modules 740 coupled to the processors 710.

[0123] The communication module 740 is used for two-way communication. The communication module 740 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface can represent any interface necessary for communication with other network elements. In some example embodiments, the communication module 740 may include at least one antenna.

[0124] The processor 710 can be of any type suitable for the local technical network and, by way of non-limiting example, can include one or more of the following: a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. The device 700 can have multiple processors, such as an application-specific integrated circuit chip that is subordinate in time to a clock synchronized with the main processor.

[0125] The memory 720 can include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 724, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), optical disc, laserdisc, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 722 and other volatile memories that do not persist during a power outage.

[0126] The computer program 730 includes computer-executable instructions executed by the associated processor 710. The program 730 can be stored in a memory (such as ROM 724). The processor 710 can perform any suitable actions and processes by loading the program 730 into the RAM 722.

[0127] Example embodiments of the present disclosure can be implemented by the program 730 such that the device 700 can execute any process of the present disclosure referred to Figures 3 to 6 in the discussion. Example embodiments of the present disclosure can also be implemented by hardware or a combination of software and hardware.

[0128] In some example embodiments, the program 730 can be tangibly embodied in a computer-readable medium, which can be included in the device 700 (such as in the memory 720) or other storage devices accessible by the device 700. The device 700 can load the program 730 from the computer-readable medium into the RAM 722 for execution. The computer-readable medium can include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, and other magnetic storage devices and / or optical storage devices. Figure 8 An example of a computer-readable medium 800 in the form of an optical storage disc is shown. The program 730 is stored on the computer-readable medium.

[0129] Figures 9A - 9D A figure showing simulation results according to some example embodiments of the present disclosure. The simulation settings are shown in Table 1. The uplink and downlink channels are generated at frequencies of 1.95 GHz and 2.14 GHz, where the duplex distance is 190 MHz. The same number of clusters N c is used for the uplink / downlink, and the angles are generated independently with the same distribution. The antenna arrays at both the first device 110 and the second device 120-1 are different for both frequencies.

[0130] Table 1

[0131]

[0132]

[0133] Embodiments of the present disclosure can be applied to the channel estimation problem, where a data processing model is executed at the first device 110 to recover CSI from imperfect CSI feedback, and the imperfect CSI feedback is just noisy CSI.

[0134] Three schemes are evaluated, where "true training" corresponds to the case when downlink CSI is used to train the data processing model for the downlink, "cUL training" is related to embodiments of the present disclosure, and "UL training" refers to the case of using uplink CSI to train the DD for the downlink without compensation.

[0135] For simplicity, consider M T = 8 and M r = 2. The normalized mean square error (NMSE) performance is as Figure 9A shown. It can be observed that it is feasible to apply uplink CSI to train the data processing model for downlink processing, but compensation should be made to improve the accuracy. Similar results are as Figure 9B shown, where the cumulative distribution function (CDF) of the throughput performance is plotted. The throughput performance under perfect channel conditions (referred to as "perfect") is also included.

[0136] Embodiments of the present disclosure can be applied to the channel recovery problem. For simplicity, it considers M T = 32 and M r = 4. The compression value of the compressed CSI is 16 (from M T ·M r = 128). The first device 110 should recover CSI from the compressed CSI feedback. The simulation results are shown in Figure 9C and Figure 9D , Figure 9C the NMSE performance is shown inFigure 9D The throughput performance is shown.

[0137] In general, the various embodiments of the present disclosure may be implemented using hardware or special-purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented using hardware, while other aspects may be implemented using firmware or software that may be executed by a controller, microprocessor, or other computing device. Although the various aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, the blocks, devices, systems, techniques, or methods described herein may be implemented using hardware, software, firmware, special-purpose circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0138] 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 includes computer-executable instructions, such as the instructions included in a program module, that are executed in a device on a target physical or virtual processor to perform any of the methods described above with reference to Figures 3 to 8 description. In general, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules may be combined or split as needed among the program modules. The machine-executable instructions of the program modules may be executed within a local or distributed device. In a distributed device, the program modules may be located in both local and remote storage media.

[0139] The program code for performing the methods of the present disclosure may be written in any combination of one or more programming languages. This 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 be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0140] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier such that the device, apparatus, or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0141] A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A 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 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.

[0142] Moreover, although the operations are described in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in sequential order, or that all of the illustrated operations be performed to obtain the desired result. In some cases, multitasking and parallel processing may be advantageous. Also, although several specific implementation details are included in the above discussion, 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. 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 separately or in any suitable sub-combination in multiple embodiments.

[0143] Although the present 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 above specific features and acts are disclosed as example forms of implementing the claims.

Claims

1. A first device for communication, comprising: At least one processor; And At least one memory storing instructions; When the instructions are executed by the at least one processor, the first device is caused to: Receive a reference signal from a second device on an uplink channel; Determine first channel information about the uplink channel based at least in part on the received reference signal, wherein the first device is caused to determine the first channel information by: determining an original reference signal transmitted by the second device, and determining the first channel information based on the original reference signal and the received reference signal; Extract second channel information about the uplink channel from the first channel information, the second channel information being generated based on the first channel information, wherein the first device is caused to extract the second channel information by: compressing the first channel information to obtain the second channel information; And Train a data processing model based on the first channel information and the second channel information, the data processing model to be used to recover channel information about a downlink channel between the first device and the second device, wherein the first device is caused to train the data processing model by: iteratively performing the following operations: using the data processing model to recover the second channel information, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until the difference between the recovered second channel information and the first channel information is less than a threshold.

2. The first device according to claim 1, wherein the first device is further caused to: Determine a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; and Compensate the phase of the received reference signal based on the compensation parameter.

3. The first device according to claim 1 or 2, wherein the first device is further caused to: Transmit an additional reference signal to the second device on the downlink channel; Receive feedback on the additional reference signal from the second device, the feedback including extracted channel information about the downlink channel; and Use the data processing model to recover the channel information about the downlink channel from the feedback.

4. The first device according to claim 1 or 2, wherein the first device is caused to receive the reference signal by: Monitoring the uplink channel for receiving the reference signal during a predetermined time period.

5. The first device according to claim 1 or 2, wherein the first device comprises a network device and the second device comprises a terminal device.

6. A second device for communication, comprising: At least one processor; And At least one memory storing instructions; When the instructions are executed by the at least one processor, the second device is caused to: Transmitting a reference signal on an uplink channel, the reference signal being used to determine first channel information and second channel information regarding the uplink channel, the first channel information being determined based on an original reference signal transmitted by the second device, and the second channel information being extracted by compressing the first channel information, and the first channel information and the second channel information being used to determine a data processing model, the data processing model being to be used to recover channel information regarding a downlink channel between the first device and the second device, and wherein the data processing model is trained by iteratively performing the following operations: recovering the second channel information using the data processing model, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until the difference between the recovered second channel information and the first channel information is less than a threshold.

7. The second device according to claim 6, wherein the second device is caused to transmit the reference signal by: Determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; and Compensating a phase of the reference signal based on the compensation parameter.

8. The second device according to claim 6, wherein the second device is further caused to: Receive an additional reference signal from the first device on the downlink channel; Determine the channel information regarding the downlink channel based on the additional reference signal; Generate a feedback on the additional reference signal, the feedback including the extracted channel information regarding the downlink channel; And Transmit the feedback to the first device.

9. The second device according to any one of claims 6 to 8, wherein the first device includes a network device and the second device includes a terminal device.

10. A method for communication, comprising: At a first device, receiving a reference signal from a second device on an uplink channel; Determining first channel information regarding the uplink channel based at least in part on the received reference signal, wherein determining the first channel information includes: determining an original reference signal transmitted by the second device, and determining the first channel information based on the original reference signal and the received reference signal; Extracting second channel information regarding the uplink channel from the first channel information, the second channel information being generated based on the first channel information, wherein extracting the second channel information includes: compressing the first channel information to obtain the second channel information; and Training a data processing model based on the first channel information and the second channel information, where the data processing model is to be used to recover channel information about a downlink channel between the first device and the second device, and where training the data processing model includes iteratively performing the following operations: recovering the second channel information using the data processing model, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until the difference between the recovered second channel information and the first channel information is less than a threshold.

11. The method according to claim 10, further comprising: Determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; And Compensating a phase of the received reference signal based on the compensation parameter.

12. The method according to claim 10 or 11, further comprising: Transmitting an additional reference signal on the downlink channel to the second device; Receiving feedback on the additional reference signal from the second device, the feedback including extracted channel information about the downlink channel; And Using the data processing model to recover the channel information about the downlink channel from the feedback.

13. The method according to claim 10 or 11, wherein receiving the reference signal includes: Monitoring the uplink channel for receiving the reference signal during a predetermined time period.

14. The method according to claim 10 or 11, wherein the first device includes a network device and the second device includes a terminal device.

15. A method for communication, comprising: At a second device, transmitting a reference signal on an uplink channel to a first device, the reference signal being for determining first channel information about the uplink channel, and second channel information, the first channel information being determined based on an original reference signal transmitted by the second device, and the second channel information being extracted by compressing the first channel information, and the first channel information and the second channel information being used to determine a data processing model, the data processing model being to be used to recover channel information about a downlink channel between the first device and the second device, and where the data processing model is trained by iteratively performing the following operations: recovering the second channel information using the data processing model, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until the difference between the recovered second channel information and the first channel information is less than a threshold.

16. The method according to claim 15, wherein transmitting the reference signal includes: Determining a compensation parameter based on a first frequency of the uplink channel and a second frequency of the downlink channel; And Compensating a phase of the reference signal based on the compensation parameter.

17. The method according to claim 15, further comprising: Receive an additional reference signal from the first device on the downlink channel; Determine the channel information regarding the downlink channel based on the additional reference signal; Generate feedback on the additional reference signal, the feedback including the extracted channel information regarding the downlink channel; And Transmit the feedback to the first device.

18. The method according to any one of claims 15 to 17, wherein the first device comprises a network device and the second device comprises a terminal device.

19. A device for communication, comprising: Means for receiving a reference signal from a second device on an uplink channel at a first device; Means for determining first channel information regarding the uplink channel based at least in part on the received reference signal, wherein the first device is caused to determine the first channel information by: determining an original reference signal transmitted by the second device, and determining the first channel information based on the original reference signal and the received reference signal; Means for extracting second channel information regarding the uplink channel from the first channel information, the second channel information being generated based on the first channel information, wherein the first device is caused to extract the second channel information by: compressing the first channel information to obtain the second channel information; And Means for training a data processing model based on the first channel information and the second channel information, the data processing model to be used for recovering channel information regarding a downlink channel between the first device and the second device, wherein the first device is caused to train the data processing model by: iteratively performing the following operations: using the data processing model to recover the second channel information, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until a difference between the recovered second channel information and the first channel information is less than a threshold.

20. A device for communication, comprising: A component for transmitting a reference signal on an uplink channel from a second device to a first device, the reference signal being used to determine first channel information and second channel information regarding the uplink channel, the first channel information being determined based on an original reference signal transmitted by the second device, and the second channel information being extracted by compressing the first channel information, and the first channel information and the second channel information being used to determine a data processing model, the data processing model being to be used to recover channel information regarding a downlink channel between the first device and the second device, and wherein the data processing model is trained by iteratively performing the following operations: recovering the second channel information using the data processing model, comparing the recovered second channel information with the first channel information, and updating the data processing model based on the comparison until a difference between the recovered second channel information and the first channel information is less than a threshold.

Images