Communication method, apparatus, device, and storage medium

Abstract

The present disclosure provides a communication method, device, equipment and storage medium, relates to the field of communication, compresses local channel information based on channel information compression network, obtains compressed local compressed channel information, receives second compression information sent by a second base station, inputs the local compressed channel information and the second compression channel information into a precoding matrix calculation network to obtain target precoding, avoids the problems of large signaling overhead and large resource waste caused by transmission of original channel information, and improves the efficiency of communication.

Description

Technical Field

[0001] This disclosure relates to the field of communications, and more particularly to a communication method, apparatus, device, and storage medium. Background Technology

[0002] To enhance network capacity, multi-station cooperative management techniques are employed. Specifically, each base station first collects its local channel information and reports it to the corresponding central node. The central node then calculates the precoding matrix for each station. However, this method incurs significant signaling overhead, resulting in substantial resource waste. Summary of the Invention

[0003] This disclosure provides a communication method, apparatus, device, and storage medium that at least to some extent overcomes the problem of significant resource waste in current multi-station collaborative management.

[0004] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0005] According to one aspect of this disclosure, a communication method is provided, comprising: Local channel information is compressed using a channel information compression network to obtain compressed local channel information. Receive the second compressed channel information sent by the second base station; The local compressed channel information and the second compressed channel information are input into the precoding matrix calculation network to obtain the target precoding.

[0006] In one embodiment of this disclosure, after receiving the second compressed channel information sent by the second base station, the method further includes: The local compressed channel information and the second compressed channel information are input into the deep reinforcement learning network to obtain the target power data.

[0007] In one embodiment of this disclosure, the deep learning reinforcement learning network includes: an Actor network for determining target power data and a Critic network for updating the policy gradient of the Actor network.

[0008] In one embodiment of this disclosure, the method further includes: Signals are transmitted based on target precoding and target power data.

[0009] In one embodiment of this disclosure, before compressing the local channel information based on the channel information compression network to obtain the compressed local channel information, the method further includes: Training data is determined based on global channel information and a weighted least mean square error algorithm. The channel information compression network and the precoding matrix calculation network are trained based on the training data. When the loss function meets the preset threshold, the trained channel information compression network and the precoding matrix calculation network are obtained. The loss function is:

[0010] in, The result of the loss function, The number of samples used in each training session. Number of base stations For the first One base station, For the first One training result, For data labels, This represents the training results.

[0011] In one embodiment of this disclosure, training data is determined based on global channel information and a weighted least mean square error algorithm, including: Initial training data is obtained by randomly initializing the training data based on the maximum transmit power constraint of the base station. The training data is determined based on the initial training data, global channel information, and a preset formula.

[0012] In one embodiment of this disclosure, training data is determined based on initial training data, global channel information, and a preset formula, including: The initial training data is iterated based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold. Then, the initial training data obtained from the last iteration is determined as the transitional training data. The preset formula is:

[0013] in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; Training data is determined based on transitional training data and a second preset formula;

[0014] in, For training data, For transitional training data.

[0015] According to another aspect of this disclosure, a communication device is provided, comprising: The compression module is used to compress local channel information based on the channel information compression network to obtain compressed local channel information. The receiving module is used to receive the second compressed channel information sent by the second base station; The first input module is used to input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0016] In one embodiment of this disclosure, the communication device further includes: The second input module, after receiving the second compressed channel information sent by the second base station, is used to input the local compressed channel information and the second compressed channel information into the deep reinforcement learning network to obtain the target power data.

[0017] In one embodiment of this disclosure, the deep learning reinforcement learning network includes: an Actor network for determining target power data and a Critic network for updating the policy gradient of the Actor network.

[0018] In one embodiment of this disclosure, the apparatus further includes: The third transmission module is used to transmit signals based on target precoding and target power data.

[0019] In one embodiment of this disclosure, the apparatus further includes: The first determining module is used to determine training data based on global channel information and the weighted least mean square error algorithm before compressing local channel information based on the channel information compression network to obtain compressed local channel information. The second determining module is used to train the channel information compression network and the precoding matrix calculation network based on the training data, and to obtain the trained channel information compression network and the precoding matrix calculation network when the loss function meets the preset threshold. The loss function is:

[0020] in, The result of the loss function, The number of samples used in each training session. Number of base stations For the first One base station, For the first One training result, For data labels, This represents the training results.

[0021] The first determining module includes: The first determining unit is used to randomly initialize training data based on the maximum transmit power constraint of the base station to obtain initial training data; The second determining unit is used to determine the training data based on the initial training data, global channel information, and a preset formula.

[0022] The second determining unit includes: The first determining subunit is used to iterate the initial training data based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold, and then determines the initial training data obtained from the last iteration as the transition training data. The preset formula is:

[0023] in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; The second determining subunit is used to determine training data based on transitional training data and a second preset formula.

[0024] in, For training data, For transitional training data.

[0025] According to another aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the above-described communication method by executing the executable instructions.

[0026] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the above-described communication method.

[0027] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0030] Figure 1 This diagram illustrates a communication method flow chart according to an embodiment of the present disclosure. Figure 2 This diagram illustrates another communication method flow according to an embodiment of the present disclosure. Figure 3 This illustration shows a flowchart of another communication method in an embodiment of the present disclosure; Figure 4 This illustration shows a flowchart of yet another communication method in an embodiment of the present disclosure; Figure 5 This illustration shows a flowchart of yet another communication method in an embodiment of the present disclosure; Figure 6 This illustration shows a flowchart of yet another communication method in an embodiment of the present disclosure; Figure 7 A schematic diagram of a communication device according to an embodiment of this disclosure is shown; and Figure 8 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0031] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0032] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0033] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0034] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0035] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0036] To address the aforementioned problems, embodiments of this disclosure provide a communication method, apparatus, device, and storage medium.

[0037] For ease of understanding, the communication method is first described in this disclosure.

[0038] Figure 1 A schematic diagram of a communication method according to an embodiment of this disclosure is shown.

[0039] like Figure 1 As shown, the communication method may include: S110, compress local channel information based on the channel information compression network to obtain compressed local channel information.

[0040] It should be noted that the passage method in this embodiment is applied to the first base station, wherein the first base station can be any base station that is different from the second base station.

[0041] In some embodiments, in a scenario comprising B base stations, each serving K users, the local channel information can be:

[0042] in , Indicates base station Arrive at the community The Middle Channels for individual users and These represent the operations of extracting the real part and the imaginary part, respectively. This represents the matrix vectorization operation. This represents the vector 2-norm operator. Since neural networks involve only real number operations, we here split the channel information into two parts: the real part and the imaginary part.

[0043] In some embodiments, with 5 base stations, each serving 3 users, the channel information compression network consists of 3 convolutional layers and 4 fully connected layers. The number of filters in the 3 convolutional layers are 64, 64, and 8, respectively, and the kernel sizes are 3×1, 3×1, and 3×3, respectively. tanh is used as the activation function after the output of each convolutional layer to increase nonlinearity and improve the model's fitting ability. The flattened output of the last convolutional layer is used as the input to the fully connected layers. The input dimensions of the 4 fully connected layers are 8, 4, 2, and 1, respectively.

[0044] In some embodiments, the compressed local compressed channel information can be .

[0045] S120, receive the second compressed channel information sent by the second base station.

[0046] In some embodiments, before receiving the second compressed information sent by the second base station, the second base station may compress the local channel information corresponding to the second base station based on the channel information compression network. The method by which the second base station compresses the local channel information based on the information compression network is the same as the method by which the first base station compresses the local channel information based on the information compression network, and will not be described again here.

[0047] S130: Input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0048] In some embodiments, the local compressed channel information and the second compressed channel information can be: It adopts a 5-layer fully connected network, the first The output dimension of each fully connected layer is ,in , , , , , Let be the number of base station antennas, and tanh be the activation function. The output of the precoding matrix network is the normalized precoding vector. .

[0049] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0050] Figure 2 A schematic diagram of another communication method in an embodiment of this disclosure is shown.

[0051] like Figure 2 As shown, the communication method may include: S210, compress local channel information based on the channel information compression network to obtain compressed local channel information; S220, Receive the second compressed channel information sent by the second base station; S230: Input the local compressed channel information and the second compressed channel information into the deep reinforcement learning network to obtain the target power data.

[0052] In some embodiments, the deep learning reinforcement learning network includes: an Actor network for determining target power data and a Critic network for updating the policy gradient of the Actor network.

[0053] In some embodiments, the base station The input to the actor network is the same as the input to its normalized precoding network, which is... The output dimension of linear layer 1 is 64, and the output dimension of linear layer 2 is... The hidden layer contains two fully connected layers with an output dimension of [32, 16]. The actor network output is the power vector allocated by the base station to each user. The base station's critic network input consists of the base station's state and action information, namely the compressed channel information of each station and the power allocation scheme output by the actor network. The output dimension of linear layer 1 is 64. The hidden layer contains two fully connected layers with an output dimension of [32, 16]. The output dimension of linear output layer 2 is 1, namely the state-action Q-value, which is used to evaluate the quality of the base station's power allocation scheme and train the base station actor network.

[0054] In some embodiments, the deep reinforcement learning network training process is as follows: the base station interacts with the wireless environment through trial and error, that is, after obtaining global compressed channel information, it calculates a power allocation scheme through the actor network. After each interaction, the state, actions, and user rate information are recorded and stored in the experience replay pool. During each training session, the base station randomly samples from the experience replay pool. A set of records is used for training. The Target-Actor network and Target-Critic network have the same structure as the Actor network and Critic network, respectively. The Target-Actor network obtains the target policy based on the sampled data. The Target-Critic network estimates the target Q-value based on the sampled data and the target policy obtained by the Target-Actor network. The Critic network calculates the Q-value based on the sampled data (the policy and state of the Actor network) in the empirical replay pool and updates the policy gradient of the Actor network. The Critic network is optimized based on the estimated target Q-value and the policy and state of the Actor network.

[0055] Figure 3 A schematic diagram of another communication method in an embodiment of this disclosure is shown.

[0056] like Figure 3 As shown, the communication method may include: S310, compress local channel information based on the channel information compression network to obtain compressed local channel information; S320, receiving the second compressed channel information sent by the second base station; S330: Input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0057] S340 inputs the local compressed channel information and the second compressed channel information into the deep reinforcement learning network to obtain the target power data.

[0058] S350 transmits signals based on target precoding and target power data.

[0059] In some embodiments, after determining the target precoding and target power data, the signal can be determined using the target precoding and target power data, and the signal transmitted based on this can reduce interference between base stations.

[0060] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0061] Figure 4 A schematic diagram of yet another communication method in an embodiment of this disclosure is shown.

[0062] like Figure 4As shown, the communication method may include: S410 determines training data based on global channel information and a weighted minimum mean square error algorithm.

[0063] S420: The channel information compression network and the precoding matrix calculation network are trained based on the training data. When the loss function meets the preset threshold, the trained channel information compression network and the precoding matrix calculation network are obtained.

[0064] In some embodiments, the loss function is:

[0065] in, The result of the loss function, The number of samples used in each training session. Number of base stations For the first One base station, For the first One training result, For data labels, This represents the training results.

[0066] S430, compresses local channel information based on the channel information compression network to obtain compressed local channel information; S440, Receive the second compressed channel information sent by the second base station; S450: Input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0067] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0068] Figure 5 A schematic diagram of yet another communication method in an embodiment of this disclosure is shown.

[0069] like Figure 5 As shown, the communication method may include: S510: Randomly initialize training data based on the maximum transmit power constraint of the base station to obtain initial training data; S520 determines training data based on initial training data, global channel information, and preset formulas.

[0070] S530 trains the channel information compression network and the precoding matrix calculation network based on the training data. When the loss function meets the preset threshold, the trained channel information compression network and the precoding matrix calculation network are obtained.

[0071] S540 compresses local channel information based on a channel information compression network to obtain compressed local channel information. S550 receives the second compressed channel information sent by the second base station; S560 inputs the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0072] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0073] Figure 6 A schematic diagram of yet another communication method in an embodiment of this disclosure is shown.

[0074] like Figure 6 As shown, the communication method may include: S610, based on the maximum transmit power constraint of the base station, randomly initializes the training data to obtain the initial training data.

[0075] In some embodiments, since the base station has a maximum transmit power constraint, the training data needs to be initialized first when determining the training data.

[0076] S620: Iterate the initial training data based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold, and then determine the initial training data obtained from the last iteration as the transitional training data.

[0077] In some embodiments, the preset formula is:

[0078] in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; Training data is determined based on transitional training data and a second preset formula;

[0079] in, For training data, For transitional training data.

[0080] In some embodiments, the difference between the initial training data obtained from multiple iterations satisfying a preset threshold may include multiple iterations of the initial training data until the initial training data converges.

[0081] S630 trains the channel information compression network and the precoding matrix calculation network based on the training data. When the loss function meets the preset threshold, the trained channel information compression network and the precoding matrix calculation network are obtained.

[0082] S640, compresses local channel information based on the channel information compression network to obtain compressed local channel information; S650 receives the second compressed channel information sent by the second base station; S660 inputs the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0083] The communication method provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain the target precoding. This avoids the problems of large signaling overhead and resource waste caused by transmitting the original channel information, thus improving communication efficiency.

[0084] Based on the same inventive concept, this disclosure also provides a communication device, as shown in the following embodiment. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiment, the implementation of this device embodiment can refer to the implementation of the above-described method embodiment, and repeated details will not be described again.

[0085] Figure 7 A schematic diagram of a communication device according to an embodiment of the present disclosure is shown.

[0086] like Figure 7 As shown, the communication device 700 may include: Compression module 710 is used to compress local channel information based on channel information compression network to obtain compressed local channel information; The receiving module 720 is used to receive the second compressed channel information sent by the second base station; The first input module 730 is used to input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding.

[0087] The communication apparatus provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain target precoding. This avoids the problems of high signaling overhead and resource waste caused by transmitting the original channel information, thereby improving communication efficiency.

[0088] In some embodiments, the communication device further includes: The second input module, after receiving the second compressed channel information sent by the second base station, is used to input the local compressed channel information and the second compressed channel information into the deep reinforcement learning network to obtain the target power data.

[0089] The communication apparatus provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain target precoding. This avoids the problems of high signaling overhead and resource waste caused by transmitting the original channel information, thereby improving communication efficiency.

[0090] In some embodiments, the deep learning reinforcement learning network includes: an Actor network for determining target power data and a Critic network for updating the policy gradient of the Actor network.

[0091] The communication apparatus provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain target precoding. This avoids the problems of high signaling overhead and resource waste caused by transmitting the original channel information, thereby improving communication efficiency.

[0092] In some embodiments, the apparatus further includes: The third transmission module is used to transmit signals based on target precoding and target power data.

[0093] The communication apparatus provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain target precoding. This avoids the problems of high signaling overhead and resource waste caused by transmitting the original channel information, thereby improving communication efficiency.

[0094] In some embodiments, the apparatus further includes: The first determining module is used to determine training data based on global channel information and the weighted least mean square error algorithm before compressing local channel information based on the channel information compression network to obtain compressed local channel information. The second determining module is used to train the channel information compression network and the precoding matrix calculation network based on the training data, and to obtain the trained channel information compression network and the precoding matrix calculation network when the loss function meets the preset threshold. The loss function is:

[0095] in, The result of the loss function, The number of samples used in each training session. Number of base stations For the first One base station, For the first One training result, For data labels, This represents the training results.

[0096] The first determining module includes: The first determining unit is used to randomly initialize training data based on the maximum transmit power constraint of the base station to obtain initial training data; The second determining unit is used to determine the training data based on the initial training data, global channel information, and a preset formula.

[0097] The second determining unit includes: The first determining subunit is used to iterate the initial training data based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold, and then determines the initial training data obtained from the last iteration as the transition training data. The preset formula is:

[0098] in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; The second determining subunit is used to determine training data based on transitional training data and a second preset formula.

[0099] in, For training data, For transitional training data.

[0100] The communication apparatus provided in the embodiments of this disclosure compresses local channel information based on a channel information compression network to obtain compressed local channel information. It then receives second compressed information sent by a second base station and inputs the local compressed channel information and the second compressed channel information into a precoding matrix calculation network to obtain target precoding. This avoids the problems of high signaling overhead and resource waste caused by transmitting the original channel information, thereby improving communication efficiency.

[0101] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0102] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0103] like Figure 8 As shown, the electronic device 800 is manifested in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including storage unit 820 and processing unit 810).

[0104] The storage unit stores program code, which can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 810 can perform the following steps of the above method embodiments: Local channel information is compressed using a channel information compression network to obtain compressed local channel information. Receive the second compressed channel information sent by the second base station; The local compressed channel information and the second compressed channel information are input into the precoding matrix calculation network to obtain the target precoding.

[0105] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0106] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0107] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0108] Electronic device 800 can also communicate with one or more external devices 840 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0109] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0110] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the methods described above is stored thereon. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0111] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0113] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0114] In practice, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0115] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0116] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0117] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0118] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A communication method, characterized in that, Applied to the first base station, including: Local channel information is compressed using a channel information compression network to obtain compressed local channel information. Receive the second compressed channel information sent by the second base station; The local compressed channel information and the second compressed channel information are input into the precoding matrix calculation network to obtain the target precoding; Training data is determined based on global channel information and a weighted least mean square error algorithm. The channel information compression network and the precoding matrix calculation network are trained based on the training data. When the loss function meets the preset threshold, the trained channel information compression network and the precoding matrix calculation network are obtained. The global channel information and the weighted least mean square error algorithm determine the training data, including: Initial training data is obtained by randomly initializing the training data based on the maximum transmit power constraint of the base station. The training data is determined based on the initial training data, global channel information, and a preset formula. The process of determining training data based on initial training data, global channel information, and a preset formula includes: The initial training data is iterated based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold. Then, the initial training data obtained from the last iteration is determined as the transitional training data. The default formula is: in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; Training data is determined based on transitional training data and a second preset formula; in, For training data, For transitional training data.

2. The communication method according to claim 1, characterized in that, After receiving the second compressed channel information sent by the second base station, the method further includes: The local compressed channel information and the second compressed channel information are input into a deep reinforcement learning network to obtain target power data.

3. The communication method according to claim 2, characterized in that, The deep learning reinforcement learning network includes: an Actor network for determining target power data and a Critic network for updating the policy gradient of the Actor network.

4. The communication method according to claim 2, characterized in that, The method further includes: Signals are transmitted based on target precoding and target power data.

5. The communication method according to claim 1, characterized in that, The loss function is: in, The result of the loss function, The number of samples used in each training session. Number of base stations For the first One base station, For the first One training result, For data labels, This represents the training results.

6. A communication device, characterized in that, Applied to the first base station, including: The compression module is used to compress local channel information based on the channel information compression network to obtain compressed local channel information. The receiving module is used to receive the second compressed channel information sent by the second base station; The first input module is used to input the local compressed channel information and the second compressed channel information into the precoding matrix calculation network to obtain the target precoding; The first determining module is used to determine training data based on global channel information and the weighted least mean square error algorithm. The second determining module is used to train the channel information compression network and the precoding matrix calculation network based on the training data, and to obtain the trained channel information compression network and the precoding matrix calculation network when the loss function meets the preset threshold. The global channel information and the weighted least mean square error algorithm determine the training data, including: Initial training data is obtained by randomly initializing the training data based on the maximum transmit power constraint of the base station. The training data is determined based on the initial training data, global channel information, and a preset formula. The process of determining training data based on initial training data, global channel information, and a preset formula includes: The initial training data is iterated based on a preset formula until the difference between the initial training data obtained from multiple iterations meets a preset threshold. Then, the initial training data obtained from the last iteration is determined as the transitional training data. The default formula is: in, For the first One base station, For base stations to base station The Middle Channel information for each user For base stations To the Precoded data for each user It is the identity matrix. As an auxiliary variable; Training data is determined based on transitional training data and a second preset formula; in, For training data, For transitional training data.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the communication method according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the communication method according to any one of claims 1 to 5.

Images