Safe and reliable multi-hop ad hoc network wireless communication method in transformer substation

Abstract

The invention relates to the technical field of wireless communication, and discloses a safe and reliable multi-hop ad hoc network wireless communication method in a transformer substation, which comprises the following steps of: S101, determining a neighbor set of each node according to a communication range of the nodes in the transformer substation; step S104, generating a search range by taking the Euclidean distance between the starting node and the ending node as a diameter, and constructing graph network data according to the nodes in the search range; s105, inputting the graph network data into the neural network model, and outputting a first adjacent matrix; step S106, sending the first adjacent matrix to the Kth jump node to complete communication; according to the invention, the incidence relation of the nodes in the transformer substation is analyzed through the neural network model, and the training sample used for training the neural network model is generated through the ant colony algorithm according to the node communication condition in the future time, so that the neural network model has the prediction capability of the node communication condition in the future time. Therefore, the fault-tolerant rate of wireless communication is improved.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and more specifically, to a safe and reliable multi-hop self-organizing network wireless communication method in a transformer substation. Background Art

[0002] With the continuous improvement of the automation level of power systems, the equipment inside substations needs to achieve efficient and reliable communication connections. Traditional multi-hop ad hoc wireless communication methods usually set jump nodes according to the communication range of nodes for node-by-node communication. However, with the increase of total jump nodes, the end-to-end transmission delay will show a trend of significant increase, especially in the case of large-scale concurrent communication. Traditional multi-hop ad hoc wireless communication methods lack an effective resource scheduling mechanism, and there may be idle nodes, resulting in low node utilization.

[0003] The existing multi-hop ad hoc wireless communication method selects the jump node by calculating the communication quality between nodes (such as channel fading factor, signal-to-noise ratio, etc.), thereby reducing the number of total jump nodes for transmission and reducing end-to-end transmission delay. However, the existing multi-hop ad hoc wireless communication method mainly relies on the node communication status at the current time and lacks the ability to predict the node communication status in the future. As a result, when the node communication status suddenly changes (such as traffic surge, node failure, etc.), it is difficult to quickly adjust the transmission path, thereby affecting the reliability and efficiency of communication. Summary of the invention

[0004] The present invention provides a safe and reliable multi-hop ad hoc network wireless communication method in a transformer substation, which solves the technical problems in the above-mentioned background technology.

[0005] The present invention provides a safe and reliable multi-hop ad hoc wireless communication method in a substation, comprising the following steps: Step S101, determining a neighbor set of each node according to the communication range of the nodes in the substation; Step S102, calculating the signal-to-noise ratio from the start node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the first jump node; Step S103, calculating the signal-to-noise ratio from the first jump node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the second jump node, and repeating this step until the Kth jump node is obtained; Where K is a custom parameter; Step S104, generating a search range with the Euclidean distance between the start node and the end node as the diameter, and constructing graph network data according to the nodes in the search range; The graph network data G is represented as: G(V, E), where V represents the set of vertices in the graph network data G, and E represents the set of edges between vertices in the graph network data G; The i-th vertex is mapped to the i-th node, where 1≤i≤N, and N represents the number of nodes in the search range; The initial features of a vertex are represented by the attributes of the node to which it is mapped; Step S105, inputting the graph network data into the neural network model, and outputting a first adjacency matrix; The first adjacency matrix includes N rows and N columns, and the element values ​​of the first adjacency matrix are represented by 0 or 1, that is, the element value of the mth row and nth column is 1, which indicates that the mth node jumps to the nth node, otherwise, it indicates that the mth node does not jump to the nth node, wherein 1≤m≤N, 1≤n≤N; Step S106: Send the first adjacency matrix to the Kth jump node to complete the communication.

[0006] Furthermore, the signal-to-noise ratio from the i-th node to the j-th node is The calculation formula includes: ; ; ; ; in represents the useful signal power received by the jth node, represents the noise signal power received by the jth node, represents the signal transmission power of the i-th node, and They represent the channel fading factor and Euclidean distance from the i-th node to the j-th node, respectively. Temp represents the absolute temperature in Kelvin. represents the bandwidth of the jth node, provided by the device manufacturer, in Hertz, where , c represents the speed of light, f represents the carrier frequency, and k represents the Boltzmann constant.

[0007] Furthermore, the attributes of the node include: received signal strength, maximum transmission rate, packet loss rate, memory size and link quality indication, and the initial features of the corresponding vertex are obtained by normalizing the attributes of the node.

[0008] Furthermore, the correlation coefficient between each node in the search range and all nodes in its neighbor set is calculated, and when it is determined that the correlation coefficient is greater than or equal to a set threshold, an edge connection is constructed between the corresponding two vertices, where the set threshold is a custom parameter; The correlation coefficient between the i-th node and the j-th node The calculation formula is as follows: ; Where Y represents the number of dimensions of the initial features of the vertex, and Respectively represent the average values ​​of the initial features of the vertices corresponding to the i-th node and the j-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the i-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the j-th node.

[0009] Further, the neural network model includes: a first hidden layer, a second hidden layer and a third hidden layer; The first hidden layer is used to convert the initial features of each vertex of the graph network data into a matrix representation; The calculation formula for the first hidden layer is as follows: ; in represents the matrix representation of the i-th vertex, represents the initial feature of the i-th vertex, and W represents the weight parameter; The second hidden layer extracts features from the matrix representation of each vertex through three convolution kernels of different sizes to obtain three feature maps of different sizes, and then expands the three feature maps into vector representations and concatenates them to obtain a combined vector. The sizes of the three convolution kernels are 1×1, 3×3, and 5×5, respectively, and the step sizes of the three convolution kernels are all 1. The third hidden layer inputs the graph network data and outputs the first adjacency matrix.

[0010] Furthermore, the calculation formula of the third hidden layer includes: ; ; ; Where S represents the first adjacency matrix output by the third hidden layer, represents the set of vertices that are connected to the i-th vertex by edges. express The number of elements in , and Respectively represent the combined vectors of the i-th vertex and the j-th vertex, represents the update vector of the ith vertex, represents the association coefficient between the i-th vertex and the j-th vertex, and Represent the first weight parameter and the second weight parameter respectively, MLP represents a multi-layer perceptron, Indicates stacking the update vectors of N vertices, concat indicates concatenation, T indicates transposition, sigmoid indicates sigmoid activation function, and F indicates rounding up element values ​​greater than or equal to 0.5 to 1 and rounding down element values ​​less than 0.5 to 0.

[0011] Furthermore, according to step S101 to step S104, sample data of training samples for training the neural network model is obtained, and the attributes of all nodes in the substation are collected again after a preset time period, a transmission path is generated by an ant colony algorithm, and the transmission path is converted into a second adjacency matrix representation as sample labels for training samples for training the neural network model, wherein the transmission path is represented by a vector with N dimensions, and the element values ​​of the vector are represented by 0 or 1, and the i-th dimension value is 1, indicating that it passes through the i-th node, otherwise it does not pass through the i-th node, and the preset time period is a custom parameter.

[0012] Furthermore, the difference between the first adjacency matrix and the second adjacency matrix output by the neural network model at each iteration is specified as the loss function until a maximum number of iterations is reached, wherein the maximum number of iterations is a custom parameter.

[0013] The present invention provides a safe and reliable multi-hop ad hoc wireless communication system in a substation, comprising: A neighbor set determination module, which is used to determine the neighbor set of each node according to the communication range of the node in the substation; The first jump module is used to calculate the signal-to-noise ratio from the starting node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the first jump node; The second jump module is used to calculate the signal-to-noise ratio from the first jump node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the second jump node, and repeat this step until the Kth jump node is obtained; A graph network data construction module, which is used to generate a search range with the Euclidean distance between the start node and the end node as the diameter, and construct graph network data according to the nodes in the search range; A first adjacency matrix generation module, which is used to input the graph network data into the neural network model and output a first adjacency matrix; The first adjacency matrix sending module is used to send the first adjacency matrix to the Kth jump node to complete the communication.

[0014] The present invention provides a readable storage medium storing non-temporary computer-readable instructions. When the non-temporary computer-readable instructions are executed by a computer, the steps of the above-mentioned safe and reliable multi-hop ad hoc wireless communication method in a substation are executed.

[0015] The beneficial effects of the present invention are as follows: the present invention analyzes the association relationship of nodes in the substation through a neural network model, and generates training samples for training the neural network model through an ant colony algorithm according to the node communication conditions in the future, so that the neural network model has the ability to predict the node communication conditions in the future, thereby improving the fault tolerance of wireless communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a safe and reliable multi-hop ad hoc wireless communication method in a substation of the present invention; Figure 2 It is a schematic diagram of a safe and reliable multi-hop ad hoc wireless communication system in a substation of the present invention; Figure 3 It is a comparison chart of the experimental results of the present invention.

[0017] In the figure: a neighbor set determination module 201, a first jump module 202, a second jump module 203, a graph network data construction module 204, a first adjacency matrix generation module 205, and a first adjacency matrix sending module 206. DETAILED DESCRIPTION

[0018] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0019] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] like Figure 1 to Figure 3As shown, a safe and reliable multi-hop ad hoc wireless communication method in a substation includes the following steps: Step S101, determining a neighbor set of each node according to the communication range of the nodes in the substation; Step S102, calculating the signal-to-noise ratio from the start node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the first jump node; Step S103, calculating the signal-to-noise ratio from the first jump node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the second jump node, and repeating this step until the Kth jump node is obtained; Where K is a custom parameter, preferably, K is set to 3; Step S104, generating a search range with the Euclidean distance between the start node and the end node as the diameter, and constructing graph network data according to the nodes in the search range; The graph network data G is represented as: G(V, E), where V represents the set of vertices in the graph network data G, and E represents the set of edges between vertices in the graph network data G; The i-th vertex is mapped to the i-th node, where 1≤i≤N, and N represents the number of nodes in the search range; The initial features of a vertex are represented by the attributes of the node to which it is mapped; Step S105, inputting the graph network data into the neural network model, and outputting a first adjacency matrix; The first adjacency matrix includes N rows and N columns, and the element values ​​of the first adjacency matrix are represented by 0 or 1, that is, the element value of the mth row and nth column is 1, which indicates that the mth node jumps to the nth node, otherwise, it indicates that the mth node does not jump to the nth node, wherein 1≤m≤N, 1≤n≤N; Step S106: Send the first adjacency matrix to the Kth jump node to complete the communication.

[0021] It should be noted that by selecting a jump node based on the signal-to-noise ratio between nodes, data can be transmitted directly before the first adjacency matrix is ​​generated, thereby avoiding the time taken to generate the first adjacency matrix being too long, resulting in data transmission blockage and inability to transmit normally. Therefore, this "asynchronous" design can effectively improve the overall communication efficiency.

[0022] It should be noted that the nodes in the substation represent communication equipment installed in the substation or intelligent devices with communication functions, such as sensors, intelligent circuit breakers, protection devices, etc. The nodes in the substation are assigned unique codes, such as self-increasing positive integer codes or UUIDs, etc. The first adjacency matrix represents the two-dimensional matrix code of the transmission path from the starting node to the ending node. For example, if the element value of the 3rd row and 5th column of the first adjacency matrix is ​​1, it means that the 3rd node jumps to the 5th node.

[0023] In one embodiment of the present invention, the signal-to-noise ratio from the i-th node to the j-th node The calculation formula includes: ; ; ; ; in represents the useful signal power received by the jth node, represents the noise signal power received by the jth node, represents the signal transmission power of the i-th node, and They represent the channel fading factor and Euclidean distance from the i-th node to the j-th node, respectively. Temp represents the absolute temperature in Kelvin. represents the bandwidth of the jth node, provided by the device manufacturer, in Hertz, where , c represents the speed of light, f represents the carrier frequency, and k represents the Boltzmann constant.

[0024] In one embodiment of the present invention, the attributes of the node include: received signal strength, maximum transmission rate, packet loss rate, memory size and link quality indication; the initial features of the corresponding vertex are obtained by normalizing the attributes of the node.

[0025] It should be noted that the initial features of the vertex are represented by a vector of size 1×5. The normalization process can be Min-Max normalization or Z-score normalization. Link Quality Indicator (LQI) is usually an indicator used to evaluate the quality of data packet reception in wireless communications. It is used to reflect the reliability of data packets during transmission. It is usually used in wireless sensor networks (such as Zigbee networks) and other low-power wide area network (LPWAN) technologies. The LQI value is usually an integer between 0 and 255, where 255 indicates the best link quality and 0 indicates the worst link quality.

[0026] In one embodiment of the present invention, the correlation coefficient between each node in the search range and all nodes in its neighbor set is calculated, and when it is determined that the correlation coefficient is greater than or equal to a set threshold, an edge connection is constructed between the corresponding two vertices, wherein the set threshold is a custom parameter, and preferably, the set threshold is set to 0.5; The correlation coefficient between the i-th node and the j-th node The calculation formula is as follows: ; The value of Y is 5. and Respectively represent the average values ​​of the initial features of the vertices corresponding to the i-th node and the j-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the i-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the j-th node.

[0027] In one embodiment of the present invention, the neural network model includes: a first hidden layer, a second hidden layer and a third hidden layer; The first hidden layer is used to convert the initial features of each vertex of the graph network data into a matrix representation; The calculation formula for the first hidden layer is as follows: ; in represents the matrix representation of the i-th vertex, represents the initial feature of the i-th vertex, and W represents the weight parameter; For example, W is designed as a vector of size 32×1, the initial features of the vertex are represented by a vector of size 1×5, and the matrix size obtained by multiplying the two is 32×5; The second hidden layer extracts features from the matrix representation of each vertex through three convolution kernels of different sizes to obtain three feature maps of different sizes, and then expands the three feature maps into vector representations and concatenates them to obtain a combined vector. The sizes of the three convolution kernels are 1×1, 3×3, and 5×5, respectively, and the step sizes of the three convolution kernels are all 1. For example, if the matrix size of the vertex is 32×5, and the sizes of the three feature maps obtained by three convolution kernels are 32×5, 30×3, and 28×1 respectively, then the size of the combined vector obtained by expanding and concatenating is 1×(160+90+28)=1×278; The third hidden layer inputs the graph network data and outputs the first adjacency matrix.

[0028] It should be noted that the second hidden layer may include multiple convolution kernels, and feature extraction may be performed through maximum pooling or average pooling after the convolution operation, which will not be elaborated here.

[0029] In one embodiment of the present invention, the calculation formula of the third hidden layer includes: ; ; ; Where S represents the first adjacency matrix output by the third hidden layer, represents the set of vertices that are connected to the i-th vertex by edges. express The number of elements in , and Respectively represent the combined vectors of the i-th vertex and the j-th vertex, represents the update vector of the ith vertex, represents the association coefficient between the i-th vertex and the j-th vertex, and Represent the first weight parameter and the second weight parameter respectively, MLP represents a multi-layer perceptron, Indicates stacking the update vectors of N vertices, concat indicates concatenation, T indicates transposition, sigmoid indicates sigmoid activation function, and F indicates rounding up element values ​​greater than or equal to 0.5 to 1 and rounding down element values ​​less than 0.5 to 0.

[0030] It should be noted that the first weight parameter and the second weight parameter in the third hidden layer are both learnable hyperparameters. For example, if the size of the combined vector of the vertices is 1×278, the first weight parameter and the second weight parameter can be designed as a matrix of size 278×8, then the size of the update vector is 1×8. The result is N×N, and the sigmoid activation function is used to unify the element values ​​in the N×N matrix to between 0 and 1.

[0031] In one embodiment of the present invention, sample data of training samples for training a neural network model is obtained according to steps S101 to S104, attributes of all nodes in the substation are collected again after a preset time period, a transmission path is generated by an ant colony algorithm, and the transmission path is converted into a second adjacency matrix representation as sample labels for training samples for training the neural network model, wherein the transmission path is represented by a vector with N dimensions, and the element values ​​of the vector are represented by 0 or 1, and the i-th dimension value is 1, indicating that it passes through the i-th node, otherwise it does not pass through the i-th node, wherein the preset time period is a custom parameter, and preferably, the preset time period is set to 30 seconds.

[0032] In one embodiment of the present invention, the heuristic factor from the i-th node to the j-th node The calculation formula is as follows: ; in , , and They represent the maximum transmission rate, packet loss rate, link quality indicator and received signal strength from the i-th node to the j-th node respectively.

[0033] It should be noted that the purpose of generating a transmission path through the ant colony algorithm after a preset time period is to enable the neural network model to have the ability to predict the node communication situation in the future, thereby improving the fault tolerance of wireless communication to a certain extent.

[0034] In one embodiment of the present invention, the difference between the first adjacency matrix and the second adjacency matrix output by the neural network model at each iteration is designated as the loss function until a maximum number of iterations is reached, wherein the maximum number of iterations is a custom parameter, and preferably, the maximum number of iterations is set to 500.

[0035] It should be noted that the gradient information of each weight parameter of the neural network model is calculated by the chain rule, and the weight parameters in the neural network model are updated by the gradient descent algorithm to minimize the loss function, which will not be elaborated here.

[0036] In one embodiment of the present invention, Figure 2 As shown, the present invention provides a safe and reliable multi-hop ad hoc wireless communication system in a substation, comprising: A neighbor set determination module 201, which is used to determine the neighbor set of each node according to the communication range of the node in the substation; A first jump module 202, which is used to calculate the signal-to-noise ratio from the start node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the first jump node; The second jump module 203 is used to calculate the signal-to-noise ratio from the first jump node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the second jump node, and repeat this step until the Kth jump node is obtained; A graph network data construction module 204, which is used to generate a search range with the Euclidean distance between the start node and the end node as the diameter, and construct graph network data according to the nodes in the search range; A first adjacency matrix generating module 205, which is used to input the graph network data into the neural network model and output a first adjacency matrix; The first adjacency matrix sending module 206 is used to send the first adjacency matrix to the Kth jump node to complete the communication.

[0037] In one embodiment of the present invention, the present invention provides a readable storage medium storing non-temporary computer-readable instructions. When the non-temporary computer-readable instructions are executed by a computer, the steps of the above-mentioned safe and reliable multi-hop self-organizing network wireless communication method in a substation are executed.

[0038] like Figure 3As shown, 10 jump communications are completed by calculating the signal-to-noise ratio between nodes, the neural network model provided by the present invention, and the ant colony algorithm respectively. The Euclidean distance between the starting node and the ending node of the jump communication is 1000m, the size of the data packet sent by the jump communication is 1500 bytes, and the maximum transmission rate is 100Mbps. It is found through observation that the time consumed by the neural network model provided by the present invention to complete the jump communication is close to the time consumed by the ant colony algorithm to complete the jump communication.

[0039] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A safe and reliable multi-hop ad hoc wireless communication method in a substation, characterized in that: The following steps are involved: Step S101, determining a neighbor set of each node according to the communication range of the nodes in the substation; Step S102, calculating the signal-to-noise ratio from the start node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the first jump node; Step S103, calculating the signal-to-noise ratio from the first jump node to each node in its neighbor set, and selecting the node with the largest signal-to-noise ratio as the second jump node, and repeating this step until the Kth jump node is obtained; Where K is a custom parameter; Step S104, generating a search range with the Euclidean distance between the start node and the end node as the diameter, and constructing graph network data according to the nodes in the search range; The graph network data G is represented as: G(V, E), where V represents the set of vertices in the graph network data G, and E represents the set of edges between vertices in the graph network data G; The i-th vertex is mapped to the i-th node, where 1≤i≤N, and N represents the number of nodes in the search range; The initial features of a vertex are represented by the attributes of the node to which it is mapped; Step S105, inputting the graph network data into the neural network model, and outputting a first adjacency matrix; The first adjacency matrix includes N rows and N columns, and the element values ​​of the first adjacency matrix are represented by 0 or 1, that is, the element value of the mth row and nth column is 1, which indicates that the mth node jumps to the nth node, otherwise, it indicates that the mth node does not jump to the nth node, wherein 1≤m≤N, 1≤n≤N; Step S106: Send the first adjacency matrix to the Kth jump node to complete the communication.

2. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 1, characterized in that: The signal-to-noise ratio from the i-th node to the j-th node The calculation formula include: ； ； ； ； in represents the useful signal power received by the jth node, represents the noise signal power received by the jth node, represents the signal transmission power of the i-th node, and They represent the channel fading factor and Euclidean distance from the i-th node to the j-th node, respectively. Temp represents the absolute temperature in Kelvin. represents the bandwidth of the jth node, provided by the device manufacturer, in Hertz, where , c represents the speed of light, f represents the carrier frequency, and k represents the Boltzmann constant.

3. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 1, characterized in that: The attributes of the node include: received signal strength, maximum transmission rate, packet loss rate, memory size and link quality indication, and the initial features of the corresponding vertex are obtained by normalizing the node attributes.

4. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 1, characterized in that: Calculate the correlation coefficient between each node in the search range and all nodes in its neighbor set, and when the correlation coefficient is greater than or equal to the set threshold, build an edge connection between the corresponding two vertices, where the set threshold is a custom parameter; The correlation coefficient between the i-th node and the j-th node The calculation formula is as follows: ； Where Y represents the number of dimensions of the initial features of the vertex, and Respectively represent the average values ​​of the initial features of the vertices corresponding to the i-th node and the j-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the i-th node, Represents the y-th dimension value of the initial feature of the vertex corresponding to the j-th node.

5. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 1, characterized in that: The neural network model includes: a first hidden layer, a second hidden layer and a third hidden layer; The first hidden layer is used to convert the initial features of each vertex of the graph network data into a matrix representation; The calculation formula for the first hidden layer is as follows: ; in represents the matrix representation of the i-th vertex, represents the initial feature of the i-th vertex, and W represents the weight parameter; The second hidden layer extracts features from the matrix representation of each vertex through three convolution kernels of different sizes to obtain three feature maps of different sizes, and then expands the three feature maps into vector representations and concatenates them to obtain a combined vector. The sizes of the three convolution kernels are 1×1, 3×3, and 5×5, respectively, and the step sizes of the three convolution kernels are all 1. The third hidden layer inputs the graph network data and outputs the first adjacency matrix.

6. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 5, characterized in that: The calculation formula for the third hidden layer includes: ； ； ； Where S represents the first adjacency matrix output by the third hidden layer, represents the set of vertices that are connected to the i-th vertex by edges. express The number of elements in , and Respectively represent the combined vectors of the i-th vertex and the j-th vertex, represents the update vector of the ith vertex, represents the association coefficient between the i-th vertex and the j-th vertex, and Represent the first weight parameter and the second weight parameter respectively, MLP represents a multi-layer perceptron, Indicates stacking the update vectors of N vertices, concat indicates concatenation, T indicates transposition, sigmoid indicates sigmoid activation function, and F indicates rounding up element values ​​greater than or equal to 0.5 to 1 and rounding down element values ​​less than 0.5 to 0.

7. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 1, characterized in that: According to step S101 to step S104, sample data of training samples for training the neural network model are obtained, and the attributes of all nodes in the substation are collected again after a preset time period. The transmission path is generated by the ant colony algorithm, and the transmission path is converted into a second adjacency matrix representation as a sample label of the training sample for training the neural network model, wherein the transmission path is represented by a vector with N dimensions, and the element value of the vector is represented by 0 or 1. The i-th dimension value is 1, which means that it passes through the i-th node, otherwise it does not pass through the i-th node, and the preset time period is a custom parameter.

8. A safe and reliable multi-hop ad hoc wireless communication method in a substation according to claim 7, characterized in that: Specify the difference between the first adjacency matrix and the second adjacency matrix output by the neural network model at each iteration as the loss function until the maximum number of iterations is reached, where the maximum number of iterations is a custom parameter.

9. A safe and reliable multi-hop ad hoc wireless communication system in a substation, characterized in that: Executing a safe and reliable multi-hop ad hoc wireless communication method in a substation as claimed in any one of claims 1 to 8, comprising: A neighbor set determination module, which is used to determine the neighbor set of each node according to the communication range of the node in the substation; The first jump module is used to calculate the signal-to-noise ratio from the starting node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the first jump node; The second jump module is used to calculate the signal-to-noise ratio from the first jump node to each node in its neighbor set, and select the node with the largest signal-to-noise ratio as the second jump node, and repeat this step until the Kth jump node is obtained; A graph network data construction module, which is used to generate a search range with the Euclidean distance between the start node and the end node as the diameter, and construct graph network data according to the nodes in the search range; A first adjacency matrix generation module, which is used to input the graph network data into the neural network model and output a first adjacency matrix; The first adjacency matrix sending module is used to send the first adjacency matrix to the Kth jump node to complete the communication.

10. A readable storage medium, characterized in that: It stores non-temporary computer-readable instructions. When the non-temporary computer-readable instructions are executed by a computer, a safe and reliable multi-hop ad hoc wireless communication method in a substation as described in any one of claims 1 to 8 is executed.

Images