Method for generating channel data, electronic equipment, base station and readable storage medium

Abstract

The invention discloses a method for generating channel data, electronic equipment, a base station and a readable storage medium, and belongs to the field of wireless communication. The method comprises the following steps: acquiring a target noise signal; inputting the target noise signal into a target machine learning model for channel prediction processing to obtain predicted channel data; and outputting the predicted channel data. Wherein the target machine learning model is a trained machine learning model used for channel prediction; the channel prediction processing comprises multi-dimensional channel feature extraction, and the multi-dimensional channel features comprise airspace channel features.

Description

Technical Field

[0001] The present application belongs to the field of wireless communications, and in particular relates to a method for generating channel data, an electronic device, a base station, and a readable storage medium. Background Art

[0002] Currently, in many cases, it is necessary to apply real channel data in wireless communication environments. However, due to limited conditions, the amount of real channel data obtained is often small. Therefore, it is very important to obtain data that is equivalent to the real channel data.

[0003] Related technologies can obtain predicted channel data that is equivalent to real channel data through wireless channel prediction. However, the wireless channel prediction methods of related technologies are often difficult to predict complex channels and cannot better meet application requirements. Summary of the invention

[0004] The embodiments of the present application provide a method for generating channel data, an electronic device, a base station and a readable storage medium, which can solve the problem that the method of wireless channel prediction in related technologies often has difficulty in predicting complex channels and cannot better meet application requirements.

[0005] In a first aspect, an embodiment of the present application provides a method for generating channel data, including:

[0006] Acquire target noise signal;

[0007] Inputting the target noise signal into a target machine learning model for channel prediction processing to obtain predicted channel data;

[0008] outputting the predicted channel data;

[0009] Among them, the target machine learning model is a machine learning model that has been trained for channel prediction; the channel prediction processing includes multi-dimensional channel feature extraction, and the multi-dimensional channel features include spatial domain channel features.

[0010] In a second aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed, the steps of the method described in the first aspect are implemented.

[0011] In a third aspect, an embodiment of the present application provides a base station, which includes the electronic device described in the second aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed, the steps of the method described in the first aspect are implemented.

[0013] In an embodiment of the present application, a target noise signal is obtained; the target noise signal is input into a target machine learning model for channel prediction processing to obtain predicted channel data; the predicted channel data is output; wherein the target machine learning model is a machine learning model that has been trained for channel prediction; the channel prediction processing includes multi-dimensional channel feature extraction, and the multi-dimensional channel features include spatial channel features. In this way, compared with the related art that only extracts frequency domain channel features or time domain channel features, by using a trained machine learning model to extract multi-dimensional channel features including spatial channel features, the effect of dimensional expansion can be achieved, so that more complex channels (such as spatially distributed multi-antenna channels) can be predicted, ensuring that the obtained predicted channel data is more three-dimensional and does not lose spatial correlation, thereby better meeting application requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1-1 It is a schematic diagram of the structure of a generative adversarial network provided in an embodiment of the present application;

[0015] Figure 1-2 is a schematic diagram of a structural model of an example generator provided in an embodiment of the present application;

[0016] Figure 1-3 is a schematic diagram of a structural model of an example identifier provided in an embodiment of the present application;

[0017] Figure 2 It is a flowchart of a method for generating channel data provided by an embodiment of the present application;

[0018] Figure 3 It is a flowchart of another method for generating channel data provided by an embodiment of the present application;

[0019] Figure 4 It is a flowchart of another method for generating channel data provided by an embodiment of the present application;

[0020] Figure 5 It is a flowchart of another method for generating channel data provided by an embodiment of the present application;

[0021] Figure 6 is a flowchart of the training process of the target machine learning model in an embodiment of the present application;

[0022] Figure 7 is a structural block diagram of a device for generating channel data provided by an embodiment of the present application;

[0023] Figure 8 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0026] As described in the background technology section, real channel data in wireless communication environments is needed in many situations, but due to limited conditions, the amount of real channel data obtained is often small. Related technologies usually use wireless channel prediction to obtain predicted channel data that is equivalent to real channel data, but because related technologies often use mathematical model modeling, it is difficult to predict complex channels, which has made it impossible to better meet the needs.

[0027] The embodiment of the present application provides a method for generating channel data, obtaining a target noise signal; inputting the target noise sample into a target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction; outputting the predicted channel data; wherein the target machine learning model is a trained machine learning model; the multi-dimensional channel features include spatial channel features. In this way, by extracting features from the multi-dimensional channel, multi-dimensional channel characteristics and distribution characteristics can be reflected simultaneously. At the same time, since the multi-dimensional channel feature extraction includes spatial channel features, it can adapt to most communication environments, so that the generated channel data has higher accuracy, which can solve the problem that the prior art cannot fully reflect the joint distribution characteristics of multi-dimensional channels to a certain extent.

[0028] In an embodiment of the present application, feature extraction is performed on spatial channel features and time domain channel features and / or frequency domain channel features through a two-dimensional convolutional layer, so as to achieve the purpose of simultaneously extracting spatial channel features and time domain channel features and / or frequency domain channel features. When the discriminator is working, the influence of spatial channel features can be considered while considering the time domain channel features and / or frequency domain channel features, thereby ensuring that the predicted channel data obtained is more three-dimensional and does not lose spatial correlation, thereby better meeting application requirements.

[0029] In an embodiment of the present application, the parameters of the generator are frozen, and the discriminator is trained through the second training sample to obtain a trained target discriminator; after obtaining the trained target discriminator, the parameters of the target discriminator are frozen. By freezing the parameters of the generator and training the discriminator, the purpose of synchronous training of the discriminator and the generator is achieved, and the entire generative adversarial network can be iterated to improve the accuracy of the generator in predicting channel data.

[0030] In an embodiment of the present application, the target machine learning model includes a target generator obtained by training based on a generative adversarial network, the target generator includes the multidimensional convolutional layer, and the predicted channel data is output by the target generator. The channel prediction method without using a generative adversarial network is limited to specific scenarios and has poor generalization, or is only applicable to small batch channel environment prediction. Compared with the method without using a generative adversarial network, the method of generating channel data provided by the embodiment of the present application is suitable for most communication environments, realizes large-scale prediction of channel data, and can simultaneously learn the correlation between time domain, frequency domain and spatial domain, so that the generated channel data is more accurate and the time-frequency characteristics are more in line with the real channel, filling the existing research gap.

[0031] At the same time, in an embodiment of the present application, during the training process of the target machine learning model, a first training sample for the generator is obtained, and the first training sample is used to reflect the real channel data; the loss value of the first training sample is determined through the generator loss function; based on the loss value of the first training sample, the generator is iteratively trained to obtain the target generator; wherein the generator loss function is associated with the real channel data and the simulated channel data generated by the generator. In this way, through this specific explicitly constrained generator loss function, the convergence speed can be increased, making the model training time shorter.

[0032] The embodiments of the present application can be used to reconstruct the real wireless channel environment in the outdoor field. On this basis, combined with the software and hardware simulation system, the performance of new systems and new methods in the real outdoor field can be studied. For example, the predicted channel data obtained can be used to verify the performance of the scheme or algorithm in the simulation platform of the wireless network. The embodiments of the present application can also be deployed in the base station as a channel predictor to perceive the wireless environment in advance, improve product performance, or improve the performance, problem finding and location of the existing technology in a specific outdoor field.

[0033] It should be understood that the discussion of the same noun or situation in the embodiments of the present application can be referenced before and after. That is to say, the discussion of a certain noun or situation in one embodiment can also be applied to the description of the noun or situation in other embodiments, as long as there is no logical contradiction.

[0034] The method provided in the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0035] The method for generating channel data provided in the embodiment of the present application is applied to the scenario of predicting and generating future channel data based on real channel data in the field of wireless communication. The method for generating channel data provided in the embodiment of the present application can be executed by a target device, wherein the target device can be an electronic device. The electronic device can be, for example, a terminal device such as a laptop computer, a tablet, or a server.

[0036] The method for generating channel data provided in the embodiment of the present application may involve a target machine learning model, which is a machine learning model that has been trained for channel prediction. The target machine learning model can be any deep learning model suitable for channel prediction. For example, the target machine learning model can be a generative adversarial network. In the field of wireless communications, a generative adversarial network includes a generator and a discriminator.

[0037] Figure 1-1 Schematic diagram of a structure of a generative adversarial network provided in an embodiment of the present application. Figure 1-1As shown in the figure, during the training process, the generator learns the characteristics of the training set data and, under the guidance of the discriminator, tries to fit the random noise distribution to the real distribution of the training data, thereby generating similar data with the characteristics of the training set. The discriminator is responsible for distinguishing whether the input data is real data or fake data generated by the generator and feeding it back to the generator. The two are trained alternately and their capabilities are improved synchronously until the data generated by the generator can pass the discriminator and reach a certain balance with the discriminator's capabilities. After the training is completed, the trained generative adversarial network can be used for the inference process. During the inference process, the input of the generator can be a noise signal, such as Gaussian white noise, and the output of the generator can be predicted channel data. In this way, the predicted channel data can be obtained using the generator in the trained generative adversarial network.

[0038] Figure 1-2 Schematic diagram of a structural model of an example generator provided in an embodiment of the present application. Figure 1-2 As shown, the input of the generator is noise, and its input is three layers of convolution-regularization-activation function layers. The kernel size of the convolution layer is 1 and the convolution layer can be a multi-dimensional convolution layer, such as a two-dimensional convolution layer. After each regularization layer, a rectified linear unit is used as the activation function. The generator uses an encoder-decoder mode. The encoder consists of several convolution-regularization-activation function layers, with a maximum pooling layer at the end of the even-numbered layers, and a loss layer is added at the end; the decoder consists of several convolution-regularization-activation function layers, with a deconvolution layer before the odd-numbered layers, and a loss layer is added at the end. Finally, there is a residual connection between the encoder and the decoder, and the final channel data is generated through several convolution-regularization-activation function layers. It should be understood that Figure 1-2 The structure of the generator shown is only an example, and the embodiment of the present application does not specifically limit the number of layers of each part of the generator.

[0039] In the embodiments of the present application, Figure 1-3 Schematic diagram of a structural model of an example identifier provided in an embodiment of the present application. Figure 1-3 As shown, Figure 1-3 The discriminator in is composed of several convolution-regularization-activation function-max pooling-loss layers, several residual blocks and several fully connected layers. Among them, the convolutional network can be designed as a multi-dimensional convolution layer to simultaneously extract features in the time domain, frequency domain and spatial domain; the residual block can expand the learning field of the discriminator; finally, the two fully connected layers extract features and determine whether the input signal is a real signal. It should be understood that the embodiments of the present application do not specifically limit the number of layers of each part of the discriminator, and are only used as examples.

[0040] Figure 2 is a flow chart of a method for generating channel data provided by an embodiment of the present application, such as Figure 2As shown, the method for generating channel data provided by the embodiment of the present application may include the following steps:

[0041] Step 210, obtaining a target noise signal;

[0042] In the embodiment of the present application, the target noise signal may be any noise obtained, including artificial noise or noise caused by natural weather. The target noise signal may be Gaussian white noise.

[0043] In the embodiment of the present application, acquiring the target noise signal may specifically be that the electronic device receives a noise signal transmitted from an external device, or obtains an external noise signal through detection.

[0044] In the embodiment of the present application, once the target noise signal is obtained, channel data may be generated.

[0045] Step 220, inputting the target noise sample into the target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction;

[0046] In the embodiment of the present application, the target machine learning model can be as follows: Figure 1-1 The model obtained after the training of the generative adversarial network model is shown. The multi-dimensional channel feature extraction includes but is not limited to extracting any one of the three channel features, namely, time domain features, frequency domain features and spatial domain features.

[0047] Step 230, output the predicted channel data; wherein the target machine learning model is a trained machine learning model; and the multidimensional channel features include spatial channel features.

[0048] In an embodiment of the present application, a target noise signal is obtained; the target noise sample is input into a target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction; the predicted channel data is output; wherein the target machine learning model is a trained machine learning model; the multi-dimensional channel features include spatial channel features. In this way, by extracting features from the multi-dimensional channel, the effect of dimensional expansion is achieved, and the multi-dimensional channel features and distribution characteristics can be reflected simultaneously. At the same time, since the multi-dimensional channel feature extraction includes spatial channel features, the influence of spatial channel features can be considered to ensure that the obtained predicted channel data is more three-dimensional and does not lose spatial correlation, thereby better meeting application requirements.

[0049] In an embodiment of the present application, the target machine learning model may include a multidimensional convolution layer, which is used to extract spatial domain channel features and target channel features, and the target channel features are time domain channel features and / or frequency domain channel features.

[0050] In an embodiment of the present application, the target machine learning model includes a two-dimensional convolution layer, which is used to extract spatial domain channel features and time domain channel features, or the two-dimensional convolution layer is used to extract spatial domain channel features and frequency domain channel features.

[0051] In an embodiment of the present application, feature extraction is performed on spatial channel features and time domain channel features and / or frequency domain channel features through a two-dimensional convolutional layer, so as to achieve the purpose of simultaneously extracting spatial channel features and time domain channel features and / or frequency domain channel features. When the discriminator is working, the influence of spatial channel features can be considered while considering the time domain channel features and / or frequency domain channel features, thereby ensuring that the predicted channel data obtained is more three-dimensional and does not lose spatial correlation, thereby better meeting application requirements.

[0052] In an embodiment of the present application, the predicted channel data is used to verify the performance of a solution or algorithm in a simulation platform of a wireless network, or the predicted channel data is used to predict a channel condition of a base station.

[0053] In an embodiment of the present application, the target machine learning model can be a target generator obtained by training based on a generative adversarial network, the target generator includes the multidimensional convolutional layer, and the predicted channel data is output by the target generator. The channel prediction method without using a generative adversarial network is limited to specific scenarios and has poor generalization, or is only applicable to small batch channel environment prediction. Compared with the method without using a generative adversarial network, the method of generating channel data provided in the embodiment of the present application outputs predicted channel data based on a target generator obtained by a generative adversarial network, which can adapt to most communication environments and realize large-scale prediction of channel data. It can also simultaneously learn the correlation between the time domain, frequency domain, and spatial domain, so that the generated channel data has higher accuracy and the time-frequency characteristics are more in line with the real channel.

[0054] Figure 3 is a flow chart of a method for generating channel data provided by an embodiment of the present application, such as Figure 3 As shown, the method for generating channel data provided by the embodiment of the present application may include the following steps:

[0055] Step 310, obtaining a first training sample for a generator, wherein the first training sample is used to reflect real channel data;

[0056] In an embodiment of the present application, before using a trained target machine learning model, the target machine learning model needs to be trained. First, a first training sample for training a generator is obtained, and the first training sample includes but is not limited to using a real noise signal.

[0057] The generator can be used like Figure 1-1 or Figure 1-2 The generator model shown in the figure can be discussed in detail in the previous article. Figure 1-1 or Figure 1-2 The discussion of the generator model shown in FIG. 1 is to obtain the first training sample for training the generator, and then start training the generator.

[0058] Step 320, determining the loss value of the first training sample through a generator loss function;

[0059] In the embodiment of the present application, the loss value of the first training sample is determined by the generator loss function. An exemplary method of determining the loss value of the first training sample may be as follows: Figure 1-1 or Figure 1-2 As shown, the first training sample is input into the generator, and the loss value is obtained inside the generator through the generator loss function.

[0060] In one embodiment of the present application, the loss function of the generator can be

[0061] Wherein, L is the generator loss function, A is the old part of the generator loss function, λ is the coefficient, H is the real channel data, To simulate channel data, k is an integer greater than 1, and N is a constant.

[0062] Step 330, iteratively training the generator based on the loss value of the first training sample to obtain a target generator with target parameters; wherein the generator loss function is associated with real channel data and simulated channel data generated by the generator;

[0063] In the embodiment of the present application, after obtaining the loss value of the first training sample, the parameters of the model can be adjusted based on the loss value.

[0064] When the training is completed and a target generator with target parameters is obtained, the target generator can be used for the next step.

[0065] Step 340: Acquire a target noise signal.

[0066] In the embodiment of the present application, the target noise signal may be any noise obtained, including artificial noise or noise caused by natural weather. The target noise signal may be Gaussian white noise.

[0067] In the embodiment of the present application, acquiring the target noise signal may specifically be that the electronic device receives a noise signal transmitted from an external device, or obtains an external noise signal through detection.

[0068] In the embodiment of the present application, once the target noise signal is obtained, channel data may be generated.

[0069] Step 350, inputting the target noise sample into a target generator for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction;

[0070] In the embodiment of the present application, the target machine learning model can be as follows: Figure 1-1 The model obtained after the training of the generative adversarial network model is shown. The multi-dimensional channel feature extraction includes but is not limited to extracting any one of the three channel features, namely, time domain features, frequency domain features and spatial domain features.

[0071] Step 360, output the predicted channel data; wherein the multi-dimensional channel characteristics include spatial channel characteristics.

[0072] In an embodiment of the present application, during the training process of the target machine learning model, a first training sample for a generator is obtained, and the first training sample is used to reflect the real channel data; the loss value of the first training sample is determined through the generator loss function; based on the loss value of the first training sample, the generator is iteratively trained to obtain a target generator; wherein the generator loss function is associated with the real channel data and the simulated channel data generated by the generator. In this way, through this specific explicitly constrained generator loss function, the convergence speed can be increased, making the model training time shorter.

[0073] Figure 4 is a flow chart of a method for generating channel data provided by an embodiment of the present application, such as Figure 4 As shown, the method for generating channel data provided by the embodiment of the present application may include the following steps:

[0074] Step 410, sampling a target channel in a wireless channel environment to obtain real channel information, wherein the target channel includes a spatial domain channel and at least one of a time domain channel and a frequency domain channel;

[0075] Step 420, converting the real channel information into a target matrix, where the target matrix is ​​used to reflect the characteristics of the real channel information in the spatial channel, and at least one of the time channel and the frequency channel, and using the target matrix as a first training sample;

[0076] In the embodiment of the present application, the target matrix may be a three-dimensional matrix, and the three-dimensional matrix may simultaneously reflect the characteristics of the real channel information in the time domain, frequency domain and spatial domain. Of course, the target matrix may also be a two-dimensional matrix.

[0077] Step 430, determining the loss value of the first training sample through a generator loss function;

[0078] In the embodiment of the present application, the loss value of the first training sample is determined by the generator loss function. An exemplary method of determining the loss value of the first training sample may be as follows: Figure 1-1 or Figure 1-2 As shown, the first training sample is input into the generator, and the loss value is obtained inside the generator through the generator loss function.

[0079] In one embodiment of the present application, the loss function of the generator can be

[0080] Wherein, L is the generator loss function, A is the old part of the generator loss function, λ is the coefficient, H is the real channel data, To simulate channel data, k is an integer greater than 1, and N is a constant.

[0081] Step 440, iteratively training the generator based on the loss value of the first training sample to obtain a target generator with target parameters; wherein the generator loss function is associated with real channel data and simulated channel data generated by the generator;

[0082] In the embodiment of the present application, after obtaining the loss value of the first training sample, the parameters of the model can be adjusted based on the loss value.

[0083] When the training is completed and a target generator with target parameters is obtained, the target generator can be used for the next step.

[0084] Step 450, obtaining a target noise signal;

[0085] In the embodiment of the present application, the target noise signal may be any noise obtained, including artificial noise or noise caused by natural weather. The target noise signal may be Gaussian white noise.

[0086] In the embodiment of the present application, acquiring the target noise signal may specifically be that the electronic device receives a noise signal transmitted from an external device, or obtains an external noise signal through detection.

[0087] In the embodiment of the present application, once the target noise signal is obtained, channel data may be generated.

[0088] Step 460, inputting the target noise sample into a target generator for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction;

[0089] In the embodiment of the present application, the target machine learning model can be as follows: Figure 1-1 The model obtained after the training of the generative adversarial network model is shown. The multi-dimensional channel feature extraction includes but is not limited to extracting any one of the three channel features, namely, time domain features, frequency domain features and spatial domain features.

[0090] Step 470, output the predicted channel data; wherein the multi-dimensional channel characteristics include spatial channel characteristics.

[0091] In an embodiment of the present application, a target channel in a wireless channel environment is sampled to obtain real channel information, wherein the target channel includes a spatial channel, and at least one of a time domain channel and a frequency domain channel; the real channel information is converted into a three-dimensional matrix, wherein the three-dimensional matrix is ​​used to reflect the characteristics of the real channel information in the time domain, frequency domain and spatial domain, and the three-dimensional matrix is ​​used as a first training sample, wherein the first training sample is used to reflect the real channel data. By sampling the target channel of the wireless channel, converting the sampled information into a three-dimensional matrix, and obtaining information that simultaneously reflects the spatial channel, the time domain channel and the frequency domain channel, the correlation of the time domain, the frequency domain and the spatial domain can be learned at the same time, so that the generated channel data has higher accuracy and the time-frequency characteristics are more in line with the real channel.

[0092] Figure 5 is a flow chart of a method for generating channel data provided by an embodiment of the present application, such as Figure 5 As shown, the method for generating channel data provided by the embodiment of the present application may include the following steps:

[0093] Step 510, sampling a target channel in a wireless channel environment to obtain real channel information, wherein the target channel includes a spatial domain channel and at least one of a time domain channel and a frequency domain channel;

[0094] Step 520, converting the real channel information into a multidimensional matrix, the multidimensional matrix is ​​used to reflect the characteristics of the real channel information in the time domain, frequency domain and spatial domain, and using the multidimensional matrix as a first training sample, the first training sample is used to reflect the real channel data;

[0095] In the embodiment of the present application, the target matrix may be a three-dimensional matrix, and the three-dimensional matrix may simultaneously reflect the characteristics of the real channel information in the time domain, frequency domain and spatial domain. Of course, the target matrix may also be a two-dimensional matrix.

[0096] Step 530, obtaining a second training sample for training the discriminator;

[0097] In this embodiment of the present application, the second training sample includes the first training sample and the output result of the generator.

[0098] Step 540, freezing the parameters of the generator, and training the discriminator through the second training sample to obtain a trained target discriminator;

[0099] In the embodiment of the present application, the parameters of the generator include but are not limited to the above Figure 3-Figure 4 The target parameters of the generator are not specifically required in the present embodiment. After freezing the parameters of the generator, the discriminator is trained. The process of training the discriminator can be referred to as above. Figure 3-Figure 4 In the training process of the generator, the second training sample is input into the discriminator, and the loss value of the second training sample is obtained by using the discriminator loss function. Based on the loss value of the second training sample, the parameters of the discriminator are obtained, and the training is repeated to further obtain the trained target discriminator.

[0100] Step 550, after obtaining the trained target discriminator, freezing the parameters of the target discriminator;

[0101] In the embodiment of the present application, after obtaining the target discriminator, the parameters of the target discriminator are frozen so as to start training the generator to obtain the target generator.

[0102] Step 560, determining the loss value of the first training sample through a generator loss function;

[0103] In the embodiment of the present application, the loss value of the first training sample is determined by the generator loss function. An exemplary method of determining the loss value of the first training sample may be as follows: Figure 1-1 or Figure 1-2 As shown, the first training sample is input into the generator, and the loss value is obtained inside the generator through the generator loss function.

[0104] In one embodiment of the present application, the loss function of the generator can be

[0105] Wherein, L is the generator loss function, A is the old part of the generator loss function, λ is the coefficient, H is the real channel data, To simulate channel data, k is an integer greater than 1, and N is a constant.

[0106] Step 570, iteratively training the generator based on the loss value of the first training sample to obtain a target generator with target parameters; wherein the generator loss function is associated with real channel data and simulated channel data generated by the generator;

[0107] In the embodiment of the present application, after obtaining the loss value of the first training sample, the parameters of the model can be adjusted based on the loss value.

[0108] When the training is completed and a target generator with target parameters is obtained, the target generator can be used for the next step.

[0109] Step 580, obtaining a target noise signal;

[0110] In the embodiment of the present application, the target noise signal may be any noise obtained, including artificial noise or noise caused by natural weather. The target noise signal may be Gaussian white noise.

[0111] In the embodiment of the present application, acquiring the target noise signal may specifically be that the electronic device receives a noise signal transmitted from an external device, or obtains an external noise signal through detection.

[0112] In the embodiment of the present application, once the target noise signal is obtained, channel data may be generated.

[0113] Step 590, inputting the target noise sample into the target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction;

[0114] In the embodiment of the present application, the target machine learning model can be as follows: Figure 1-1 The model obtained after the training of the generative adversarial network model is shown. The multi-dimensional channel feature extraction includes but is not limited to extracting any one of the three channel features, namely, time domain features, frequency domain features and spatial domain features.

[0115] Step 595, output the predicted channel data; wherein the multi-dimensional channel characteristics include spatial channel characteristics.

[0116] In an embodiment of the present application, the parameters of the generator are frozen, and the discriminator is trained through the second training sample to obtain a trained target discriminator; after obtaining the trained target discriminator, the parameters of the target discriminator are frozen. By freezing the parameters of the generator and training the discriminator, the purpose of synchronous training of the discriminator and the generator is achieved, and the entire generative adversarial network can be iterated to improve the accuracy of the generator in predicting channel data.

[0117] Figure 6 Flowchart of the training process of the target machine learning model in the embodiment of the present application. Figure 6 As shown, the training process of the target machine learning model in the embodiment of the present application may include:

[0118] Step S1: Establish the generator model and discriminator model in the generative adversarial network and define the loss function and

[0119] In an embodiment of the present application, the process of constructing the generator model in step S1 can be as follows: construct a generator model, the input of the generator is noise, and its input is three layers of convolution-regularization-activation function layers, and the kernel size of the convolution layer is 1. After each regularization layer, a rectified linear unit is used as the activation function. The generator uses an encoder-decoder mode, the encoder consists of several convolution-regularization-activation function layers, there is a maximum pooling layer at the end of the even layer, and a loss layer is added at the end; the decoder consists of several convolution-regularization-activation function layers, there is a deconvolution layer before the odd layer, and a loss layer is added at the end. Finally, there is a residual connection between the encoder and the decoder, and the final channel data is generated through several convolution-regularization-activation function layers.

[0120] In the embodiment of the present application, the process of constructing the discriminator model in step S1 can be as follows: construct a discriminator model, which consists of several convolution-regularization-activation function-maximum pooling-loss layers, several residual blocks and several fully connected layers. Among them, the convolution network needs to be designed as a two-dimensional convolution layer to simultaneously extract features in the time domain, frequency domain and spatial domain; the residual block expands the discriminator learning field of view; finally, two fully connected layers extract features and determine whether the input signal is a real signal.

[0121] In this embodiment of the present application, the noise signal z can be defined as obeying the probability distribution p z , the generator and discriminator models are G and D respectively, and the generator parameter is θ G , using H and Represent the original channel data and the generated channel data respectively, use λ as the proportional coefficient, and define the generator loss function

[0122] in, Represents a generator parameter set θ G , so that the following calculation formula is minimized; Indicates that the input noise obeys the noise distribution; G(z,H) indicates that when the current training sample is H, the input noise z, the channel data generated by the generator D(x,H) represents the probability that the input discriminator data x is judged as real channel data when the current training sample is H, and the value is 0-1, 1-D(x,H) represents the probability of being judged as false channel data; log(1-D(G(z,H),H)) represents the probability that the generator generates The probability of being judged as fake by the discriminator; Represents the channel data generated by the generator and the difference norm of the true noise data H.

[0123] Then, the discriminator input noise signal z is defined, and the real channel data H follows the probability distribution p data , the discriminator parameter is θ D , the data input from the generator to the discriminator is x, and the discriminator loss function is defined

[0124] in, Represents a discriminator parameter set θ D ; = indicates that the input data x of the discriminator follows the distribution of the real channel data, that is, x is randomly extracted from the real channel data set, and x and H are both from the same real channel data set; [logD(x,H)] represents the probability of judging the real data as true; E z [log(1-D(G(z,H),H))] indicates that the discriminator converts the channel data generated by the generator The probability of being false.

[0125] Step S2, collecting channel information H′, organizing it into three dimensions of time domain, frequency domain and space domain, normalizing the data, and obtaining the first training sample H.

[0126] In the process of collecting channel information, the channel in the wireless channel environment can be sampled every fixed time slot to collect the real channel information H′, which is organized into three dimensions: time domain, frequency domain and space domain. The matrix is ​​obtained by the maximum-minimum linear normalization method. That is, first calculate the maximum amplitude H of all elements of the complex matrix H max With the minimum amplitude H min The difference is that all element amplitudes are subtracted from H min Then divide by this difference;

[0127] Step S3, initialize the generator parameters θG , discriminator parameters θ D , learning rate η and learning batch B, so that θ G and θ D Follows Gaussian distribution Where μ and σ represent the mean and variance of the initialization parameters respectively;

[0128] Step S4, sampling a training batch m from the training data set H; sampling a training batch m from the data set H, m should be smaller than the amount of data in the entire data set, but the maximum value that can be obtained under the support of computing power;

[0129] Step S5, freeze the generator parameters θ G ; Input the training batch m into the discriminator and start training the discriminator alone;

[0130] Step S6: Update the discriminator parameters through the Adaptive Moment Estimation (Adam) optimizer Through the loss function and Adam optimizer to update the discriminator parameters

[0131] Step S7, freeze the discriminator parameters θ D ; Input the noise signal z into the generator and start training the generator alone;

[0132] Step S8, update the generator parameters through the Adam optimizer Through the loss function And Adam optimizer updates the generator parameters

[0133] Step S9, determine whether the generator has reached convergence. If not, return to S5. If converged, end, and finally obtain a trained generative adversarial network and a predictively generated wireless channel.

[0134] The following two examples are used to Figure 6 The training process is specifically described. It should be understood that the examples are for better illustrating the embodiments of the present application, rather than limiting them.

[0135] In one embodiment of the present application, the training process of the target machine learning model provided in the embodiment of the present application may include:

[0136] First, build the generative adversarial network generator and discriminator models and define the loss function and

[0137] Among them, the establishment of Figure 1-1The generator model shown in the figure has noise as the input of the generator, which inputs three layers of convolution-regularization-activation function layers, and the kernel size of the convolution layer is 1. After each regularization layer, a rectified linear unit is used as the activation function. The generator uses an encoder-decoder mode. The encoder consists of six convolution-regularization-activation function layers, with maximum pooling layers at the end of the 2nd, 4th and 6th layers, and a loss layer is added at the end; the decoder consists of six convolution-regularization-activation function layers, with deconvolution layers before the 1st, 3rd and 5th layers, and a loss layer is added at the end. Finally, there is a residual connection between the encoder and the decoder, and the final channel data is generated through three convolution-regularization-activation function layers;

[0138] Establish as Figure 1-2 The discriminator model is constructed as shown in the figure. It consists of three convolution-regularization-activation function-max pooling-loss layers, three residual blocks and two fully connected layers. Among them, the convolutional network needs to be designed as a two-dimensional convolution layer to simultaneously extract features in the time domain, frequency domain and spatial domain; the residual block expands the discriminator learning field of view; finally, the two fully connected layers extract features and determine whether the input signal is a real signal;

[0139] For the generator, the noise signal z is defined to obey the probability distribution p z , the generator and discriminator models are G and D respectively, and the generator parameter is θ G , using H and Represent the original channel data and the generated channel data respectively, use λ as the proportional coefficient, and define the generator loss function The value of λ is 0.5;

[0140] in, Represents a generator parameter set θ G , so that the following calculation formula is minimized; Indicates that the input noise obeys the noise distribution; G(z,H) indicates that when the current training sample is H, the input noise z, the channel data generated by the generator D(x,H) represents the probability that the input discriminator data x is judged as real channel data when the current training sample is H, and the value is 0-1, 1-D(x,H) represents the probability of being judged as false channel data; log91-D9G(z,H),H)) represents the probability generated by the generator The probability of being judged as fake by the discriminator; Represents the channel data generated by the generator The difference norm between the real noise data H;

[0141] For the discriminator, the discriminator input noise signal z is defined, and the real channel data H obeys the probability distribution p data , the discriminator parameter is θ D, the data input from the generator to the discriminator is x, and the discriminator loss function is defined

[0142] in, Represents a discriminator parameter set θ D ; = indicates that the input data x of the discriminator follows the distribution of the real channel data, that is, x is randomly extracted from the real channel data set, and x and H are both from the same real channel data set; [logD(x,H)] represents the probability of judging the real data as true; E z [log(1-D(G(z,H),H))] indicates that the discriminator converts the channel data generated by the generator The probability of being judged as false;

[0143] All frequency domain channels in the wireless channel environment are sampled every fixed time slot to collect the real channel information H′, which is organized into three dimensions: time domain, frequency domain, and spatial domain. The matrix is ​​obtained by the maximum-minimum linear normalization method. That is, first calculate the maximum amplitude H of all elements of the complex matrix H max With the minimum amplitude H min The difference is that all element amplitudes are subtracted from H min Then divide it by the difference to get the training sample H;

[0144] Initialize the generator parameters θ G , discriminator parameters θ D , learning rate η and learning batch B, so that θ G and θ D Follows Gaussian distribution Where μ and σ represent the mean and variance of the initialization parameters respectively;

[0145] Sample training batch m from the dataset H. m should be smaller than the amount of data in the entire dataset but the maximum value that can be obtained if the computing power supports it.

[0146] Freeze generator parameters θ G , input the training batch m into the discriminator to start training the discriminator alone;

[0147] Through the loss function and Adam optimizer to update the discriminator parameters

[0148] Freeze the discriminator parameters θ D , input the noise signal z into the generator and start training the generator alone;

[0149] Through the loss function And Adam optimizer updates the generator parameters

[0150] Determine the generator parameter θ G Whether convergence is achieved, if not, return to Figure 6 The discussion shown in step S5 ends if convergence occurs. Finally, a trained generative adversarial network and a wireless channel generated predictively by a target generator are obtained.

[0151] In another embodiment of the present application, in one embodiment of the present application, the training process of the target machine learning model provided by the embodiment of the present application may include:

[0152] Build a generative adversarial network generator and discriminator model and define the loss function and

[0153] Among them, a generator model is established, the input of the generator is noise, and its input is five layers of convolution-regularization-activation function layers, and the kernel size of the convolution layer is 1. After each regularization layer, a rectified linear unit is used as the activation function. The generator uses an encoder-decoder mode. The encoder consists of eight convolution-regularization-activation function layers, with maximum pooling layers at the end of the 2nd, 4th, 6th and 8th layers, and a loss layer is added at the end; the decoder consists of eight convolution-regularization-activation function layers, with deconvolution layers before the 1st, 3rd, 5th and 7th layers, and a loss layer is added at the end. Finally, there is a residual connection between the encoder and the decoder, and the final channel data is generated through three convolution-regularization-activation function layers;

[0154] Establish a discriminator model, which consists of three convolution-regularization-activation function-max pooling-loss layers, three residual blocks and two fully connected layers. Among them, the convolutional network needs to be designed as a two-dimensional convolutional layer to simultaneously extract features in the time domain, frequency domain and spatial domain; the residual block expands the discriminator learning field of view; finally, the two fully connected layers extract features and determine whether the input signal is a real signal;

[0155] For the generator, the noise signal z is defined to obey the probability distribution p z , the generator and discriminator models are G and D respectively, and the generator parameter is θ G , using H and Represent the original channel data and the generated channel data respectively, use λ as the proportional coefficient, and define the generator loss function The value of λ is 0.7;

[0156] in, Represents a generator parameter set θ G , so that the following calculation formula is minimized; Indicates that the input noise obeys the noise distribution; G(z,H) indicates that when the current training sample is H, the input noise z, the channel data generated by the generator D(x,H) represents the probability that the input discriminator data x is judged as real channel data when the current training sample is H, and the value is 0-1, 1-D(x,H) represents the probability of being judged as false channel data; log(1-D(G(z,H),H)) represents the probability that the generator generates The probability of being judged as fake by the discriminator; Represents the channel data generated by the generator The difference norm between the real noise data H;

[0157] For the discriminator, the discriminator input noise signal z is defined, and the real channel data H obeys the probability distribution p data , the discriminator parameter is θ D , the data input from the generator to the discriminator is x, and the discriminator loss function is defined

[0158] in, Represents a discriminator parameter set θ D ; E x～pdata = indicates that the input data x of the discriminator follows the distribution of the real channel data, that is, x is randomly extracted from the real channel data set, and x and H are both from the same real channel data set; [logD(x,H)] represents the probability of judging the real data as true; E z [log(1-D(G(z,H),H))] indicates that the discriminator converts the channel data generated by the generator The probability of being judged as false;

[0159] The frequency domain channel in the wireless channel environment is sampled every fixed time slot to collect the real channel information H′, which is organized into three dimensions: time domain, frequency domain, and spatial domain. The matrix is ​​obtained by the maximum-minimum linear normalization method. That is, first calculate the maximum amplitude H of all elements of the complex matrix H max With the minimum amplitude H min The difference is that all element amplitudes are subtracted from H min Then divide it by the difference to get the training sample H;

[0160] Initialize the generator parameters θ G , discriminator parameters θ D , learning rate η and learning batch B, so that θ G and θ D Follows Gaussian distribution Where μ and σ represent the mean and variance of the initialization parameters respectively;

[0161] Sample training batch m from the dataset H. m should be smaller than the amount of data in the entire dataset but the maximum value that can be obtained if the computing power supports it.

[0162] Freeze generator parameters θ G , input the training batch m into the discriminator to start training the discriminator alone;

[0163] Through the loss function and Adam optimizer to update the discriminator parameters

[0164] Freeze the discriminator parameters θ D , input the noise signal z into the generator and start training the generator alone;

[0165] Through the loss function And Adam optimizer updates the generator parameters

[0166] Determine the generator parameter θ G Whether convergence is achieved, if not, return to Figure 6 The discussion shown in step S5 ends if convergence occurs. Finally, the trained generative adversarial network and the target generator are obtained to perform predictive generation of the wireless channel.

[0167] Figure 7 is a structural block diagram of a device for generating channel data provided by an embodiment of the present application. Figure 7 , the device 700 for generating channel data provided in the embodiment of the present application includes:

[0168] The acquisition module 710 is used to acquire a target noise signal.

[0169] The processing module 720 is used to input the target noise sample into the target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction.

[0170] The output module 730 is used to output the predicted channel data; wherein the target machine learning model is a trained machine learning model; and the multidimensional channel features include spatial channel features.

[0171] In an embodiment of the present application, a target noise signal is obtained; the target noise sample is input into a target machine learning model for channel prediction processing to obtain predicted channel data; wherein the channel prediction processing includes multi-dimensional channel feature extraction; the predicted channel data is output; wherein the target machine learning model is a trained machine learning model; the multi-dimensional channel features include spatial channel features. In this way, by extracting features from the multi-dimensional channel, the effect of dimensional expansion is achieved, and the multi-dimensional channel characteristics and distribution characteristics can be reflected simultaneously. At the same time, since the multi-dimensional channel feature extraction includes spatial channel features, it can adapt to most communication environments, so that the generated channel data is more accurate, which can solve the problem that the prior art cannot fully reflect the joint distribution characteristics of multi-dimensional channels to a certain extent.

[0172] In one embodiment of the present application, the target machine learning model includes a multidimensional convolution layer, which is used to extract spatial domain channel features and target channel features, and the target channel features are time domain channel features and / or frequency domain channel features.

[0173] In one embodiment of the present application, the target machine learning model includes a two-dimensional convolutional layer, which is used to extract spatial domain channel features and time domain channel features, or the two-dimensional convolutional layer is used to extract spatial domain channel features and frequency domain channel features.

[0174] In one embodiment of the present application, the target machine learning model includes a target generator trained based on a generative adversarial network.

[0175] In one embodiment of the present application, in the target machine learning training model process, the processing module 720 is also used to obtain a first training sample for the generator, wherein the first training sample is used to reflect real channel data; the loss value of the first training sample is determined through a generator loss function; based on the loss value of the first training sample, the generator is iteratively trained to obtain a target generator with target parameters; wherein the generator loss function is associated with the real channel data and the simulated channel data generated by the generator.

[0176] In one embodiment of the present application, in the process of obtaining the first training sample for the generator, the processing module 720 is also used to sample the target channel in the wireless channel environment to obtain real channel information, wherein the target channel includes a spatial domain channel, and at least one of a time domain channel and a frequency domain channel; convert the real channel information into a three-dimensional matrix, wherein the three-dimensional matrix is ​​used to reflect the characteristics of the real channel information in the time domain, frequency domain and spatial domain, and use the three-dimensional matrix as the first training sample.

[0177] In one embodiment of the present application, during the target machine learning training model process, the processing module 720 is also used to obtain a second training sample for training the discriminator; freeze the parameters of the generator, train the discriminator through the second training sample, and obtain a trained target discriminator; after obtaining the trained target discriminator, freeze the parameters of the target discriminator.

[0178] In addition, if Figure 8 As shown, the embodiment of the present application further provides an electronic device 800, which may be various types of computers, etc. The electronic device 800 includes: a processor 810 and a memory 820, wherein the memory 820 stores programs or instructions, and when the programs or instructions are executed by the processor 810, the steps of any of the methods described above are implemented, such as Figure 2-Figure 5 The steps of the method for generating channel data are shown in .

[0179] An embodiment of the present application further provides a base station, which includes the electronic device provided by any embodiment of the present application, and the electronic device can execute the method for generating channel data provided by any embodiment of the present application.

[0180] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0181] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0182] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0183] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0184] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0186] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for generating channel data, characterized in that: include: Acquire target noise signal; Inputting the target noise signal into a target machine learning model for channel prediction processing to obtain predicted channel data; outputting the predicted channel data; Among them, the target machine learning model is a machine learning model that has been trained for channel prediction; the channel prediction processing includes multi-dimensional channel feature extraction, and the multi-dimensional channel features include spatial domain channel features.

2. The method according to claim 1, characterized in that The target machine learning model includes a multidimensional convolution layer, which is used to extract spatial domain channel features and target channel features, and the target channel features include at least one of time domain channel features and frequency domain channel features.

3. The method according to claim 2, characterized in that The multidimensional convolution layer includes a two-dimensional convolution layer, and the two-dimensional convolution layer is used to extract spatial domain channel features and time domain channel features, or the two-dimensional convolution layer is used to extract spatial domain channel features and frequency domain channel features.

4. The method according to claim 2, characterized in that: The target machine learning model includes a target generator obtained through training based on a generative adversarial network, the target generator includes the multi-dimensional convolutional layer, and the predicted channel data is output by the target generator.

5. The method according to claim 4, characterized in that The training process of the target machine learning model includes: Acquire a first training sample for a generator, wherein the first training sample is used to reflect real channel data; Determining a loss value of the first training sample by using a generator loss function; Iteratively training the generator based on the loss value of the first training sample to obtain a target generator; Wherein, the generator loss function is associated with real channel data and simulated channel data generated by the generator.

6. The method according to claim 5, characterized in that The generator loss function is expressed as follows: Wherein, L is the generator loss function, A is the old part of the generator loss function, λ is the coefficient, H is the real channel data, To simulate channel data, k is an integer greater than 1, and N is a constant.

7. The method according to claim 5, characterized in that The obtaining of a first training sample for a generator comprises: Sampling a target channel in a wireless channel environment to obtain real channel information, wherein the target channel includes a spatial domain channel and at least one of a time domain channel and a frequency domain channel; The real channel information is converted into a target matrix, where the target matrix is ​​used to reflect the characteristics of the real channel information in a spatial domain channel, and at least one of a time domain channel and a frequency domain channel, and the target matrix is ​​used as a first training sample.

8. The method according to claim 5, characterized in that Before determining the loss value of the first training sample by the generator loss function, the training process of the target machine learning model further includes: Obtaining a second training sample for training the discriminator; Freezing the parameters of the generator, and training the discriminator through the second training sample to obtain a trained target discriminator; After obtaining the trained target discriminator, the parameters of the target discriminator are frozen.

9. The method according to claim 1, characterized in that: The predicted channel data is used to verify the performance of a solution or algorithm in a simulation platform of a wireless network, or the predicted channel data is used to predict a channel condition of a base station.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A base station, characterized in that: The base station comprises the electronic device according to claim 10.

12. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed, the steps of the method according to any one of claims 1 to 8 are implemented.

Images