Signal transmission method and device, equipment, server and storage medium

Abstract

The invention discloses a signal transmission method and device, equipment, a server and a storage medium, and relates to the technical field of wireless communication, the signal transmission method and device are applied to a neural network in a wireless communication system, the neural network comprises a preset beam forming structure obtained through deep learning, and the neural network is used for determining a beam forming matrix according to received uplink channel information; the method comprises: receiving request information from an electronic device, the request information being transmitted through an uplink channel; determining downlink channel state information, reflection phase shift and transmitting power based on the uplink channel; in response to the request information, generating feedback information based on a preset beam forming structure, downlink channel state information and reflection phase shift; and sending the feedback information to the electronic equipment according to the transmitting power. And the transmission rate of wireless signals can be effectively improved while the complexity of a beam forming algorithm is reduced.

Description

Technical Field

[0001] Embodiments of the present application relate to wireless communication technology, and in particular, to a signal transmission method, apparatus, device, server, and storage medium. Background Art

[0002] Reconfigurable Intelligent Surface (RIS) is a wireless communication technology. Specifically, RIS can improve the propagation of signals in wireless communications by intelligently controlling the reflection, refraction and scattering characteristics of electromagnetic waves. Among them, RIS can usually be composed of a large number of programmable reflection units, each of which can be set individually, so that the propagation channel can be reconfigured by adjusting the phase and amplitude of each transmitting unit in wireless communication. For example, a group of passive electrical components in RIS is set to adjust the reflection of the incident signal, thereby improving the rate, spectrum efficiency, coverage and other performance of the communication system. It is worth mentioning that the passive radio components used in RIS have low power consumption and have the ability to improve the performance of the communication system.

[0003] Generally speaking, during the transmission of wireless signals, when the base station (BS) combines RIS to generate the transmission signal, i.e. beamforming, there will be a problem of reflection phase shift and BD jointly optimizing RIS phase shift. In order to solve this technical problem, the traditional technology adopts the alternate optimization of reflection phase shift and RIS phase shift, or the Block Coordinate Descent (BCD) method, or the Semidefinite Relaxation (SDR) method. However, the high complexity of the algorithms in these solutions slows down the convergence speed of the wireless communication system, which in turn limits the application of wireless signal transmission in 5G or 6G systems, especially limiting the application of this technology in services with higher transmission rate and efficiency requirements. Summary of the invention

[0004] The present application provides a signal transmission method, which can effectively improve the transmission rate of wireless signals while reducing the complexity of generating a beamforming algorithm.

[0005] In order to achieve the above technical objectives, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, the present application provides a signal transmission method, which can be applied to a wireless communication system, wherein the wireless communication system includes a neural network, and the neural network includes a preset beamforming structure obtained by deep learning, and the neural network is used to determine a beamforming matrix based on received uplink channel information, so as to generate a transmission signal according to the beamforming matrix. Specifically, the signal transmission method is: receiving request information from an electronic device, wherein the request information is transmitted via an uplink channel. Determine downlink channel state information, reflection phase shift, and transmit power based on the uplink channel information. Furthermore, in response to the request information, feedback information can be generated based on the preset beamforming structure, downlink channel state information, and reflection phase shift, and the feedback information can be sent to the electronic device according to the transmit power.

[0007] It can be understood that in the transmission process of wireless signals, wireless channel state information (CSI) is the key information for beamforming in multi-user multi-antenna systems. Neural networks are learned in a data-driven manner and trained with a large amount of sample data to obtain a neural network that meets the requirements of data transmission. A beamforming structure is preset in the neural network, and the downlink channel state information can be predicted based on the uplink channel information. In other words, the wireless system provided in the embodiment of the present application is a driving method that combines data drive and model drive. This method can meet the transmission power when the base station transmits a beam signal on the one hand, and can ensure that the transmitted signal meets the phase constraint of RIS.

[0008] In combination with the first aspect, in a possible implementation, the neural network includes data-driven and model-driven. The data-driven is used to receive request information for uplink channel transmission, and determine downlink channel state information, reflection phase shift and transmission power according to the channel state information of the uplink channel; the model-driven includes a preset beamforming structure.

[0009] Generally speaking, the use of a dual-driven neural system for beamforming in wireless communications can effectively solve the problems of beamforming and reflection phase shift in a multi-user multiple-input single-output (MISO) system, and jointly optimize it, while reducing the complexity of generating the beamforming algorithm, it can effectively increase the transmission rate of the wireless signal.

[0010] In combination with the first aspect, in another possible implementation, the neural network includes a first channel state network, a second channel state network, a phase network and a power network; the first channel state network outputs predicted downlink direct channel state information based on the uplink channel; the second channel state network outputs predicted downlink cascade channel state information based on the uplink channel; the phase network outputs reconfigurable intelligent surface RIS phase shift and base station reflection phase shift based on the uplink channel; the power network outputs transmission power based on the power information of the uplink channel.

[0011] In combination with the first aspect, in another possible implementation, a wireless communication system includes a base station, a reconfigurable smart surface RIS and the electronic device.

[0012] The method further includes: the base station receives the request information from the electronic device, wherein the request information is transmitted by the uplink channel. The base station determines the downlink channel state information, the reflection phase shift and the transmission power according to the uplink channel; the base station generates response information based on the request information, the downlink channel state information and the base station reflection phase shift; the base station sends the reflection control information and feedback information to the RIS according to the transmission power; the RIS adjusts the reflection element in response to the reflection control information and sends feedback information to the electronic device.

[0013] In combination with the first aspect, in another possible implementation, the method may further include: the base station determines the equivalent downlink channel information based on the request information, the downlink channel state information and the base station reflection phase shift; and restores the beamforming matrix according to the equivalent downlink channel information and the transmit power.

[0014] Among them, restoring the beamforming matrix can help the base station restore the beamforming. This recovery method is directly calculated and can effectively improve the generation efficiency of the beamforming.

[0015] In a second aspect, an embodiment of the present application also provides a signal transmission device, including a receiving module, a determining module, a generating module and a sending module.

[0016] The receiving module is used to receive request information from an electronic device, wherein the request information is transmitted through an uplink channel. The determining module is used to determine channel state information, reflection phase shift and transmission power based on the uplink channel. The generating module is used to generate feedback information based on a preset beamforming structure, downlink channel state information and reflection phase shift in response to the request information. The sending module is used to send the feedback information to the electronic device according to the transmission power.

[0017] In combination with the second aspect, in a possible implementation manner, the device further includes a beamforming recovery module.

[0018] The beamforming recovery module is used to determine equivalent downlink channel information based on request information, downlink channel state information and base station reflection phase shift; and recover the beamforming matrix according to the equivalent downlink channel information and transmit power.

[0019] In a third aspect, an embodiment of the present application further provides a signal transmission device, comprising: a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method in the first aspect and any possible implementation manner.

[0020] In a fourth aspect, an embodiment of the present application further provides a server, comprising: a processor; and a memory for storing instructions executable by the processor.

[0021] The processor is configured to execute the instructions to implement the method in the above-mentioned first aspect and any possible implementation manner.

[0022] In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed on an electronic device, the method in the above-mentioned first aspect and any possible implementation manner is implemented.

[0023] It can be understood that the beneficial effects that can be achieved by the device in the second aspect and any possible implementation manner provided above, the equipment in the third aspect, the server in the fourth aspect, and the computer-readable storage medium in the fifth aspect can be referred to as the beneficial effects in the first aspect and any possible design manner thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic diagram of the structure of a wireless communication system provided in an embodiment of the present application;

[0025] Figure 2 is a flow chart of a signal transmission method provided by an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of a neural network module structure provided in an embodiment of the present application;

[0027] Figure 4 It is a structural schematic diagram of a wireless signal transmission device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0029] The method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings. Those skilled in the art will appreciate that the structural diagram of the electronic device, base station or RIS shown in the embodiment of the present application is not sufficient to limit the structure of the device. In practical applications, the electronic device, base station or RIS may include more or fewer components or modules, or may combine certain components, or may rearrange the components.

[0030] like Figure 1 As shown in FIG. , data transmission between devices in a wireless communication system is shown. Figure 1 As shown, the wireless communication system includes a base station BS, an IRS and a plurality of electronic devices (such as Figure 1 (U1, U2 and U3).

[0031] During a wireless signal data transmission process, the electronic device sends data request information to the BS, and the BS generates corresponding response information in response to the data request information and sends the response information to the electronic device. During another wireless signal transmission process, the electronic device (such as U1) cannot directly send data request information to the BS. Then U1 sends data request information to the IRS, and the IRS forwards the data request information to the BS base station. The BS base station receives the data request information from the electronic device through the IRS, generates corresponding response information, and sends the response information to the IRS, and the IRS sends the response information to the electronic device.

[0032] Among them, the electronic device sends information to the IRS, the IRS sends information to the base station, and the electronic device sends information to the BS, all through the uplink channel. The base station sends information to the electronic device, the IRS sends information to the electronic device, and the base station sends information to the IRS, all through the downlink channel.

[0033] Specifically, when BS combines RIS to generate a transmit signal, i.e., beamforming, it will produce reflection phase shift and BD jointly optimize RIS phase shift. When using deep learning to solve this technical problem, the beamforming problem in the base station is studied from a data-driven perspective. In one solution, it is proposed that a multi-layer fully connected neural network (Fully Connected Neural Network, FCNN) can be used to learn the phase shift in a single electronic device wireless communication system in order to reduce the complexity of the RIS algorithm. It is worth noting that these neural networks are usually learned in a data-driven manner. This process requires a large number of data samples to train the neural network, which will reduce the convergence speed of the neural system training and reduce the accuracy of the neural network output. Further, in order to solve this shortcoming in the neural network training process, one implementation method is to add a classic model in wireless communication theory to the neural network to reduce the output of the neural network. In other words, a model-driven learning method is used. In this way, the number of training samples can be reduced.

[0034] It is worth noting that when optimizing the beamforming of a wireless communication system, the beamforming of a multi-user (i.e., multi-electronic device) multiple-input single-output (MISO) system is generally used. However, in such a wireless communication system, the optimization of the beamforming of the RIS-assisted MISO system and the phase shift optimization are coupled to each other. In other words, the larger the phase shift error is when the beamforming in the main RIS-assisted MISO system is performed. Therefore, in a wireless communication system, the single use of this model-driven approach cannot meet the various transmission requirements of the wireless communication system.

[0035] In addition, in the transmission of wireless communication systems, there is also a problem that is easily overlooked, that is, the reciprocity between the uplink channel link and the downlink channel link may not exist.

[0036] Reciprocity means that in a communication system, the uplink and downlink transmit information in different time slots under the same frequency resources. Then, within a relatively short period of time (coherence time of channel propagation), it can be considered that the channel fading experienced by the transmission signals of the uplink and downlink is the same.

[0037] Wireless channel state information (CSI) is the key information for beamforming in multi-user multi-antenna systems. According to CSI, key information such as channel quality and environmental conditions in wireless communications can be determined. In some implementations, in a wireless communication system combining BS with RIS, it is assumed that there is good CSI at the BS, so that the BS can estimate the CSI in the downlink based on the CSI in the uplink. Of course, this method is based on the existence of the reciprocity condition of the uplink and downlink. In practice, due to the existence of analog front-end circuits in the radio transmitting unit, the CSI in the uplink and downlink are different, and it is difficult to estimate the CSI of the downlink based on the uplink. In other words, in practical applications, the uplink and downlink channels are non-reciprocal.

[0038] Based on this, an embodiment of the present application provides a signal transmission method, which is applied to a wireless communication system so that the system becomes a data-driven and model-driven wireless system. For example, the system may include a neural network, and a preset beamforming structure obtained by deep learning is set in the neural network. In this way, the wireless communication system can determine the beamforming matrix based on the received uplink channel information. While reducing the complexity of generating the beamforming algorithm, the transmission rate of the wireless signal can be effectively improved.

[0039] like Figure 2 As shown, it is a flow chart of the signal transmission method provided in the embodiment of the present application. Figure 2 As shown, the signal transmission method includes steps 202 to 204.

[0040] Step 201: Receive request information from an electronic device.

[0041] The request information is transmitted through an uplink channel.

[0042] It can be understood that the request information may be information that a user operates the electronic device when using the electronic device, so that the electronic device sends the information to the base station.

[0043] The electronic device sends a request message to the base station via an uplink channel. In some implementations, when the distance between the electronic device and the base station exceeds a preset distance value, or when there is an obstruction in the wireless transmission between the electronic device and the base station, the electronic device can send a request message to the IRS via an uplink channel, and the IRS forwards the received request message to the base station. For example, there is a user k (which can be the electronic device U1 in Figure 1) that sends a request message to the base station.

[0044] Exemplarily, in a MISO system with IRS-assisted downlink, a BS with N antennas serves K single-antenna users. An IRS equipped with an array of N passive reflective elements is deployed to assist transmission between the BS and the users. The BS controls the IRS via an IRS controller that is able to adjust the phase of the array elements in order to reflect the incident signal to the desired direction.

[0045] In some implementations, Figure 1 The wireless communication system shown is taken as an example. represents the downlink channel from the base station to user k, represents the downlink channel from IRS to user K, B d Indicates the downlink channel from the base station to the IRS. represents the uplink channel from user k to the base station, represents the uplink channel from user K to IRS, B u represents the uplink channel from IRS to base station. Then the signal received at user k can be expressed by the following formula 1:

[0046]

[0047] in, represents the concatenated channel between the base station and user k through IRS reflection.

[0048] Furthermore, the downlink channel matrix can be expressed as: Assume w k is the beamforming vector, x k is the information transmitted from BS to user k. is the phase shift vector at the IRS, where w i ∈[-π,π) is the phase shift of the i-th element, is an additive Gaussian white noise with zero mean and zero variance. Then the signal-to-noise ratio (SINR) at user k can be expressed by formula 2 as follows:

[0049]

[0050] in, Indicates the equivalent downlink channel.

[0051] Then the total rate of all electronic devices can be expressed by the following formula 3:

[0052]

[0053] Among them, α k is the weight.

[0054] In the signal transmission method provided in the embodiment of the present application, the optimization problem of beamforming can be expressed as maximizing the sum rate of all users while satisfying the transmission power and continuous phase shift constraints. It can be expressed by the following formula 4:

[0055]

[0056] C2:|v i |=1,i=1,…,M Formula (4)

[0057] Where W = [w1,…,w K ] is the beamforming matrix at the BS. C1 is the transmit power constraint, and P is the maximum transmit power of the BS. C2 is the continuous phase shift constraint at the RIS. When the downlink CSI is known, the above problem can be solved iteratively using a known method. In this case, if this problem can be optimized using deep learning, better optimization results can be obtained. That is, the dual-drive model provided in the embodiment of the present application. In addition, in actual situations, there may be no channel reciprocity between the uplink and downlink. Therefore, assuming that there is only uplink channel information on the BS, channel reciprocity does not hold.

[0058] Exemplarily, assuming that there is a function Ω(·), whose input is the uplink CSI and whose output is the optimal beamforming matrix W and phase shift v that satisfy the constraints of the problem (P), the problem can be expressed as follows:

[0059]

[0060] in, is the uplink channel matrix represents the uplink channel from user k to the base station, represents the uplink channel from user K to IRS, B u Indicates the uplink channel from IRS to base station.

[0061] In general, there is no closed expression for the function Ω(·). Since any continuous-valued function can be approximated with a small approximation error according to the universal approximation theorem, the problem (P) can be transformed into a trainable problem. Assuming that the network Ω(·; μ) has a trainable parameter set μ, the above formula 5 can be approximately expressed by the following formula 6:

[0062]

[0063] It should be noted that the data drive in the embodiment of the present application is a model-based beamforming structure. This data drive can effectively reduce the output dimension of the neural network, reduce the difficulty of training the neural network, thereby improving the training efficiency, and then improve the performance of the data drive, and improve the data transmission efficiency and performance of wireless communications. It is worth noting that this structure can be applied to a multi-antenna MISO system, but cannot be directly applied to a RIS-assisted MISO system. Because the RIS system includes complex direct and cascade channels, as well as phase shift vectors. Therefore, in a possible implementation of the present application, a fixed phase shift vector v can be given in the wireless communication system so that the data drive matches the RIS-assisted MISO system.

[0064] Specifically, from a mathematical point of view, the RIS system can be equivalently regarded as a multi-user MISO system. Therefore, the optimal beamforming structure of the RIS-assisted MISO system can be expressed as follows:

[0065]

[0066] in, is the identity matrix. k and q k All are satisfied Positive parameter. p=[p1,…,p K ] T is the optimal downlink power vector, q=[q1,…,q K ] T is an auxiliary vector that can be used to determine the beamforming direction.

[0067] It should be noted that the power vector [p; q] is considered to be a key feature of the beamforming solution. Therefore, unlike directly learning the high-dimensional beamforming matrix W, the data model used in the embodiment of the present application is capable of learning the low-dimensional power feature [p; q]. Furthermore, the beamforming vector can be recovered from the learned power feature. From a practical point of view, the above approach can reduce the output dimension of the neural network learning beamforming from 2NK to 2K, thereby improving the training efficiency.

[0068] Step 202: Determine downlink channel state information, reflection phase shift and transmit power based on the uplink channel.

[0069] The neural network architecture provided in the embodiment of the present application includes a neural network that learns two parts, phase shift v and power characteristics [p; q], to maximize the sum rate while complying with the transmission power constraint and phase shift constraint. is the input, and the final output is the beamforming matrix W and phase shift v at the RIS.

[0070] For example, the entire neural network architecture consists of four modules, such as Figure 3 As shown in Figure 1, the neural network includes a channel state network (CSI-Net), a phase network (Phase-Net) and a power network (Power-Net). Figure 3 As shown, the channel state network includes a first channel state network (CSI-Net1) and a second channel state network (CSI-Net2).

[0071] Among them, CSI-Net1 and CSI-Net2 are two fully connected neural networks (FCNNs), which are used to learn the uplink and downlink relationship (i.e., unitary transformation relationship) of the direct channel and the cascade channel respectively. CSI-Net1 and CSI-Net2 are used to learn the uplink and downlink relationship (i.e., unitary transformation relationship) of the direct channel and the cascade channel respectively. The input of CSI-Net1 and CSI-Net2 is the uplink The output of CSI-Net1 is the predicted downlink direct connection The output of CSI-Net2 is the predicted downlink cascade

[0072] In some implementations, supervised learning methods can be used to train the two networks, CSI-Net1 and CSI-Net2. Since its input is a complex matrix, it is divided into real and imaginary parts to facilitate the training of the neural network.

[0073] Specifically, suppose there is a channel training data set with T uplink-downlink CSI pairs. The prediction outputs of CSI-Net1 and CSI-Net2 are recorded as and The labels of the corresponding real channels are recorded as and The loss function of CSI-Net1 can be expressed as mean square error (MSE), as shown in the following formula 8:

[0074]

[0075] The loss function of CSI-Net2 can be expressed as follows:

[0076]

[0077] Phase-Net: This module aims to learn and optimize the phase shift v of RIS. Specifically, the neural network uplinks As input, it outputs the phase shift v in a supervised learning manner. Similarly, the complex vector v is divided into real and imaginary parts. The predicted output of Phase-Net is recorded as And its label is vt At the same time, the Phase-Net loss function based on MSE is expressed as follows:

[0078]

[0079] Power-Net: Power-Net aims to understand the power characteristics [p; q] of the beamforming scheme. The predicted output of Power-Net is and where p t and q t are the t-th training samples of the downlink and uplink power vectors obtained by the BCD algorithm in power training. Similar to the previous network, the supervised learning method is used to train this network. At the same time, the loss function of Power-Net is given, as shown in the following formula 11:

[0080]

[0081] Step 203: In response to the request information, feedback information is generated based on a preset beamforming structure, downlink channel state information, and reflection phase shift.

[0082] Specifically, the base station sends information to the downlink channel to recover the optimal beamforming based on the beamforming in the neural network. In some implementations, the estimated direct and cascade channels and the estimated phase shift are used to obtain the equivalent downlink Then the beamforming matrix W is restored using the power characteristics and the equivalent downlink channel information.

[0083] It is worth mentioning that this module does not contain any training parameters and only calculates the beamforming matrix W. In addition, in order to maximize the sum rate, a hybrid training method is used, and the overall loss function is expressed as follows:

[0084] Loss = α H L H +α A L A +α V L V +α P L P +α R L R Formula (12)

[0085] where α i , i∈{H,A,V,P,R} is the weight of each loss component. The learning of channel matrix, phase shift vector and power characteristics is only an intermediate process. The ultimate goal is to maximize the sum rate of the system. Therefore, the sum rate is taken as an additional part of the overall loss function, that is, L R =-Rsum Using a hybrid training approach, the downlink CSI, power characteristics, and phase shift vector are trained in a supervised manner, and the rate is trained in an unsupervised manner.

[0086] Step 204: Send feedback information to the electronic device according to the transmission power.

[0087] The embodiment of the present application also provides a wireless signal transmission device, which includes computer instructions. When the computer instructions are executed on the wireless signal transmission device, the wireless signal transmission device performs the functions or steps in the above method embodiment. For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0088] In the case of an integrated unit, Figure 4 A possible structural diagram of the wireless signal transmission device 400 involved in the above embodiment is shown. The wireless signal transmission device 400 may include: a processing module 401, a storage module 402 and a communication module 403. The processing module 401 is used to control and manage the actions of the server. The storage module 402 is used to save the program code and data of the server, such as the method for creating a chat group. The communication module 403 is used to support the communication between the server and other network entities to realize functions such as data interaction. For example, the communication module 403 supports the communication between the server and the electronic device to realize the data interaction function.

[0089] The processing module 401 may be a processor or a controller. The communication module 403 may be a transceiver, an RF circuit or a communication interface, etc. The storage module 402 may be a memory.

[0090] Some other embodiments of the present application provide a server, which may include: a memory and one or more processors. The touch screen, the memory and the processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the server may execute each function or step executed by the server in the above method embodiment.

[0091] An embodiment of the present application also provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed on the above-mentioned electronic device, the electronic device executes each function or step executed by the mobile phone in the above-mentioned method embodiment.

[0092] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0093] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0094] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0095] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0096] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0097] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A signal transmission method, characterized in that: Applied to a wireless communication system, the wireless communication system comprising a neural network, the neural network comprising a preset beamforming structure obtained by deep learning, the neural network being used to determine a beamforming matrix according to received uplink channel information; The method comprises: Receiving request information from an electronic device, wherein the request information is transmitted via an uplink channel; Determine downlink channel state information, reflection phase shift and transmit power based on the uplink channel; In response to the request information, generating feedback information based on the preset beamforming structure, the downlink channel state information and the reflection phase shift; The feedback information is sent to the electronic device according to the transmission power.

2. The method according to claim 1, characterized in that The neural network includes data-driven and model-driven; The data driver is used to receive the request information transmitted by the uplink channel, and determine the downlink channel state information, the reflection phase shift and the transmission power according to the channel state information of the uplink channel; The model driving includes the preset beamforming structure.

3. The method according to claim 1 or 2, characterized in that: The neural network includes a first channel state network, a second channel state network, a phase network and a power network; The first channel state network outputs predicted downlink direct channel state information according to the uplink channel; The second channel state network outputs predicted downlink cascade channel state information according to the uplink channel; The phase network outputs a reconfigurable smart surface RIS phase shift and a base station reflection phase shift according to the uplink channel; The power network outputs the transmit power according to the power information of the uplink channel.

4. The method according to any one of claims 1 to 3, characterized in that: The wireless communication system comprises a base station, a reconfigurable intelligent surface RIS and the electronic device; the method further comprises: The base station receives the request information from the electronic device, wherein the request information is transmitted by the uplink channel; The base station determines downlink channel state information, reflection phase shift and transmission power according to the uplink channel; The base station generates response information based on the request information, the downlink channel state information and the base station reflection phase shift; The base station sends the reflection control information and the feedback information to the RIS according to the transmission power; The RIS adjusts a reflective element in response to the reflection control information and sends the feedback information to the electronic device.

5. The method according to claim 4, characterized in that The method further comprises: The base station determines equivalent downlink channel information based on the request information, the downlink channel state information and the base station reflection phase shift; A beamforming matrix is ​​restored according to the equivalent downlink channel information and the transmit power.

6. A signal transmission device, characterized in that: It includes a receiving module, a determining module, a generating module and a sending module; The receiving module is used to receive request information from an electronic device, wherein the request information is transmitted via an uplink channel; The determination module is used to determine downlink channel state information, reflection phase shift and transmission power based on the uplink channel; The generating module is used to generate feedback information in response to the request information based on the preset beamforming structure, the downlink channel state information and the reflection phase shift; The sending module is used to send the feedback information to the electronic device according to the transmission power.

7. The device according to claim 6, characterized in that The apparatus also includes a beamforming recovery module; The beamforming recovery module is used to determine equivalent downlink channel information based on the request information, the downlink channel state information and the base station reflection phase shift; and recover the beamforming matrix according to the equivalent downlink channel information and the transmission power.

8. A signal transmission device, characterized in that: include: a processor and a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 5.

9. A server, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed on an electronic device, the method according to any one of claims 1 to 5 is implemented.

Images