Wireless channel modeling method and device

Abstract

The invention provides a wireless channel modeling method and device, and the method comprises the steps: inputting noise data into a generator of a target model, mapping a potential vector of the noise data to a higher-dimensional feature space through a linear block, carrying out the up-sampling of abstract high-dimensional features through a convolution transpose block, enabling the abstract high-dimensional features to be more specific, and carrying out the modeling of a wireless channel. The specific high-dimensional features are subjected to standardization processing in a batch processing layer, and the mean value and variance of the features are adjusted; the high-dimensional features are subjected to global spatial information compression, feature channel re-calibration and feature re-weighting in a channel attention module to obtain a feature re-weighting result, and finally an activation layer generates wireless channel data; and inputting the generated wireless channel data and real channel data into a discriminator of the target model, expanding the input data in a zero filling block, extracting features of a convolution block, discriminating in a linear block, outputting a discrimination result, updating weight parameters of the generator according to the discrimination result, and training the generator to generate wireless channel data similar to the real channel data. According to the invention, effective channel modeling is realized.

Description

Technical Field

[0001] The present invention relates to the field of wireless network technology, and in particular to a wireless channel modeling method and device. Background Art

[0002] Wireless channel modeling is the cornerstone of wireless network design and performance analysis. It provides a theoretical basis for understanding channel behavior and guides the design and optimization of wireless systems. This modeling work not only needs to consider the physical characteristics of the signal during transmission, such as attenuation, multipath effects, and Doppler shift, but also environmental factors such as the influence of terrain, buildings, and other obstacles. However, due to the inherent characteristics of wireless channels, including multipath propagation, fading, and shadowing effects, it exhibits a high degree of nonlinearity and time-varying properties, making the channel characteristics complex and difficult to accurately describe using traditional mathematical models.

[0003] With the development of deep learning technology, a series of deep learning-based wireless channel modeling methods have emerged in recent years. These methods use the powerful function approximation ability of neural networks to establish channel models by learning a large amount of channel measurement data, aiming to capture the complex nonlinear relationship of channel characteristics. They usually rely on large-scale field measurement data to ensure that the model can accurately reflect the physical and statistical characteristics of the channel. However, this dependence brings two major problems: first, the field measurement process is usually time-consuming and costly, especially in complex or inaccessible environments; second, as the communication environment continues to change, the amount of data required to continuously update the model is huge, and the data demand faced by traditional methods is growing exponentially, further exacerbating the resource burden. Summary of the invention

[0004] The present invention provides a wireless channel modeling method and device, which are used to solve the defects of wireless channel modeling in the prior art that wireless channel modeling relies on large-scale field measurement data and is high in cost. The present invention combines the attention mechanism with WGAN-GP and applies it to channel modeling, which can significantly reduce the amount of channel data required in the modeling process and effectively improve the accuracy and diversity of wireless channel samples.

[0005] The present invention provides a wireless channel modeling method, comprising:

[0006] The noise data is input into the generator of the target model. The linear block maps the potential vector of the noise data to a higher-dimensional feature space to obtain a high-dimensional feature. The convolution transposition block upsamples the abstract high-dimensional feature to make it more specific. The specific high-dimensional feature is standardized in the batch layer to adjust the mean and variance of the feature. The high-dimensional feature is compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel. Finally, the wireless channel data output is generated through the activation layer.

[0007] The generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolutional block, and finally discriminated by a linear block to output a discrimination result;

[0008] The weight parameters of the generator are updated according to the identification result, and the generator is trained to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, so as to achieve effective wireless channel modeling.

[0009] According to a wireless channel modeling method provided by the present invention, the high-dimensional features are subjected to global spatial information compression, feature channel recalibration and feature reweighting in a channel attention module to obtain a feature reweighting result for each channel, including:

[0010] Compressing the global spatial information of the feature map of the noise data by an adaptive average pooling operation, reducing the spatial dimensions of each channel of the noise data in height and width to 1, and obtaining the global spatial features of the noise data;

[0011] Passing the global spatial features through a network including a fully connected layer to obtain a weight coefficient for each channel;

[0012] After the weight coefficient of each channel is expanded to the spatial dimension of the corresponding feature map, it is multiplied by the feature map of each channel to obtain the feature re-weighted result of each channel.

[0013] According to a wireless channel modeling method provided by the present invention, the global spatial features are passed through a network including a fully connected layer to obtain a weight coefficient of each channel, including:

[0014] Performing dimensionality reduction on the global spatial features through a first fully connected layer;

[0015] The global spatial features after dimensionality reduction are processed by a ReLU activation function to increase the expression capability of the target model;

[0016] Performing dimensionality restoration on the processed global spatial features through a second fully connected layer;

[0017] The global spatial features after dimension restoration are passed through a Sigmoid activation function to obtain a weight coefficient for each channel.

[0018] According to a wireless channel modeling method provided by the present invention, the linear block maps the potential vector of the noise data to a higher dimensional feature space to obtain a high dimensional feature, including:

[0019] Inputting the noise data into the fully connected layer, batch normalization layer and Leaky ReLU activation function in the linear block in sequence;

[0020] Wherein, the fully connected layer is used to map the potential vector in the noise data to a feature space of a specific dimension;

[0021] The batch normalization layer is used to perform batch normalization processing on the feature vector of the noise data to accelerate the training process of the target model and stabilize the training of the target model;

[0022] The Leaky ReLU activation function is used to introduce nonlinear transformation and enhance the expressive power of the target model.

[0023] According to a wireless channel modeling method provided by the present invention, the convolution transposition block upsamples the abstract high-dimensional features to make them more specific, and the specific high-dimensional features are standardized in the batch processing layer to adjust the mean and variance of the features, including:

[0024] The feature map output by the linear block is sequentially convolved and transposed through multiple convolutional transposition layers in the convolutional transposition block;

[0025] Each of the convolutional transposition layers except the last convolutional transposition layer in the multiple convolutional transposition layers is sequentially connected to a batch normalization layer, a channel attention module, and a Leaky ReLU activation function;

[0026] The last convolution transpose layer upsamples the feature map to one channel, and finally outputs the generated wireless channel data through a Tanh activation function.

[0027] According to a wireless channel modeling method provided by the present invention, the generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally discriminated by a linear block to output a discrimination result, including:

[0028] Passing the real wireless channel data and the generated wireless channel data through the zero-filling module, the convolution block and the linear block of the discriminator in sequence to obtain the identification result;

[0029] Wherein, the zero padding module preprocesses the real wireless channel data and the generated wireless channel data through a Zero Padding function;

[0030] The convolution block is used to extract features from the real wireless channel data and the generated wireless channel data;

[0031] The linear block is used to discriminate the generated wireless channel data and output the discrimination result.

[0032] The present invention also provides a wireless channel modeling device, comprising:

[0033] A generation module is used to input the noise data into the generator of the target model. The linear block maps the potential vector of the noise data to a higher-dimensional feature space to obtain a high-dimensional feature. The convolution transposition block upsamples the abstract high-dimensional feature to make it more specific. The specific high-dimensional feature is standardized in the batch layer to adjust the mean and variance of the feature. The high-dimensional feature is compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel. Finally, the wireless channel data output is generated through the activation layer.

[0034] An identification module, used for inputting the generated wireless channel data and the real channel data as input data into the discriminator of the target model, wherein the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally subjected to linear block discrimination to output an identification result;

[0035] A training module is used to update the weight parameters of the generator according to the identification result, train the generator to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, and realize effective wireless channel modeling.

[0036] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the wireless channel modeling methods described above is implemented.

[0037] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the wireless channel modeling method described in any one of the above methods is implemented.

[0038] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the wireless channel modeling method described in any one of the above is implemented.

[0039] The wireless channel modeling method and device provided by the present invention, by introducing the channel attention module SEL into the generator of WGAN-GP, the model can adaptively recalibrate the importance of each feature channel, so as to focus more on the features that are critical to channel modeling, which not only enhances the model's ability to capture channel characteristics, but also improves the quality of the generated channel samples, thereby improving the accuracy and efficiency of wireless channel modeling. In addition, the introduction of the attention mechanism also helps to improve the training stability and efficiency of the model, so that the model can perform channel modeling more flexibly and accurately when facing a complex and changeable wireless environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a structural diagram of GAN in the wireless channel modeling method provided by the present invention;

[0042] Figure 2 It is a flow chart of the wireless channel modeling method provided by the present invention;

[0043] Figure 3 It is one of the structural schematic diagrams of the SE-GAN model in the wireless channel modeling method provided by the present invention;

[0044] Figure 4 This is the second structural diagram of the SE-GAN model in the wireless channel modeling method provided by the present invention;

[0045] Figure 5 It is a structural schematic diagram of a channel attention module in the wireless channel modeling method provided by the present invention;

[0046] Figure 6 It is a schematic diagram comparing the probability distribution of data generated by different models in the wireless channel modeling method provided by the present invention;

[0047] Figure 7 It is a structural schematic diagram of the wireless channel modeling device provided by the present invention;

[0048] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The rapid advancement of wireless communication technologies is driving the development of modern society, making it indispensable in daily life and industrial applications. The application scope of wireless communication technologies is rapidly expanding with the widespread application of technologies ranging from personal mobile communications to the Internet of Things (IoT), 5G networks and even the upcoming 6G technologies. The successful implementation of these technologies not only facilitates the instant exchange of information, but also provides a basis for innovative applications such as smart cities, telemedicine, and autonomous vehicles. In all of this, the wireless channel plays a vital role as a core component of the communication system. The characteristics of the wireless channel and its accurate modeling have a decisive influence on the design of efficient, reliable and forward-looking communication systems.

[0051] The introduction of Generative Adversarial Networks (GAN) provides a new perspective for wireless channel modeling. GAN provides a new approach to solving two problems in the existing wireless channel modeling methods. The structure of GAN is as follows: Figure 1 As shown in the figure, GAN can train a generative model by learning a limited channel measurement data set. The model can learn the data distribution of the channel data set, obtain the channel distribution, and generate a large amount of channel data consistent with the statistical characteristics of the real channel environment. Using GAN for channel modeling can not only significantly reduce the amount of channel data required in the modeling process, but also improve the adaptability and flexibility of the model, providing an efficient and cost-effective modeling method for the design and optimization of wireless communication systems.

[0052] On this basis, Wasserstein GAN (WGAN) effectively improves the mode collapse problem in the traditional GAN ​​training process by using Wasserstein distance as the loss function, and improves the quality of generated samples. In particular, the improved version of WGAN, WGAN-GP (WGAN with Gradient Penalty), further stabilizes the training process by introducing a gradient penalty term, allowing the model to generate more realistic and diverse data samples.

[0053] Combine the following Figure 2 A wireless channel modeling method of the present invention is described, comprising:

[0054] Step 201, input the noise data into the generator of the target model, the linear block maps the potential vector of the noise data to a higher dimensional feature space to obtain a high dimensional feature, the convolution transpose block upsamples the abstract high dimensional feature to make it more specific, the specific high dimensional feature is standardized in the batch layer, and the mean and variance of the feature are adjusted; the high dimensional feature is compressed by global spatial information, recalibrated by feature channels and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel, and finally the wireless channel data output is generated through the activation layer.

[0055] The noise data is in complex form.

[0056] Step 202, the generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally discriminated by a linear block to output a discrimination result;

[0057] Step 203, updating the weight parameters of the generator according to the identification result, training the generator to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, and realizing effective wireless channel modeling.

[0058] The target model is the WGAN-GP network. The WGAN-GP network is an improvement on the GAN, which includes a generator (G) and a discriminator (D). The goal of the generator is to generate data that is as close to the real data distribution as possible, while the goal of the discriminator is to distinguish between real data and generated data. The generator is ultimately able to generate data that is very similar to the real data. The discriminator finally outputs a scalar value. The scalar value represents the probability that the generated wireless channel data is the real channel data.

[0059] This embodiment combines the attention mechanism with the WGAN-GP network and applies it to the channel modeling field to enhance the model's ability to learn channel features. Figure 3 As shown in the figure, the WGAN-GP is used as the basic network, and the channel attention mechanism (Squeeze-and-Excitation Layer, SEL) is introduced to form the SE-GAN model. The introduced channel attention mechanism enhances the model's ability to express and recalibrate channel features by explicitly modeling the dependencies between channels, significantly improving the model's ability to learn wireless channel characteristics and the authenticity of generated samples. It also adaptively recalibrates the characteristic response of the channel, strengthening the model's capture of important channel features, thereby effectively improving the accuracy and diversity of wireless channel samples without increasing excessive computational complexity.

[0060] The SE-GAN structure proposed in this embodiment is as follows Figure 4 As shown in the figure. The generator consists of linear blocks and convolutional transposition blocks, and introduces the SEL layer of the channel attention mechanism. The main function of the linear block is to map the potential vector to a high-dimensional feature space. The convolutional transposition block is used to perform convolution and transposition processing on its input feature map to generate wireless channel data.

[0061] This embodiment introduces the channel attention module SEL into the generator of WGAN-GP, so that the model can adaptively recalibrate the importance of each feature channel, so as to focus more on the features that are critical to channel modeling, which not only enhances the model's ability to capture channel characteristics, but also improves the quality of the generated channel samples, thereby improving the accuracy and efficiency of wireless channel modeling. In addition, the introduction of the attention mechanism also helps to improve the training stability and efficiency of the model, so that the model can perform channel modeling more flexibly and accurately when facing a complex and changeable wireless environment. In general, this method of combining the attention mechanism with WGAN-GP provides a new perspective and tool for wireless channel modeling, showing significant improvements and advantages.

[0062] On the basis of the above embodiment, the high-dimensional features in this embodiment are subjected to global spatial information compression, feature channel recalibration and feature reweighting in the channel attention module to obtain feature reweighting results for each channel, including:

[0063] Compressing the global spatial information of the feature map of the noise data by an adaptive average pooling operation, reducing the spatial dimensions of each channel of the noise data in height and width to 1, and obtaining the global spatial features of the noise data;

[0064] Passing the global spatial features through a network including a fully connected layer to obtain a weight coefficient for each channel;

[0065] After the weight coefficient of each channel is expanded to the spatial dimension of the corresponding feature map, it is multiplied by the feature map of each channel to obtain the feature re-weighted result of each channel.

[0066] The design concept of the channel attention module SEL is that different feature channels contribute differently to the output of the model, and some channels may contain more valuable information for the current task. Therefore, by introducing a mechanism that can adaptively adjust the importance of each channel, the model can focus more on those more critical feature channels, thereby improving the overall model performance. Figure 5 The structure of SEL is shown in Figure 2. SEL can be divided into three parts: global spatial information compression, feature channel recalibration, and feature reweighting.

[0067] Global spatial information compression: SEL first compresses the global spatial information of the input feature map through the AdaptiveAvgPool 2D operation, reducing the spatial dimension (height and width) of each channel to 1, thereby obtaining a global spatial feature. This step helps capture the global statistical characteristics of each channel and provides a basis for subsequent importance evaluation.

[0068] Feature channel recalibration: The compressed features are passed through a network consisting of two fully connected layers to obtain the weight coefficient of each channel.

[0069] Feature reweighting: The calculated weight coefficient of each channel is multiplied by the original feature map on each channel to achieve dynamic recalibration of each channel feature. The Expand step expands the weight coefficient to the spatial dimension of the original feature map so that the features of each channel are multiplied by the corresponding weight coefficient.

[0070] This embodiment introduces a channel attention mechanism to explicitly model the dependencies between channels, enhances the model's ability to express and recalibrate channel features, and significantly improves the model's ability to learn wireless channel characteristics and the authenticity of generated samples. It also adaptively recalibrates the channel's characteristic response, strengthens the model's capture of important channel features, and effectively improves the accuracy and diversity of wireless channel samples without increasing excessive computational complexity.

[0071] On the basis of the above embodiment, in this embodiment, the global spatial feature is passed through a network including a fully connected layer to obtain a weight coefficient of each channel, including:

[0072] Performing dimensionality reduction on the global spatial features through a first fully connected layer;

[0073] The global spatial features after dimensionality reduction are processed by a ReLU activation function to increase the expression capability of the target model;

[0074] Performing dimensionality restoration on the processed global spatial features through a second fully connected layer;

[0075] The global spatial features after dimension restoration are passed through a Sigmoid activation function to obtain a weight coefficient for each channel.

[0076] When recalibrating the feature channels, the compressed features are passed through a network consisting of two fully connected layers. The first Linear layer realizes feature dimensionality reduction to reduce the number of parameters and computational complexity, while increasing the expressiveness of the model through the ReLU activation function. The second Linear layer is responsible for restoring the feature dimension, and finally outputs the weight coefficient of each channel through the Sigmoid activation function.

[0077] Based on the above embodiment, the linear block in this embodiment maps the potential vector of the noise data to a higher dimensional feature space to obtain a high dimensional feature, including:

[0078] Inputting the noise data into the fully connected layer, batch normalization layer and Leaky ReLU activation function in the linear block in sequence;

[0079] Wherein, the fully connected layer is used to map the potential vector in the noise data to a feature space of a specific dimension;

[0080] The batch normalization layer is used to perform batch normalization processing on the feature vector of the noise data to accelerate the training process of the target model and stabilize the target model network training;

[0081] The Leaky ReLU activation function is used to introduce nonlinear transformation and enhance the expressive power of the target model.

[0082] like Figure 4 As shown in the figure, the fully connected layer Linear in the linear block maps the input potential vector to a feature vector of a specific dimension. The batch normalization layer BatchNorm 1D batch normalizes the feature vector to speed up the training process and stabilize the model training. Then the Leaky ReLU activation function introduces nonlinear transformation to enhance the expressiveness of the model.

[0083] On the basis of the above embodiment, the convolution transposition block in this embodiment upsamples the abstract high-dimensional features to make them more specific. The specific high-dimensional features are standardized in the batch layer to adjust the mean and variance of the features, including:

[0084] The feature map output by the linear block is sequentially convolved and transposed through multiple convolutional transposition layers in the convolutional transposition block;

[0085] Each of the convolutional transposition layers except the last convolutional transposition layer in the multiple convolutional transposition layers is sequentially connected to a batch normalization layer, a channel attention module, and a Leaky ReLU activation function;

[0086] The last convolution transpose layer upsamples the feature map to one channel, and finally outputs the generated wireless channel data through a Tanh activation function.

[0087] like Figure 4As shown in the figure, the convolutional transpose block consists of five convolutional transpose layers. The first four convolutional transpose layers ConvTranspose2D are followed by a batch normalization layer BatchNorm 2D, a SEL layer, and a Leaky ReLU activation function. The fifth convolutional transpose layer upsamples the feature map to 1 channel, and finally outputs the generated channel data through the Tanh activation function.

[0088] On the basis of the above embodiment, in this embodiment, the generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in the zero-filling block, then extracted by the convolution block feature, and finally discriminated by the linear block to output the identification result, including:

[0089] Passing the real wireless channel data and the generated wireless channel data through the zero-filling module, the convolution block and the linear block of the discriminator in sequence to obtain the identification result;

[0090] Wherein, the zero padding module preprocesses the real wireless channel data and the generated wireless channel data through a Zero Padding function;

[0091] The convolution block is used to extract features from the real wireless channel data and the generated wireless channel data;

[0092] The linear block is used to discriminate the generated wireless channel data and output the discrimination result.

[0093] like Figure 4 As shown in Figure 1, the discriminator consists of three main modules, namely the zero padding module, the convolution block, and the linear block. The zero padding module preprocesses the input signal through the Zero Padding function. The height of the input signal is padded and expanded, while the width remains unchanged. This operation is designed to preserve the spatial characteristics of the signal and prevent information loss in subsequent convolution operations.

[0094] The convolutional block consists of four convolutional layers and four Leaky ReLU activation functions. The output of the convolutional block is flattened by the view function to form a high-dimensional vector. This vector is then input to the linear block Linear. The linear block consists of a fully connected layer that maps the high-dimensional input vector to a one-dimensional output.

[0095] In the forward propagation process, the input signal first passes through the zero padding module, then passes through the convolution block for feature extraction, and finally passes through the linear block for discrimination. The output discrimination result is a scalar value. The scalar value indicates the probability that the input signal belongs to the real channel data or the generated channel data.

[0096] A large number of simulation experiments are conducted to verify the effectiveness of the proposed algorithm. First, the consistency and discreteness of the real channel data and the generated channel data are numerically verified using similarity indicators and diversity indicators. The relevant simulation parameter settings are shown in Table 1. The data used comes from Wireless-Intelligence, which is a public channel data set library. The data set used is a full channel information data set in a MIMO channel environment with 32 transmitting antennas and 4 receiving antennas. The channel data consists of 4000 different samples. The samples are in plural form, each with a size of 4096, and the dimensional order is arranged as 4 receiving antennas, 32 transmitting antennas, and 32 delay extensions.

[0097] Table 1 Simulation parameter settings

[0098] parameter Numeric Carrier frequency 3.5GHz System bandwidth 10MHz Subcarrier spacing 15kHz Number of transmitting antennas 32 Number of receiving antennas 4 Delay Spread 32 Number of subcarriers 12

[0099] In order to evaluate the similarity between the channel data distribution generated by the network and the real channel data distribution, the similarity is expressed as:

[0100]

[0101] Where N fake is the number of generated channel samples, N real is the number of real channel samples, and H i are the vectored channels of the j-th generated channel sample and the i-th real channel sample respectively.

[0102] In addition, the diversity of the generated channel data is calculated using variance, and the diversity is expressed as:

[0103]

[0104] Where Var(·) represents the variance calculation of vector l, and l=[l1,l2,……l real Each element l in ] i0 It is expressed as:

[0105]

[0106] Where arg Max represents the real channel sample index corresponding to the maximum value of the above equation, and N(·) represents the value for all N fake The generated channel sample is taken the number of times the real channel sample index corresponds to i0.

[0107] The numerical results of the similarity and diversity between the channel data generated by SE-GAN and ChannelGAN proposed in this embodiment and the real channel data are shown in Table 2. The greater the similarity between the generated channel data and the real channel data, the smaller the diversity, that is, the smaller the multi / sim, the closer the distribution of the generated false channel data is to the distribution of the real channel data. From the numerical results in Table 2, SE-GAN is superior to ChannelGAN in terms of similarity, and its diversity index is significantly lower than that of ChannelGAN, and the comprehensive evaluation index Multi / Sim is much lower than that of ChannelGAN. Therefore, the experimental results show that the SE-GAN model proposed in this embodiment shows higher similarity and lower diversity in generating channel data, and the distribution of the channel data it generates is closer to the distribution of the real channel data, which verifies the superiority of SE-GAN in the channel modeling task.

[0108] Table 2 Similarities and differences between different channel modeling and generation schemes

[0109]

[0110] In order to verify the authenticity and validity of the complex channel data generated by the generator, the probability distribution of the amplitudes of the generated data of the SE-GAN proposed in this embodiment, the generated data of the existing model ChannelGAN and the real data on the first transmitting antenna, the first receiving antenna and the first delay extension are compared.

[0111] Figure 6 The figure shows the probability distribution of data generated by the SE-GAN model (yellow line), the probability distribution of data generated by the ChannelGAN model (green line), and the probability distribution of real data (blue line). As can be seen from the figure, the probability distribution of data generated by the SE-GAN model (yellow line) and the probability distribution of real data (blue line) are close in overall shape and peak position. The data generated by SE-GAN has a significant peak near 0, which is consistent with the main peak position of the real data. In addition, the tail attenuation trend of the data generated by SE-GAN on both the positive and negative sides is also similar to that of the real data, showing that SE-GAN can better capture the main characteristics of the channel when simulating channel data.

[0112] In contrast, although the probability distribution of the data generated by ChannelGAN (green line) also has a peak near 0, its peak is significantly higher and narrower than the real data and the data generated by SE-GAN. This shows that ChannelGAN has certain deviations in capturing the main features of the channel data, and the data it generates is too concentrated in certain amplitude values, lacking an accurate simulation of the amplitude distribution in the real data. In addition, the probability distribution of the data generated by ChannelGAN has two very obvious peaks, which is seriously inconsistent with the probability distribution of the real data. Moreover, the tail attenuation trend of the data generated by ChannelGAN on both the positive and negative sides is also quite different from the real data, further showing its limitations in generating channel data.

[0113] In summary, SE-GAN effectively improves the accuracy of wireless channel data generation by introducing the channel attention module. The probability distribution of the generated data is highly consistent with the real data, and it shows better performance than the existing model ChannelGAN. These experimental results not only prove the application value of the SE-GAN model in the field of wireless channel modeling and generation, but also provide new directions and ideas for subsequent research.

[0114] The SE-GAN proposed in this embodiment optimizes the network structure, thereby achieving higher efficiency in the process of loading and generating wireless channel data. In the experimental setting, the SE-GAN and ChannelGAN models are required to generate 4000 data samples respectively under the same conditions to evaluate their time efficiency in the data loading and generation process. The experimental results show that, as shown in Table 3, in the data loading stage, the SE-GAN model only takes 0.746142 seconds, while the ChannelGAN model takes 1.375484 seconds. In addition, in the data generation stage, the SE-GAN model is also more efficient, taking only 0.502677 seconds to complete the generation task, while the ChannelGAN model takes 0.572778 seconds. These results clearly show that SE-GAN has a significant advantage in the speed of data processing.

[0115] This significant performance improvement is mainly due to the introduction of the SE module in SE-GAN. The SE module effectively improves the network's attention to important information by dynamically adjusting the feature channels within the network, which not only improves the learning efficiency of the model but also reduces the time for data processing. In addition, the network structure optimization of SE-GAN further reduces the computational complexity, thereby achieving higher efficiency in the data loading and generation process.

[0116] Table 3 Data generation time for different channel modeling and generation schemes

[0117]

[0118] The wireless channel modeling device provided by the present invention is described below. The wireless channel modeling device described below and the wireless channel modeling method described above can be referenced to each other.

[0119] like Figure 7 As shown, the device includes a generation module 701, an identification module 702 and a training module 703, wherein:

[0120] The generation module 701 is used to input the noise data into the generator of the target model. The linear block maps the potential vector of the noise data to a higher-dimensional feature space to obtain a high-dimensional feature. The convolution transposition block upsamples the abstract high-dimensional feature to make it more specific. The specific high-dimensional feature is standardized in the batch layer to adjust the mean and variance of the feature. The high-dimensional feature is compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel. Finally, the wireless channel data output is generated through the activation layer.

[0121] The identification module 702 is used to input the generated wireless channel data and the real channel data as input data to the discriminator of the target model, wherein the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally discriminated by a linear block to output an identification result;

[0122] The training module 703 is used to update the weight parameters of the generator according to the identification result, and train the generator to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, so as to achieve effective wireless channel modeling.

[0123] In this embodiment, by introducing the channel attention module SEL into the generator of WGAN-GP, the model can adaptively recalibrate the importance of each feature channel, so as to focus more on the features that are critical to channel modeling. This not only enhances the model's ability to capture channel characteristics, but also improves the quality of generated channel samples, thereby improving the accuracy and efficiency of wireless channel modeling.

[0124] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8As shown, the electronic device may include: a processor (processor) 810, a communication interface (Communications Interface) 820, a memory (memory) 830 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 can call the logic instructions in the memory 830 to execute the wireless channel modeling method, which includes: inputting the noise data into the generator of the target model, the linear block maps the potential vector of the noise data to a higher dimensional feature space, the convolution transpose block upsamples the abstract high-dimensional features to make them more specific, and the specific high-dimensional features are standardized in the batch layer to adjust the mean and variance of the features; the high-dimensional features are compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain feature reweighted results, and finally the activation layer generates wireless channel data; the generated wireless channel data and the real channel data are input into the discriminator of the target model, the input data is expanded in the zero-filling block, the convolution block feature is extracted, and the linear block is discriminated, and the identification result is output, the weight parameters of the generator are updated according to the identification result, and the generator is trained to generate wireless channel data similar to the real channel data to achieve effective channel modeling.

[0125] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0126] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the wireless channel modeling method provided by the above methods, which includes: inputting noise data into the generator of the target model, the linear block maps the potential vector of the noise data to a higher-dimensional feature space, the convolution transpose block upsamples the abstract high-dimensional features to make them more specific, and the specific high-dimensional features are standardized in the batch layer to adjust the mean and variance of the features; the high-dimensional features are compressed by global spatial information, feature channel recalibration and feature reweighting in the channel attention module to obtain feature reweighting results, and finally the activation layer generates wireless channel data; the generated wireless channel data and the real channel data are input into the discriminator of the target model, the input data is expanded in the zero-filling block, the convolution block feature is extracted and the linear block is discriminated, and the identification result is output, the weight parameters of the generator are updated according to the identification result, and the generator is trained to generate wireless channel data similar to the real channel data to achieve effective channel modeling.

[0127] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the wireless channel modeling method provided by the above methods, the method comprising: inputting noise data into the generator of the target model, a linear block mapping the potential vector of the noise data to a higher dimensional feature space, a convolution transpose block upsampling the abstract high-dimensional features to make them more specific, and the specific high-dimensional features are standardized in the batch layer to adjust the mean and variance of the features; the high-dimensional features are subjected to global spatial information compression, feature channel recalibration and feature reweighting in the channel attention module to obtain feature reweighting results, and finally the activation layer generates wireless channel data; the generated wireless channel data and the real channel data are input into the discriminator of the target model, the input data is expanded in the zero-filling block, the convolution block feature is extracted and the linear block is discriminated, and the identification result is output, the weight parameters of the generator are updated according to the identification result, and the generator is trained to generate wireless channel data similar to the real channel data to achieve effective channel modeling.

[0128] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wireless channel modeling method, characterized in that: include: The noise data is input into the generator of the target model. The linear block maps the potential vector of the noise data to a higher-dimensional feature space to obtain a high-dimensional feature. The convolution transposition block upsamples the abstract high-dimensional feature to make it more specific. The specific high-dimensional feature is standardized in the batch layer to adjust the mean and variance of the feature. The high-dimensional feature is compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel. Finally, the wireless channel data output is generated through the activation layer. The generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolutional block, and finally discriminated by a linear block to output a discrimination result; The weight parameters of the generator are updated according to the identification result, and the generator is trained to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, so as to achieve effective wireless channel modeling.

2. The wireless channel modeling method according to claim 1, characterized in that: The high-dimensional features are subjected to global spatial information compression, feature channel recalibration and feature reweighting in the channel attention module to obtain feature reweighting results for each channel, including: Compressing the global spatial information of the feature map of the noise data by an adaptive average pooling operation, reducing the spatial dimensions of each channel of the noise data in height and width to 1, and obtaining the global spatial features of the noise data; Passing the global spatial features through a network including a fully connected layer to obtain a weight coefficient for each channel; After the weight coefficient of each channel is expanded to the spatial dimension of the corresponding feature map, it is multiplied by the feature map of each channel to obtain the feature re-weighted result of each channel.

3. The wireless channel modeling method according to claim 2, characterized in that: The global spatial features are passed through a network including a fully connected layer to obtain the weight coefficient of each channel, including: Performing dimensionality reduction on the global spatial features through a first fully connected layer; The global spatial features after dimensionality reduction are processed by a ReLU activation function to increase the expression capability of the target model; Performing dimensionality restoration on the processed global spatial features through a second fully connected layer; The global spatial features after dimension restoration are passed through a Sigmoid activation function to obtain a weight coefficient for each channel.

4. The wireless channel modeling method according to claim 1, characterized in that: The linear block maps the potential vector of the noise data to a higher dimensional feature space to obtain a high dimensional feature, including: Inputting the noise data into the fully connected layer, batch normalization layer and Leaky ReLU activation function in the linear block in sequence; Wherein, the fully connected layer is used to map the potential vector in the noise data to a feature space of a specific dimension; The batch normalization layer is used to perform batch normalization processing on the feature vector of the noise data to accelerate the training process of the target model and stabilize the training of the target model; The Leaky ReLU activation function is used to introduce nonlinear transformation and enhance the expressive power of the target model.

5. The wireless channel modeling method according to claim 1, characterized in that: The convolution transposition block upsamples the abstract high-dimensional features to make them more specific. The specific high-dimensional features are standardized in the batch processing layer to adjust the mean and variance of the features, including: The feature map output by the linear block is sequentially convolved and transposed through multiple convolutional transposition layers in the convolutional transposition block; Each of the convolutional transposition layers except the last convolutional transposition layer in the multiple convolutional transposition layers is sequentially connected to a batch normalization layer, a channel attention module, and a Leaky ReLU activation function; The last convolution transpose layer upsamples the feature map to one channel, and finally outputs the generated wireless channel data through a Tanh activation function.

6. The wireless channel modeling method according to claim 1, characterized in that: The generated wireless channel data and the real channel data are input as input data to the discriminator of the target model, the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally discriminated by a linear block to output a discrimination result, including: Passing the real wireless channel data and the generated wireless channel data through the zero-filling module, the convolution block and the linear block of the discriminator in sequence to obtain the identification result; Wherein, the zero padding module preprocesses the real wireless channel data and the generated wireless channel data through a Zero Padding function; The convolution block is used to extract features from the real wireless channel data and the generated wireless channel data; The linear block is used to discriminate the generated wireless channel data and output the discrimination result.

7. A wireless channel modeling device, characterized in that: include: A generation module is used to input the noise data into the generator of the target model. The linear block maps the potential vector of the noise data to a higher-dimensional feature space to obtain a high-dimensional feature. The convolution transposition block upsamples the abstract high-dimensional feature to make it more specific. The specific high-dimensional feature is standardized in the batch layer to adjust the mean and variance of the feature. The high-dimensional feature is compressed by global spatial information, recalibrated by feature channels, and reweighted by features in the channel attention module to obtain the feature reweighted results of each channel. Finally, the wireless channel data output is generated through the activation layer. An identification module, used to input the generated wireless channel data and real channel data as input data into the discriminator of the target model, wherein the input data is first expanded in a zero-filling block, then subjected to feature extraction by a convolution block, and finally discriminated by a linear block to output an identification result; A training module is used to update the weight parameters of the generator according to the identification result, train the generator to generate wireless channel data whose similarity with the real channel data is less than a preset threshold, and realize effective wireless channel modeling.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the wireless channel modeling method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the wireless channel modeling method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the wireless channel modeling method according to any one of claims 1 to 6 is implemented.

Images