Vehicle-ground wireless channel prediction method based on position information coding and periodic nonlinear neural network

Abstract

The invention belongs to the field of communication technologies and neural networks, provides a train-ground wireless channel prediction method based on position information coding and a periodic nonlinear neural network, and is suitable for optimization of a train-ground wireless communication system. The method comprises the following specific steps: S1, collecting position information and wireless channel instances of a train, carrying out position coding on the collected channel instances, and mapping the channel instances to a high-dimensional Fourier feature space; s2, integrating the periodic nonlinear neural network, constructing a generative deep neural network, and learning and modeling the channel instance based on the position information coding and the periodic nonlinear neural network; and S3, performing real-time channel prediction by using the trained model, and supporting dynamic optimization of a wireless communication system. According to the method, the precision and efficiency of train-ground wireless channel prediction are improved, and the method has remarkable technical advantages.

Description

Technical Field

[0001] The invention belongs to the fields of communication technology and neural network, and in particular relates to a vehicle-ground wireless channel prediction method based on position information coding and periodic nonlinear neural network. Background Art

[0002] Intelligent channel prediction plays a vital role in artificial intelligence (AI) optimization or AI-native communication networks in intelligent high-speed railways. Especially in the vehicle-to-ground (T2G) wireless communication scenario, the fast time-varying channel state information (CSI) obtained by traditional channel estimation schemes is often outdated, so efficient and accurate channel prediction is indispensable without consuming additional radio resources. Considering that the generation and change of the channel itself is caused by the propagation of specific electromagnetic waves, it has a clear physical meaning and is very suitable for characterization and prediction using neural networks. In actual communication scenarios, the area served by the base station, the number and position of scatterers are relatively fixed. Therefore, the channel at any fixed position in the area served by the base station can be considered as quasi-static. Since all wireless communication processes occurring in a specific area are affected by the same scattering environment, the static channel characteristics at different locations in the area are highly correlated and therefore predictable. In addition, when considering the T2G wireless communication scenario, the T2 wireless channel can be calculated by compensating the Doppler shift of the static channel. Therefore, it is possible to learn the implicit representation of the scattering environment using channel data randomly sampled in the wireless environment, and efficiently and accurately predict the channel impulse response at any location in the environment.

[0003] There are two major challenges in this work: first, the channel response is highly non-smooth in space, and conventional learning structures cannot accurately characterize the changes of the channel in space with limited samples as training data; second, this problem requires reconstructing high-dimensional information (such as channel impulse response) from extremely low-dimensional data (such as position coordinates), which is essentially a complex generation problem that requires the network to have the ability to learn channel structure.

[0004] Machine learning is one of the effective ways to solve the above problems. Many studies have shown that neural networks have the ability to directly mine the correlation between data and learn information about the scattering environment. However, traditional deep neural networks (DNNs) often require a large amount of training data and a large number of hidden parameters to complete such prediction tasks. And traditional DNNs are likely to cause overfitting or large prediction errors. In addition, the phase part of the electromagnetic wave propagation process is very sensitive to position changes. A small position change between adjacent sampling points will cause a huge change in phase. This has an important impact on the final fitting accuracy of the DNN. Therefore, it is necessary to design a special learning structure that can make full use of the physical characteristics of electromagnetic wave propagation. Summary of the invention

[0005] The purpose of the present invention is to overcome the above existing challenges and provide a vehicle-ground wireless channel prediction method based on position information coding and periodic nonlinear neural network. Channel information is obtained based on neural network to improve the efficiency and accuracy of channel prediction.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for predicting a vehicle-ground wireless channel based on position information coding and periodic nonlinear neural network, characterized in that it comprises the following steps:

[0008] S1: collecting the train location information and wireless channel instances, and performing position coding on the collected channel instances;

[0009] Collect train location information and wireless channel instances;

[0010] Perform positional encoding (PE) on the collected channel instances and map the channel instances to a high-dimensional Fourier feature space;

[0011] S2: Based on position information encoding and periodic nonlinear neural network, a generative deep neural network is constructed to learn and model channel instances;

[0012] S3: Apply the generative deep neural network model to perform real-time channel prediction.

[0013] Further, step S1 includes:

[0014] S11: Collect train location information

[0015] The train location information includes but is not limited to the acquisition of various train location information, and the various train location information includes: obtaining train location information by transponder, inertial navigation, GPS, Beidou, etc.;

[0016] S12: Collect wireless channel examples

[0017] The wireless channel instance includes one or more uplink / downlink historical communication data and historical channel information generated during the communication between the train and the base station; the historical communication data includes channel state information CSI; the historical channel information includes historical channel state information and historical channel impulse response (Channel Impulse Response, CIR).

[0018] S13: Position encoding is performed on the collected channel instances, as follows:

[0019] G(d k )=[…,a k cos(2πσ j / m d k ),a k sin(2πσ j / m d k ),…] T for j=0,…,m-1.

[0020] Among them, σ and j / m are the scale factors of the position encoding. The frequency of each dimension is adjusted by the scale factors σ and j / m to generate a series of frequencies from low to high. Here σ is an adjustable scale factor, j represents the index of the encoding, and m is the total number of frequencies.

[0021] Further, step S2 includes:

[0022] S21: Integrate periodic nonlinear neural networks and position encoding to construct generative deep neural networks;

[0023] The generative deep neural network includes a position information encoding layer and a periodic nonlinear neural network layer;

[0024] The position information encoding layer expands the input position, time, frequency and other parameters into high-dimensional features through position encoding, and provides them to the periodic nonlinear neural network layer for real-time channel prediction;

[0025] The periodic nonlinear neural network refers to a neural network using a nonlinear activation function. The present invention uses a sinusoidal representation network (SIREN), as follows:

[0026]

[0027]

[0028] In SIREN, x represents the input of the neural network, Φ(x) represents the output of the neural network, Represents a specific connection between two layers, represents the i-th layer of the network, which is composed of the weight matrix enter Bias And sine nonlinear activation function.

[0029] S22: Learn and model the channel instances.

[0030] The overall training process is as follows:

[0031] First, data preparation is performed by loading the real channel impulse response (CIR) dataset and decomposing the complex value into real and imaginary parts. The input parameters such as position, time and frequency are expanded into high-dimensional features through position encoding.

[0032] Model initialization, initialize the weights and biases of SIREN. Use a special weight initialization method to ensure that the model can effectively capture the high-frequency characteristics of the channel. The weight initialization scheme is as follows:

[0033]

[0034] Among them, d in is the input dimension, and U is the uniform distribution function.

[0035] The supervised learning method is used in the training process, using wireless channel instances (i.e., channel impulse response (CIR)) as labels, and the prediction accuracy and generalization ability of the model are improved by optimizing the loss function, which is:

[0036]

[0037] Among them, q is the output dimension, y is the training label, is the predicted value. MSE represents the average distance between the target value and the predicted value in all output dimensions.

[0038] Back propagation calculates gradients and updates network parameters.

[0039] Furthermore, in step S3, the neural network model trained in step S2 is used to perform real-time channel prediction, and the train position, environment and channel parameters are input to output the predicted real-time channel impulse response (CIR), including the real and imaginary parts of the CIR, to provide support for dynamic adjustment of the communication system.

[0040] Furthermore, the real-time channel prediction includes predicting future wireless channel impulse responses based on the real-time position information, running speed and other dynamic data of the train, and dynamically adjusting the parameters of the communication system to optimize the signal quality.

[0041] By mathematically analyzing the physical process of the channel impulse response, the present invention finds that for a certain electromagnetic wave propagation path in a specific area, its response amplitude is only related to the propagation path length and the number of reflections, while its phase changes periodically with the path length. Therefore, in the framework proposed by the present invention, the position information encoding provides a high-dimensional Fourier feature, which helps the model capture the high-frequency information of the input signal in the feature space and enhances the model's perception of the multipath characteristics of the channel. The periodic nonlinear neural network further processes the Fourier features of the position encoding. Due to the periodic characteristics of its sinusoidal activation function, the periodic nonlinear neural network can better fit the high dynamic phase characteristics of the channel instance mapped to the Fourier feature space, thereby accurately predicting the channel response in both the frequency domain and the time domain.

[0042] Compared with the prior art, the present invention has the following advantages:

[0043] 1) The network proposed in the present invention simulates the physical process of CIR generation, thereby integrating prior information into the network structure, which greatly reduces the complexity of network learning and the dependence on data volume.

[0044] 2) The convergence speed of the network proposed in the present invention is faster than that of various control networks. Thanks to the convergence characteristics of the sine representation network (SIREN), the addition of position information encoding enables the periodic nonlinear neural network to avoid the problem of spectrum deviation in traditional neural network fitting during the fitting process. The model's perception of the multipath characteristics of electromagnetic wave propagation is effectively enhanced, and the network can quickly obtain high-frequency information in the input signal in the initial stage. Since the training algorithm of the network is back propagation, shallow networks with fewer parameters have a faster convergence speed.

[0045] 3) The difference in the final convergence loss of the network proposed in the present invention under different sampling rates is smaller than that of various control networks. The special network structure that simulates the CIR generation process reduces the network's dependence on the sampling rate of the training data set. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of the channel prediction method of the present invention;

[0047] Figure 2 A schematic diagram of a neural network of the present invention;

[0048] Figure 3 It is a schematic diagram of the convergence curve of the neural network of the present invention;

[0049] Figure 4 It is a schematic diagram of the performance comparison between the neural network of the present invention and various control methods;

[0050] Figure 5 A schematic diagram showing the comparison between the neural network prediction result and the original data of the present invention;

[0051] Figure 6 It is a schematic diagram comparing the prediction results of the control method of the present invention with the original data;

[0052] Figure 7 It is a schematic diagram for comparing the predicted results of the control method of the present invention with the original data. DETAILED DESCRIPTION

[0053] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] like Figure 1 The present invention relates to a vehicle-ground wireless channel prediction method based on position information coding and periodic nonlinear neural network, characterized in that it comprises the following steps:

[0055] A method for predicting a vehicle-ground wireless channel based on position information coding and periodic nonlinear neural network, characterized in that it comprises the following steps:

[0056] S1: collecting the train location information and wireless channel instances, and performing position coding on the collected channel instances;

[0057] Collect train location information and wireless channel instances;

[0058] Perform positional encoding (PE) on the collected channel instances and map the channel instances to a high-dimensional Fourier feature space;

[0059] S2: Based on position information encoding and periodic nonlinear neural network, a generative deep neural network is constructed to learn and model channel instances;

[0060] S3: Apply neural network model for real-time channel prediction.

[0061] Further, step S1 includes:

[0062] S11: Collect train location information

[0063] The train location information includes but is not limited to the acquisition of various train location information, and the various train location information includes: obtaining train location information by transponder, inertial navigation, GPS, Beidou, etc.;

[0064] S12: Collect wireless channel examples

[0065] The wireless channel instance includes one or more uplink / downlink historical communication data and historical channel information generated during the communication between the train and the base station; the historical communication data includes channel state information CSI; the historical channel information includes historical channel state information and historical channel impulse response (Channel Impulse Response, CIR). It should be pointed out that CIR is not only used to directly calculate parameters related to CSI, but also provides an intuitive representation of the multipath characteristics of the wireless channel.

[0066] The quasi-static expression of the CIR can be expressed as:

[0067]

[0068] Where N represents the number of propagation paths, a k represents the loss function of the kth path, f is the carrier frequency, v c represents the speed of light, d k represents the propagation path length, and τ represents the propagation delay. The CIR formula shows that a channel instance is formed by a series of path responses coupled. Each path response can be divided into two parts: the attenuation factor a k =λ / 4πd k and phase shift

[0069] Estimating Doppler shift: In the vehicle-to-ground wireless communication scenario, there is a Doppler effect between the base station and the train, which causes a frequency shift in each propagation path. For a given path, the Doppler shift is estimated as:

[0070]

[0071] Among them, v k is the relative speed of the kth path.

[0072] The presence of Doppler frequency shift causes the received CIR to change dynamically over time, which can be expressed as:

[0073]

[0074] Furthermore, in order to mitigate the impact of Doppler frequency shift and restore the quasi-static nature of CIR, a Doppler compensation mechanism is applied at the receiver. The Doppler compensation mechanism includes but is not limited to: Doppler compensation based on velocity and position information.

[0075] According to formulas (1), (2), and (3), by introducing Doppler compensation to offset phase adjustment, the compensated CIR can be expressed as:

[0076] h comp (f,τ)=h(f-Δf,τ)·e j2πΔft(4)

[0077] Furthermore, for quasi-static CIR, according to the Friis equation, the signal energy received by a certain signal transmission path can be written as:

[0078]

[0079] Among them, d k represents the path length of the direct path, P TX Indicates the transmission energy of TX, G TX represents the transmit antenna gain, G RX represents the receiving antenna gain, and λ = c / f is the wavelength of the electromagnetic wave. The electromagnetic field strength excited by a certain propagation path at the RX end can be written as:

[0080]

[0081] When all antenna gains are set to 1, the received signal energy is the square root of the transmitted energy and can be written as:

[0082]

[0083] For phase shift The phase shift information can be decomposed into real and imaginary parts using sine and cosine components in polar coordinate form, namely:

[0084]

[0085] S13: Position encoding is performed on the collected channel instances, as follows:

[0086]

[0087] Among them, σ and j / m are the scale factors of the position encoding. The frequency of each dimension is adjusted by the scale factors σ and j / m to generate a series of frequencies from low to high. Here σ is an adjustable scale factor, j represents the index of the encoding, and m is the total number of frequencies.

[0088] From the above formulas (1) and (4), it can be concluded that the wireless channel instance in vehicle-to-ground wireless communication (i.e., channel impulse response (CIR)) can be decomposed into multiple electromagnetic wave propagation paths, where each path (LOS path and NLOS path) has a loss factor inversely proportional to the path length and a phase shift proportional to the path length. The channel impulse response function exhibits certain radial and periodic characteristics of amplitude and phase, respectively, where:

[0089] The radial characteristic, i.e. the amplitude, is inversely proportional to the propagation path length (based on the Friis equation).

[0090] Periodic characteristics: On the electromagnetic wave propagation path, the phase shift of the signal changes periodically with the path length and carrier frequency.

[0091] Therefore, the channel impulse response can be regarded as an implicit function of the train position information coordinates.

[0092] Further, step S2 includes:

[0093] S21: Integrate periodic nonlinear neural networks and position encoding to construct generative deep neural networks;

[0094] Position coding, i.e. position information coding, provides high-dimensional Fourier features, which helps the model capture the high-frequency information of the input signal in the feature space and enhances the model's ability to perceive the multipath characteristics of the channel. The periodic nonlinear neural network further processes the Fourier features of the position coding.

[0095] like Figure 2 , the generative deep neural network includes a position information encoding layer and a periodic nonlinear neural network layer;

[0096] The position information encoding layer expands the input position, time, frequency and other parameters into high-dimensional features through position encoding, and provides them to the periodic nonlinear neural network layer for real-time channel prediction;

[0097] According to formulas (1), (7), and (8), in the generation problem of channel impulse response, the channel impulse response function is considered to be two parts, which respectively show radial and periodic characteristics of amplitude and phase. This characteristic is called partial implicit periodicity. This type of function can be expressed as:

[0098]

[0099] d k =(P x , P y , P z ) (11)

[0100] The CIR is decomposed into the radial variation of the amplitude F(d k ) and the periodic changes in phase d k The three-dimensional coordinates P of the receiver and transmitter x , P y , P z Determine, F(d k ) is about k The inverse function of , describing the attenuation of the signal with distance, The position code obtained in step S1 is about A periodic function of . For a about d kThe implicit periodic function of It has partial implicit periodicity.

[0101] Specifically, the periodic nonlinear neural network refers to a neural network using a nonlinear activation function. The present invention uses a sinusoidal representation network (SIREN), as follows:

[0102]

[0103] In SIREN, x represents the input of the neural network, Φ(x) represents the output of the neural network, Represents a specific connection between two layers, represents the i-th layer of the network, which is composed of the weight matrix enter Bias Compared with the traditional ReLU and Tanh activation functions, SIREN can accurately model the implicit periodic characteristics of the phase change of the channel due to the difference in sampling distance and propagation path length, as well as the radial attenuation characteristics of the signal amplitude that changes with path loss and propagation distance through the sine activation function.

[0104] S22: Learn and model the channel instances.

[0105] The overall training process is as follows:

[0106] First, data preparation is performed by loading the real channel impulse response (CIR) dataset and decomposing the complex value into real and imaginary parts. The input parameters such as position, time and frequency are expanded into high-dimensional features through position encoding.

[0107] Model initialization, initialize the weights and biases of SIREN. Use a special weight initialization method to ensure that the model can effectively capture the high-frequency characteristics of the channel. The weight initialization scheme is as follows:

[0108]

[0109] Among them, d in is the input dimension, and U is the uniform distribution function.

[0110] The supervised learning method is used in the training process, using wireless channel instances (i.e., channel impulse response (CIR)) as labels, and the prediction accuracy and generalization ability of the model are improved by optimizing the loss function, which is:

[0111]

[0112] Among them, q is the output dimension, y is the training label, is the predicted value. MSE represents the average distance between the target value and the predicted value in all output dimensions.

[0113] Back propagation calculates gradients and updates network parameters.

[0114] Furthermore, in step S3, the neural network model trained in step S2 is used to perform real-time channel prediction, and the train position, environment and channel parameters are input to output the predicted real-time channel impulse response (CIR), including the real and imaginary parts of the CIR, to provide support for dynamic adjustment of the communication system.

[0115] Furthermore, the real-time channel prediction includes predicting future wireless channel impulse responses based on the real-time position information, running speed and other dynamic data of the train, and dynamically adjusting the parameters of the communication system to optimize the signal quality.

[0116] By mathematically analyzing the physical process of the channel impulse response, the present invention finds that for a certain electromagnetic wave propagation path in a specific area, its response amplitude is only related to the propagation path length and the number of reflections, while its phase changes periodically with the path length. Therefore, in the framework proposed by the present invention, the position information encoding provides a high-dimensional Fourier feature, which helps the model capture the high-frequency information of the input signal in the feature space and enhances the model's perception of the multipath characteristics of the channel. The periodic nonlinear neural network further processes the Fourier features of the position encoding. Due to the periodic characteristics of its sinusoidal activation function, the periodic nonlinear neural network can better fit the high dynamic phase characteristics of the channel instance mapped to the Fourier feature space, thereby accurately predicting the channel response in both the frequency domain and the time domain.

[0117] Algorithm performance comparison: The prediction accuracy of the vehicle-ground wireless channel prediction method (PE_SIREN) based on position information encoding and periodic nonlinear neural network of the present invention is compared with that of the sine representation network (SIREN), feedforward neural network (FNN), LSTM network, and CGAN network, as follows:

[0118] 1) If Figure 3 As shown, when the sampling rate is 80%, the convergence speed and prediction accuracy of the method of the present invention (PE_SIREN), the sine representation network (SIREN) and the feedforward neural network (FNN) training can be compared from the curve. Among them, the X-axis represents the training step size, ranging from 1 to 200000. The y-axis represents the mean square error (MSE) on the training data set. Under the same sampling rate (sample rate), the method of the present invention (PE_SIREN) can achieve higher prediction accuracy and maintain a faster convergence speed compared to the sine representation network and the feedforward neural network. At the same time, the addition of position information encoding has a significant improvement in the performance of deep neural networks.

[0119] 2) If Figure 4 As shown, the present invention compares the five methods mentioned at three sampling rates. All five methods can effectively solve the CIR prediction problem to a certain extent, and can achieve better performance when more training data is obtained. Among them, in the absence of a periodic activation function, the method of the feedforward neural network performs worse than the other four methods at all sampling rates. The results of the LSTM and CGAN networks show that these two network structures do not have the ability to learn in a scattering environment, because the prediction results depend on the channel correlation of adjacent sampling points. When the sampling rate is 80%, the NMSEs of the feedforward neural network, the sinusoidal representation network and the method of the present invention (PE_SIREN) are 0.0243754, 0.0103265 and 0.00959294 respectively. When the sampling rate is 40%, the NMSEs of the three schemes are 0.0448695, 0.0145865 and 0.0128514 respectively. When the sampling rate is set to 20%, the NMSEs are 0.0729376, 0.0225399, and 0.0179453, respectively. The above results show that the learning structure using PE_SIREN can bring excellent performance improvement compared with the traditional learning structure and popular network. And at a lower sampling rate, the prediction accuracy of the method (PE_SIREN) of the present invention will not decrease significantly. This further verifies the feasibility of the scheme proposed in this paper.

[0120] 3) If Figure 5 , 6 7 shows the comparison of the prediction results of the three networks with the original measured power delay profile (PDP) at a low sampling rate of 1 km from the base station. It can be calculated that at 4 km, the MSE of the prediction results of the method of the present invention (PE_SIREN), the sine representation network and the feedforward neural network and the original data (Original_PDP) are 11.227120dB, 14.919109dB, and 27.023975dB, respectively.

[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for predicting vehicle-ground wireless channels based on position information coding and periodic nonlinear neural network, characterized in that: The following steps are involved: S1: collecting the train location information and wireless channel instances, and performing position coding on the collected channel instances; Collect train location information and wireless channel instances; Position encoding is performed on the collected channel instances, and the channel instances are mapped to a high-dimensional Fourier feature space; S2: Based on position information encoding and periodic nonlinear neural network, a generative deep neural network is constructed to learn and model channel instances; S3: Apply the generative deep neural network model to perform real-time channel prediction.

2. The method according to claim 1, characterized in that: Step S1 includes: S11: Collect train location information The train location information includes but is not limited to the acquisition of various train location information, and the various train location information includes: obtaining train location information by transponder, inertial navigation, GPS, Beidou, etc.; S12: Collect wireless channel examples The wireless channel instance includes one or more uplink / downlink historical communication data and historical channel information generated during the communication between the train and the base station; the historical communication data includes channel state information CSI; the historical channel information includes historical channel state information and historical channel impulse response; S13: Position encoding is performed on the collected channel instances, as follows: G(d k )=[…,a k cos(2πσ j / m d k ),a k sin(2πσ j / m d k ),…] T for j=0,…,m-1. Among them, σ and j / m are the scaling factors of position encoding. The frequency of each dimension is adjusted by the scaling factors σ and j / m to generate a series of frequencies from low to high; σ is an adjustable scale factor, j represents the index of the encoding, and m is the total number of frequencies.

3. The method according to claim 1, characterized in that: Step S2 includes: S21: Integrate periodic nonlinear neural networks and position encoding to construct generative deep neural networks; The generative deep neural network includes a position information encoding layer and a periodic nonlinear neural network layer; The position information encoding layer expands the input position, time, frequency and other parameters into high-dimensional features through position encoding, and provides them to the periodic nonlinear neural network layer for real-time channel prediction; The periodic nonlinear neural network refers to a neural network using a nonlinear activation function; S22: Learn and model the channel instances. The overall training process is as follows: First, data preparation is performed by loading the real channel impulse response (CIR) dataset and decomposing the complex value into real and imaginary parts. Input parameters such as position, time, and frequency are expanded into high-dimensional features through position encoding. Model initialization, initialization of the weights and biases of the periodic nonlinear neural network; the weight initialization scheme is as follows: Among them, d in is the input dimension, U is the uniform distribution function; During the training process, a supervised learning method is used, and the wireless channel instance, namely the channel impulse response CIR, is used as a label. The prediction accuracy and generalization ability of the model are improved by optimizing the loss function. The loss function is: Among them, q is the output dimension, y is the training label, is the predicted value; MSE represents the average distance between the target value and the predicted value in all output dimensions; Back propagation calculates gradients and updates network parameters.

4. The method according to claim 3, characterized in that: The periodic nonlinear neural network is a sinusoidal representation network SIREN, as follows: In SIREN, x represents the input of the neural network, Φ(x) represents the output of the neural network, and Φ(x) represents the specific connection between the two layers. represents the i-th layer of the network, which is composed of the weight matrix enter Bias And sine nonlinear activation function.

5. The method according to claim 1, characterized in that: In step S3, the neural network model trained in step S2 is used to perform real-time channel prediction, and the train position, environment and channel parameters are input to output the predicted real-time channel impulse response CIR, including the real part and imaginary part of CIR, to provide support for dynamic adjustment of the communication system.

6. The method according to claim 1, characterized in that: In step S3, the real-time channel prediction includes predicting the future wireless channel impulse response according to the real-time position information and running speed dynamic data of the train, and dynamically adjusting the parameters of the communication system to optimize the signal quality.

Images