A method and system for active defense of power network in an open and integrated network environment

Abstract

The present invention relates to the field of network security technology, and in particular to a method and system for active defense of a power network in an open and converged network environment. The method comprises identifying electromagnetic field intensity gradient change zones based on electromagnetic field distribution data between a plurality of valve towers in a UHV converter station valve hall, generating an electromagnetic interference relationship topology map based on the electromagnetic field coupling strength between each valve tower group in the electromagnetic field intensity gradient change zone, and obtaining a co-evolutionary relationship between the port link quality and the electromagnetic field topology structure in combination with the port link quality data of communication equipment near the electromagnetic field intensity gradient change zone; analyzing the potential impact of the dynamic migration of the electromagnetic field intensity gradient change zone on communication security based on the co-evolutionary relationship, and obtaining a communication security risk prediction result, so as to generate an optimal power network protection strategy through a reinforcement learning algorithm. The present invention realizes active defense of the power network in an open and converged environment by monitoring the electromagnetic field distribution in the valve hall of the UHV converter station and analyzing the impact of the dynamic migration of the electromagnetic field intensity gradient change zone on communication security.

Description

Technical Field

[0001] The present invention relates to the field of network security technology, and in particular to a method and system for active defense of a power network in an open and integrated network environment. Background Art

[0002] In an open and integrated network environment, the stable operation of the power network faces unprecedented challenges, and key power facilities such as ultra-high voltage converter stations are also facing more complex electromagnetic interference and network security threats. This is especially true in the valve hall of the ultra-high voltage converter station, a key area. The electromagnetic field distribution inside the valve hall is complex, and the electromagnetic field coupling between multiple groups of valve towers not only has variable intensity, but also its spatial distribution shows significant dynamic migration characteristics over time. This dynamic migration causes the position of the electromagnetic field intensity gradient zone to change, seriously affecting the communication link quality of the industrial control equipment in the valve hall. There is a spatiotemporal correlation between the link quality of the network port and the topological structure of the electromagnetic field. The two show complex dynamic behaviors of mutual influence and coordinated evolution, forming a dynamically balanced system.

[0003] However, this dynamic change in the electromagnetic field often leads to a sharp drop in the link signal-to-noise ratio, which in turn causes a significant increase in communication delay and packet loss rate. In extreme cases, it may even lead to the interruption of the communication link, posing a serious threat to the stable operation of the power network. At the same time, the fluctuation of link quality does not exist in isolation. It will produce feedback disturbances on the distribution of the electromagnetic field, further exacerbating the dynamic correlation and evolutionary complexity between the electromagnetic field and the link. The current power network faces many difficulties in responding to this challenge. On the one hand, it is extremely difficult to obtain electromagnetic field measurement data, and there is a lack of in-depth understanding of the coordinated evolution of the electromagnetic field and link quality. On the other hand, the real-time perception accuracy of link quality also needs to be improved to more accurately reflect the impact of electromagnetic field changes on communication links. Due to these two limitations, existing active defense mechanisms often lack the necessary trigger criteria and find it difficult to accurately identify security threats caused by electromagnetic distortion.

[0004] Therefore, how to break through the bottleneck of electromagnetic and link collaborative perception in an open and integrated network environment and deeply explore the evolution laws contained in cross-domain data has become a key issue that needs to be urgently solved in the current field of active defense of power networks to ensure the stable operation of power networks. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a method and system for active defense of power network in an open and integrated network environment.

[0006] In a first aspect, the present invention provides a method for active defense of a power network in an open converged network environment, the method comprising the following steps:

[0007] In an open and integrated network environment, the electromagnetic field spatial intensity gradient is analyzed based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of an ultra-high voltage converter station, and the electromagnetic field intensity gradient change area is identified.

[0008] According to the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, the spatial propagation attenuation characteristics of the electromagnetic field are analyzed to generate an electromagnetic interference relationship topology map;

[0009] Determining the migration direction of the electromagnetic field intensity gradient change area, and collecting port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area;

[0010] Acquire a co-evolution relationship between port link quality and electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map;

[0011] Based on the co-evolutionary relationship between port link quality and electromagnetic field topology, the potential impact of dynamic migration of electromagnetic field intensity gradient zones on communication security is analyzed, and communication security risk prediction results are obtained.

[0012] Based on the communication security risk prediction results, an optimal power network protection strategy is generated through a reinforcement learning algorithm.

[0013] In a further embodiment, the step of analyzing the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the ultra-high voltage converter station to identify the electromagnetic field intensity gradient change area includes:

[0014] The electromagnetic field distribution data between several groups of valve towers collected by the electromagnetic field sensor array in the valve hall of the UHV converter station are divided into different monitoring areas to obtain the electromagnetic field distribution data of each monitoring area;

[0015] According to the electromagnetic field distribution data between adjacent monitoring areas, the electromagnetic field intensity difference between different monitoring areas is obtained by using spatial divergence calculation;

[0016] Dynamically analyzing the electromagnetic field intensity difference using a sliding time window to calculate the gradient change rate of the electromagnetic field intensity between regions;

[0017] The monitoring area where the rate of change of the electromagnetic field intensity gradient between the areas exceeds a preset electromagnetic field intensity gradient change threshold range is determined as an electromagnetic field intensity gradient change area.

[0018] In a further embodiment, the step of analyzing the spatial propagation attenuation characteristics of the electromagnetic field according to the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient region to generate the electromagnetic interference relationship topology map includes:

[0019] A vector electromagnetic field model of the valve tower array is constructed based on Maxwell's equations, and the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient region is calculated according to the vector electromagnetic field model;

[0020] The shielding strength parameter is introduced and the spatial attenuation coefficient of the electromagnetic field between each group of valve towers is calculated according to the electromagnetic field coupling strength.

[0021] According to the spatial attenuation coefficient, an exponential attenuation function is used to fit the attenuation of the electromagnetic field intensity at different propagation distances to obtain an electromagnetic field propagation attenuation characteristic curve;

[0022] The electromagnetic wave propagation path loss is calculated based on the electromagnetic field propagation attenuation characteristic curve, and the electromagnetic wave propagation path loss is used as a weight to search for the shortest propagation path between each path node using the Dijkstra algorithm.

[0023] The shortest propagation path and electromagnetic field distribution data are analyzed using a graph neural network to calculate the topological correlation between each group of valve towers, and a topological map of the electromagnetic interference relationship between the valve towers is constructed based on the topological correlation.

[0024] In a further embodiment, the step of determining the migration direction of the electromagnetic field intensity gradient region comprises:

[0025] Based on the electromagnetic field distribution data, a sliding time window is used to calculate the field intensity mean of the electromagnetic field intensity gradient change area in each time window to obtain a field intensity mean sequence of the electromagnetic field intensity gradient change area;

[0026] Calculating the standard deviation of the field intensity in each time window based on the field intensity mean value sequence of the electromagnetic field intensity gradient region to obtain a standard deviation time series;

[0027] Performing wavelet analysis on the standard deviation time series to extract characteristic vectors of electromagnetic field intensity changes;

[0028] Based on the electromagnetic field intensity change characteristic vector, a time series analysis method is used to model and predict the electromagnetic field intensity change trend to generate an electromagnetic field intensity change trend matrix;

[0029] A Kalman filter is used to perform real-time estimation on the electromagnetic field intensity variation trend matrix to determine the migration direction of the electromagnetic field intensity gradient variation zone.

[0030] In a further embodiment, the step of collecting port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area includes:

[0031] Based on the migration direction of the electromagnetic field intensity gradient change area, the port data packet transmission rate between the communication devices near the electromagnetic field intensity gradient change area is collected;

[0032] Calculate the port link bandwidth utilization rate based on the port data packet transmission rate and the port physical bandwidth;

[0033] According to the port link bandwidth utilization and the pre-acquired link quality index, the port link quality data between the communication devices near the electromagnetic field intensity gradient change area is obtained.

[0034] In a further embodiment, the step of obtaining the co-evolution relationship between the port link quality and the electromagnetic field topology structure based on the port link quality data and the electromagnetic interference relationship topology map includes:

[0035] Analyzing the relationship topology graph of the port link quality data and the electromagnetic interference using a graph mining method to extract time-varying feature sequences of the relationship topology graph of the port link quality data and the electromagnetic interference at different time points;

[0036] The time-varying characteristic sequence is modeled and analyzed using the differential autoregressive moving average method to obtain a topological evolution trend vector;

[0037] Based on the topology evolution trend vector, a dynamic mode decomposition algorithm is used to identify the co-evolution relationship between the port link quality and the electromagnetic field topology structure.

[0038] In a further embodiment, the step of analyzing the potential impact of dynamic migration of electromagnetic field intensity gradient zones on communication security based on the co-evolution relationship between port link quality and electromagnetic field topology to obtain a communication security risk prediction result includes:

[0039] A co-evolution state transition matrix is ​​constructed based on the co-evolution relationship between the port link quality and the electromagnetic field topology, and a long short-term memory network is used to learn and predict the co-evolution state transition matrix to obtain the bandwidth limitation probability and packet loss rate;

[0040] Using the Markov method to perform state prediction on the bandwidth limitation probability and the packet loss rate to obtain a communication link interruption probability distribution;

[0041] According to the characteristic parameters of the electromagnetic field intensity gradient change area, the dynamic migration of the electromagnetic field intensity gradient change area is analyzed using a spatiotemporal correlation analysis method to construct a spatial position determination matrix;

[0042] Calculating the degree of overlap between the communication link and the transition zone migration path according to the communication link interruption probability distribution and the spatial position determination matrix;

[0043] If the degree of overlap exceeds a preset overlap threshold, the probability of the communication link being interfered with is calculated based on the degree of overlap, and a communication security risk prediction result is generated based on the probability of the communication link being interfered with.

[0044] In a further embodiment, the step of analyzing the dynamic migration of the electromagnetic field intensity gradient change region using a spatiotemporal correlation analysis method based on the characteristic parameters of the electromagnetic field intensity gradient change region and constructing a spatial position determination matrix includes:

[0045] Based on the characteristic parameters of the electromagnetic field intensity gradient change region, Gaussian process regression is used to analyze the spatial distribution state of the electromagnetic field intensity gradient change region at different time points to obtain a dynamic migration trajectory matrix of the electromagnetic field intensity gradient change region; the characteristic parameters of the electromagnetic field intensity gradient change region include the intensity gradient, spatial distribution range and migration rate of the electromagnetic field intensity gradient change region;

[0046] Determine the time point sequence of the magnetic field intensity gradient change region and its position information at different time points based on the dynamic migration trajectory matrix;

[0047] Using the spatiotemporal correlation analysis method, the time sequence of changes in the electromagnetic field intensity gradient change area and its location information at different time points are analyzed to obtain the device point density and link connectivity between communication devices near the electromagnetic field intensity gradient change area;

[0048] A spatial position determination matrix is ​​constructed using a weighted algorithm according to the device point density and the link connectivity.

[0049] In a further embodiment, the step of generating an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction result includes:

[0050] Combining the power network operation state and the communication security risk prediction result into a multidimensional state vector, and using the multidimensional state vector as the state space in the reinforcement learning algorithm;

[0051] A protection strategy is defined as an action space according to the protection requirements of the power network, and each action in the action space is encoded to form a discrete action set;

[0052] Initialize the Q-value table of the reinforcement learning algorithm. In the power network simulation environment under the open converged network environment, the control agent selects an action from the action space based on the current state. It iteratively updates the Q-value table based on the reward obtained from executing the action. Repeat the above process until the Q-value converges.

[0053] According to the converged Q-value table, the action with the largest Q-value is selected as the optimal protection strategy in the current state.

[0054] In a second aspect, the present invention provides an active defense system for a power network in an open and integrated network environment, the system comprising:

[0055] The gradient change identification module is used to analyze the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the UHV converter station in an open and integrated network environment, and identify the electromagnetic field intensity gradient change area;

[0056] The electromagnetic analysis module is used to analyze the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, and generate an electromagnetic interference relationship topology map;

[0057] A migration analysis module is used to determine the migration direction of the electromagnetic field intensity gradient change area and collect port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area;

[0058] A co-evolution module, configured to obtain a co-evolution relationship between port link quality and electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map;

[0059] The risk prediction module is used to analyze the potential impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtain the communication security risk prediction results;

[0060] A strategy generation module is used to generate an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction results.

[0061] The present invention provides a method and system for active defense of an electric power network in an open and integrated network environment. The method analyzes the spatial intensity gradient of the electromagnetic field based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of an ultra-high voltage converter station, and identifies the electromagnetic field intensity gradient zone; analyzes the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient zone, and generates an electromagnetic interference relationship topology map; collects port link quality data between communication equipment near the electromagnetic field intensity gradient zone based on the migration direction of the electromagnetic field intensity gradient zone; obtains the co-evolution relationship between the port link quality and the electromagnetic field topology structure based on the port link quality data and the electromagnetic interference relationship topology map; analyzes the potential impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtains a communication security risk prediction result; and generates an optimal electric power network protection strategy based on the communication security risk prediction result through a reinforcement learning algorithm. Compared with the existing technology, this method accurately analyzes the impact of the dynamic migration of electromagnetic field intensity gradient zones on communication security by monitoring the electromagnetic field distribution in the valve hall of the ultra-high voltage converter station, and combines the electromagnetic interference relationship topology map and co-evolution relationship to achieve active defense of the power network in an open and integrated environment, effectively reducing the risk of communication failures caused by electromagnetic interference, and ensuring the communication security and stable operation of the power network in a complex electromagnetic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of a method for active defense of a power network in an open and integrated network environment provided by an embodiment of the present invention;

[0063] Figure 2 This is a block diagram of an active defense system for a power network in an open and integrated network environment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following describes the embodiments of the present invention in detail with reference to the accompanying drawings. The embodiments are provided for illustrative purposes only and are not to be construed as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of protection of the present invention. Many changes may be made to the present invention without departing from the spirit and scope of the present invention.

[0065] refer to Figure 1 , the embodiment of the present invention provides a method for active defense of power network in an open and integrated network environment, such as Figure 1 As shown, the method includes the following steps:

[0066] S1. In an open and integrated network environment, the electromagnetic field spatial intensity gradient is analyzed based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the UHV converter station, and the electromagnetic field intensity gradient change area is identified.

[0067] In this embodiment, the step of analyzing the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the ultra-high voltage converter station to identify the electromagnetic field intensity gradient change area includes:

[0068] The electromagnetic field distribution data between several groups of valve towers collected by the electromagnetic field sensor array in the valve hall of the UHV converter station are divided into different monitoring areas to obtain the electromagnetic field distribution data of each monitoring area;

[0069] According to the electromagnetic field distribution data between adjacent monitoring areas, the electromagnetic field intensity difference between different monitoring areas is obtained by using spatial divergence calculation;

[0070] Dynamically analyzing the electromagnetic field intensity difference using a sliding time window to calculate the gradient change rate of the electromagnetic field intensity between regions;

[0071] The monitoring area where the rate of change of the electromagnetic field intensity gradient between the areas exceeds a preset electromagnetic field intensity gradient change threshold range is determined as an electromagnetic field intensity gradient change area.

[0072] Specifically, this embodiment arranges the electromagnetic field sensor array in a grid-like manner evenly in the valve hall of the UHV converter station, ensuring that the distance between adjacent electromagnetic field sensors is 3 meters. This embodiment installs a three-axis electromagnetic field sensor at each monitoring point. This layout can fully and evenly cover the space in the valve hall to collect electromagnetic field distribution data in the three directions of X, Y, and Z in real time to ensure the integrity of the collected data. This embodiment uses a three-axis electromagnetic field sensor to monitor and collect the electromagnetic field distribution data of its location in real time. The sampling frequency is set to 100 Hz, and the electromagnetic field sensor monitoring time span is 24 hours to obtain sufficient data for subsequent analysis. After the electromagnetic field sensor array is deployed, this embodiment starts to collect electromagnetic field distribution data in real time. The data collection system The system groups and stores the collected electromagnetic field distribution data according to the monitoring areas (such as around each valve tower, the center of the valve hall, etc.) to form a time series database for subsequent analysis. Then, this embodiment extracts the electromagnetic field distribution data of adjacent monitoring areas from the time series database, and uses the spatial divergence calculation method to analyze the electromagnetic field distribution data between adjacent monitoring areas. For the data at each time point, the electromagnetic field intensity data of the adjacent monitoring areas are spatially diverged to obtain the electromagnetic field intensity difference between the adjacent areas, so as to quantify the change of electromagnetic field intensity between different monitoring areas. For example, when the electromagnetic field intensity of monitoring area A is 300 milliteslas, if the electromagnetic field intensity of adjacent area B is 250 milliteslas, the difference between them is 50 milliteslas.

[0073] Next, this embodiment sets the length of the sliding time window to 10 minutes. In the time series database, 10 minutes is used as a time segment. The sliding time window method is used to perform dynamic analysis on the electromagnetic field intensity difference. In each sliding time window, the average change rate of the electromagnetic field intensity difference between adjacent time points is calculated to obtain the gradient change rate of the electromagnetic field intensity between regions in each time window to evaluate the dynamic change of the electromagnetic field intensity. For example, if the electromagnetic field intensity difference between adjacent regions increases from 50 millitesla to 70 millitesla within a sliding time window of 10 minutes, the change rate is 20 millitesla / 10 minutes. Finally, this embodiment pre-sets the electromagnetic field intensity gradient change threshold range based on actual engineering experience and safety standards for electromagnetic field intensity changes, and screens out monitoring areas with significant electromagnetic field intensity gradient changes based on the preset electromagnetic field intensity gradient change threshold range. The calculated electromagnetic field intensity gradient change rate between regions is compared with the preset threshold range. If there is a monitoring area where the electromagnetic field intensity gradient change rate exceeds the preset electromagnetic field intensity gradient change threshold range, the monitoring area is determined to be an electromagnetic field intensity gradient change area, thereby effectively identifying the electromagnetic field intensity gradient change area by accurately analyzing the electromagnetic field spatial intensity gradient.

[0074] S2. Analyze the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, and generate an electromagnetic interference relationship topology map.

[0075] In this embodiment, the step of analyzing the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient region to generate the electromagnetic interference relationship topology map includes:

[0076] A vector electromagnetic field model of the valve tower array is constructed based on Maxwell's equations, and the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient region is calculated according to the vector electromagnetic field model;

[0077] The shielding strength parameter is introduced and the spatial attenuation coefficient of the electromagnetic field between each group of valve towers is calculated according to the electromagnetic field coupling strength.

[0078] According to the spatial attenuation coefficient, an exponential attenuation function is used to fit the attenuation of the electromagnetic field intensity at different propagation distances to obtain an electromagnetic field propagation attenuation characteristic curve;

[0079] The electromagnetic wave propagation path loss is calculated based on the electromagnetic field propagation attenuation characteristic curve, and the electromagnetic wave propagation path loss is used as a weight to search for the shortest propagation path between each path node using the Dijkstra algorithm.

[0080] The shortest propagation path and electromagnetic field distribution data are analyzed using a graph neural network to calculate the topological correlation between each group of valve towers, and a topological map of the electromagnetic interference relationship between the valve towers is constructed based on the topological correlation.

[0081] Specifically, this embodiment is based on Maxwell's equations and combines the specific structural parameters of the valve tower array in the valve hall of the ultra-high voltage converter station (such as the size, shape, material properties and mutual arrangement of the valve towers) to establish a partial differential equation describing the electromagnetic field around the valve tower array, and uses numerical calculation methods such as the finite element method (FEM) or the finite difference method (FDM) to solve the partial differential equation to obtain the vector electromagnetic field distribution of the valve tower array. According to the vector electromagnetic field distribution, a vector electromagnetic field model of the valve tower array is constructed. The vector electromagnetic field model accurately describes the spatial distribution of the electromagnetic field, such as the vector characteristics of the electric field and the magnetic field around the valve tower array. On the basis of the vector electromagnetic field model, this embodiment uses electromagnetic field theory to calculate the electromagnetic field between each group of valve towers in the electromagnetic field intensity gradient zone. Field coupling strength. For example, this embodiment can calculate the magnitude of the electric field or magnetic field generated by the electromagnetic field emitted from a single valve tower at the adjacent valve tower, as well as the phase relationship between the two fields, so as to determine the coupling strength between them. Then, considering the shielding effect between the valve towers, the shielding strength parameter is defined according to the conductivity and magnetism of the valve tower material. The shielding strength parameter can characterize the degree to which the electromagnetic field is weakened due to the shielding effect during the propagation process. By combining the electromagnetic field coupling strength and the shielding strength parameter, the electromagnetic field propagation theory is used to calculate the spatial attenuation coefficient of the electromagnetic field between each group of valve towers. According to the spatial attenuation coefficient, the exponential attenuation function is used to fit the attenuation of the electromagnetic field intensity at different propagation distances to obtain the electromagnetic field propagation attenuation characteristic curve. The exponential attenuation function is expressed as follows:

[0082]

[0083] Where, is the electromagnetic field strength when the propagation distance is d; is the initial electromagnetic field strength; is the exponential attenuation coefficient, and its value is equal to the spatial attenuation coefficient.

[0084] Then, this embodiment calculates the electromagnetic wave propagation path loss between the electromagnetic wave propagating from one valve tower to another valve tower based on the electromagnetic field propagation attenuation characteristic curve. This embodiment can determine the electromagnetic wave propagation path loss by integrating the attenuation within a specific distance range of the electromagnetic field propagation attenuation characteristic curve or directly using a fitting function to calculate the attenuation value at the corresponding distance. Then, the valve tower array is used as a node in the graph structure, the propagation path is used as an edge, and the electromagnetic wave propagation path loss is used as the edge weight. The Dijkstra algorithm is used to search for the shortest propagation path from the source node to the target node on the graph structure.

[0085] Finally, the shortest propagation path and electromagnetic field distribution data that have been searched are preprocessed. For the shortest propagation path data, this embodiment converts it into a graph structure representation, where the nodes represent valve towers, the edges represent the shortest propagation paths between valve towers, and the edge weights are path cost values ​​determined based on electromagnetic wave propagation path losses, etc.; the electromagnetic field distribution data includes numerical information such as the electromagnetic field intensity and coupling intensity at each valve tower position. This embodiment integrates this data as the input of the graph neural network. This embodiment uses a graph neural network model such as a graph convolutional network (GCN) including an attention mechanism to train the preprocessed data and learn the topological correlation between the valve towers. The correlation reflects the closeness between the valve towers in electromagnetic field propagation and distribution. The larger the value, the stronger the correlation. The specific process is as follows:

[0086] In the graph neural network, this embodiment first extracts the features of the node (valve tower). The input node features include electromagnetic field strength, coupling strength and other information in the electromagnetic field distribution data. The graph neural network aggregates the feature information of adjacent nodes layer by layer through the convolution operation of these features to generate a new node embedding representation. This process can help the network learn the complex topological relationship between nodes and the association between electromagnetic field distribution characteristics. For example, the first layer GCN can calculate the initial embedding vector of each node and update the node representation by aggregating the features of its neighboring nodes and its own features. In the calculation process of the graph neural network, the weight of the edge can be dynamically updated according to the feature embedding of the node, and an attention coefficient is calculated for each edge through the attention mechanism. The coefficient represents the degree of influence of the source node on the target node feature. This method of dynamically updating the edge weight can better capture the correlation and topology between nodes. The characteristics of the flutter structure are taken into account, so as to calculate a more accurate topological correlation. After calculation by the multi-layer graph neural network, the final embedding representation of each node is obtained. Based on these embedding vectors, the topological correlation between each group of valve towers (i.e., each pair of nodes) is calculated. Specifically, this embodiment can use a similarity measurement method such as cosine similarity to measure the similarity between the embedding vectors of different nodes, which is used as a quantitative indicator of the topological correlation. This embodiment constructs an electromagnetic interference relationship topological map between valve towers based on the calculated topological correlation. In the topological map, each node represents a valve tower, and the edge represents the electromagnetic interference relationship between the valve towers. The weight of the edge is the value of the corresponding topological correlation. It should be noted that this embodiment needs to normalize the value of the topological correlation to the interval [0, 1] as the weight of the edge to accurately reflect the strength of the electromagnetic interference relationship, so as to facilitate in-depth analysis of the electromagnetic environment in the valve hall of the ultra-high voltage converter station.

[0087] S3. Determine the migration direction of the electromagnetic field intensity gradient change area, and collect port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area.

[0088] In this embodiment, the step of determining the migration direction of the electromagnetic field intensity gradient change region includes:

[0089] Based on the electromagnetic field distribution data, a sliding time window is used to calculate the field intensity mean of the electromagnetic field intensity gradient change area in each time window to obtain a field intensity mean sequence of the electromagnetic field intensity gradient change area;

[0090] Calculating the standard deviation of the field intensity in each time window based on the field intensity mean value sequence of the electromagnetic field intensity gradient region to obtain a standard deviation time series;

[0091] Performing wavelet analysis on the standard deviation time series to extract characteristic vectors of electromagnetic field intensity changes;

[0092] Based on the electromagnetic field intensity change characteristic vector, a time series analysis method is used to model and predict the electromagnetic field intensity change trend to generate an electromagnetic field intensity change trend matrix;

[0093] A Kalman filter is used to perform real-time estimation on the electromagnetic field intensity variation trend matrix to determine the migration direction of the electromagnetic field intensity gradient variation zone.

[0094] Specifically, this embodiment sets the length of the sliding time window based on the electromagnetic field distribution data. The length of the sliding time window can be adjusted according to actual needs, such as being set to 1 second, 5 seconds or 10 seconds. In each time window, the electromagnetic field intensity data of all monitoring points in the electromagnetic field intensity gradient change area are averaged to obtain the field intensity mean of the electromagnetic field intensity gradient change area in the time window. The field intensity means corresponding to all time windows are arranged in chronological order to form a field intensity mean sequence of the electromagnetic field intensity gradient change area. For each time window in the field intensity mean sequence of the electromagnetic field intensity gradient change area, the electromagnetic field intensity of all monitoring points in the time window is calculated. The standard deviation of the data is used to measure the degree of fluctuation of the electromagnetic field intensity in the gradient region within the time window. The standard deviation of each time window is arranged in chronological order to form a standard deviation time series. The standard deviation time series is then subjected to wavelet transform. The wavelet transform can decompose the time series into components of different frequencies, thereby extracting characteristic information on different time scales. In this embodiment, the characteristic vector of the change in electromagnetic field intensity is extracted by analyzing the coefficients of each layer after wavelet decomposition. For example, the Daubechies wavelet can be used to decompose the standard deviation time series into three layers, and the low-frequency and high-frequency components of each layer can be extracted as the electromagnetic field intensity. The embodiment selects a time series analysis method based on the time series characteristics of the electromagnetic field intensity change characteristic vectors, and uses the historical electromagnetic field intensity change characteristic vectors as input to train a time series analysis model. The trained time series analysis model is used to predict the trend of electromagnetic field intensity changes in the future. The prediction results are organized into an electromagnetic field intensity change trend matrix, where each row of the matrix represents a predicted value at a time point. At the same time, initial parameters of the Kalman filter are set, such as setting the state vector to the electromagnetic field intensity value and the state transition matrix to the unit matrix. The predicted values ​​of the electromagnetic field intensity change trend matrix are input as observation values ​​into the Kalman filter for real-time estimation. The Kalman filter is recursively updated based on the prediction model and the observation model to estimate the state of the electromagnetic field intensity gradient change area in real time. The migration direction of the electromagnetic field intensity gradient change area is determined based on the estimation result of the Kalman filter. For example, if the position of the electromagnetic field intensity gradient change area is estimated to move in a certain direction over time, the direction is the migration direction. Port link quality data between communication devices near the electromagnetic field intensity gradient change area is collected based on the migration direction of the electromagnetic field intensity gradient change area. The specific steps include:

[0095] Based on the migration direction of the electromagnetic field intensity gradient change area, the port data packet transmission rate between the communication devices near the electromagnetic field intensity gradient change area is collected;

[0096] Calculate the port link bandwidth utilization rate based on the port data packet transmission rate and the port physical bandwidth;

[0097] According to the port link bandwidth utilization and the pre-acquired link quality index, the port link quality data between the communication devices near the electromagnetic field intensity gradient change area is obtained.

[0098] Specifically, this embodiment identifies, based on the migration direction of the determined electromagnetic field intensity gradient change zone, communication devices located near the migration direction and affected by the electromagnetic field, and uses the management interface of the communication device to collect port packet transmission rate data between these communication devices. The port packet transmission rate is divided by the physical bandwidth to obtain the port link bandwidth utilization. Finally, link quality indicators such as the bandwidth utilization threshold are set according to the requirements of the communication system. The port link bandwidth utilization and other link quality indicators are combined to form port link quality data between communication devices near the electromagnetic field intensity gradient change zone. By comprehensively considering multiple factors, a more comprehensive and accurate port link quality assessment result is obtained.

[0099] S4. Acquire a co-evolution relationship between port link quality and electromagnetic field topology structure based on the port link quality data and the electromagnetic interference relationship topology map.

[0100] In this embodiment, the step of obtaining the co-evolution relationship between the port link quality and the electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map includes:

[0101] Analyzing the relationship topology graph of the port link quality data and the electromagnetic interference using a graph mining method to extract time-varying feature sequences of the relationship topology graph of the port link quality data and the electromagnetic interference at different time points;

[0102] The time-varying characteristic sequence is modeled and analyzed using the differential autoregressive moving average method to obtain a topological evolution trend vector;

[0103] Based on the topology evolution trend vector, a dynamic mode decomposition algorithm is used to identify the co-evolution relationship between the port link quality and the electromagnetic field topology structure.

[0104] Specifically, this embodiment maps the port link quality data to the node attributes of the graph, where each node represents a port or device, and the attribute value is a link quality indicator; at the same time, the electromagnetic interference relationship topology graph is converted into a graph form, where the nodes represent devices and the edges represent the electromagnetic interference relationship between devices. The graph mining method is used to perform snapshot sampling of the graph at different time points to obtain a series of time-related graph snapshots, and features are extracted from each snapshot, such as the average link quality of the node, the average interference intensity of the edge, etc. These features are arranged in chronological order to form a time-varying feature sequence of the port link quality data and the electromagnetic interference relationship topology graph. These time-varying feature sequences record the dynamic changes of the port link quality and the electromagnetic field topology structure over time.

[0105] Then, for the extracted time-varying feature sequence, this embodiment selects the differential autoregressive moving average method for modeling and analysis. This embodiment performs a stationarity test on the time-varying feature sequence. If the sequence is not stationary, a differential operation is performed until a stationary sequence is obtained. Then, the order (p, d, q) of the ARIMA model is determined based on the autocorrelation function (ACF) and the partial autocorrelation function (PACF), where p is the autoregressive order, d is the differential order, and q is the moving average order. The ARIMA model is fitted using historical data to obtain parameter estimates of the model. This embodiment uses the trained ARIMA model to predict the time-varying feature sequence over a period of time in the future. The prediction results reflect the evolution trend of the port link quality and the electromagnetic field topology structure. These prediction results are arranged in chronological order to form a topology evolution trend vector. This vector represents the changing trend of the relationship between the port link quality and the electromagnetic interference over time, and includes a quantitative description of future topology changes.

[0106] Finally, this embodiment arranges the topology evolution trend vectors in chronological order to construct an input matrix for dynamic mode decomposition. Each column of the input matrix represents the topology evolution trend vector at a time point. This embodiment performs dynamic mode decomposition (DMD) on the topology evolution trend vectors to obtain a series of dynamic mode matrices and corresponding modal matrices. These dynamic mode matrices reflect the different characteristics and behaviors of the port link quality and the electromagnetic field topology during the evolution process. By analyzing the eigenvalues ​​and modal vectors of these dynamic modes, the co-evolutionary relationship between the port link quality and the electromagnetic field topology can be identified. For example, if the eigenvalue of a dynamic mode indicates a stable growth trend, and the corresponding modal vector shows that the port link quality indicator and certain characteristics of the electromagnetic field topology (such as the interference intensity between specific nodes and the bandwidth utilization of the corresponding link) change synchronously, then it can be determined that the port link quality and the electromagnetic field topology have a co-evolutionary relationship under this dynamic mode. By comprehensively analyzing all dynamic modes, a comprehensive understanding of the co-evolution between the two can be achieved, providing a basis for further optimizing the electromagnetic environment and communication system performance of the UHV converter station.

[0107] S5. Based on the co-evolution relationship between port link quality and electromagnetic field topology, the potential impact of dynamic migration of electromagnetic field intensity gradient zone on communication security is analyzed to obtain communication security risk prediction results.

[0108] In this embodiment, the step of analyzing the potential impact of dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure to obtain a communication security risk prediction result includes:

[0109] A co-evolution state transition matrix is ​​constructed based on the co-evolution relationship between the port link quality and the electromagnetic field topology, and a long short-term memory network is used to learn and predict the co-evolution state transition matrix to obtain the bandwidth limitation probability and packet loss rate;

[0110] Using the Markov method to perform state prediction on the bandwidth limitation probability and the packet loss rate to obtain a communication link interruption probability distribution;

[0111] According to the characteristic parameters of the electromagnetic field intensity gradient change area, the dynamic migration of the electromagnetic field intensity gradient change area is analyzed using a spatiotemporal correlation analysis method to construct a spatial position determination matrix;

[0112] Calculating the degree of overlap between the communication link and the transition zone migration path according to the communication link interruption probability distribution and the spatial position determination matrix;

[0113] If the degree of overlap exceeds a preset overlap threshold, the probability of the communication link being interfered with is calculated based on the degree of overlap, and a communication security risk prediction result is generated based on the probability of the communication link being interfered with.

[0114] Specifically, this embodiment determines the state space of the system based on the extracted co-evolutionary relationship between the port link quality and the electromagnetic field topology. Each state in the state space can be represented as a combined state, including key indicators of the port link quality (such as bandwidth utilization and packet loss rate) and characteristic parameters of the electromagnetic field topology (such as interference intensity between nodes and topological connection status). This embodiment analyzes historical data, calculates the transition probabilities between different states, and constructs a co-evolutionary state transition matrix. The elements of the co-evolutionary state transition matrix represent the probability of transitioning from one state to another. This embodiment uses the constructed co-evolutionary state transition matrix as input data for a long short-term memory (LSTM) network and performs preprocessing operations such as normalization before inputting it into the LSTM network. This embodiment uses the trained LSTM model to learn and predict the co-evolutionary state transition matrix, predicting the probability of bandwidth limitation and packet loss rate for a future period of time. The bandwidth limitation probability reflects the possibility of insufficient bandwidth of the communication link in the future, and the packet loss rate reflects the proportion of data packets that may be lost during future transmission.

[0115] This embodiment uses the Markov method to perform state prediction based on the bandwidth limitation probability and packet loss rate predicted by the LSTM network. Specifically, this embodiment uses the bandwidth limitation probability and packet loss rate as system state variables to construct a Markov chain model and calculate the transition probabilities between each state to obtain a state transition probability matrix. Based on the current bandwidth limitation probability, packet loss rate, and state transition probability matrix, the bandwidth limitation probability and packet loss rate are predicted at various future time points. Based on the predicted bandwidth limitation probability and packet loss rate, combined with the conditions for communication link interruption (such as link interruption when the bandwidth falls below a certain threshold or the packet loss rate exceeds a certain threshold), the communication link interruption probability distribution is calculated. If the bandwidth limitation probability is predicted to be high and the packet loss rate exceeds a certain threshold within a certain time period, the probability of communication link interruption will increase accordingly. By analyzing the bandwidth limitation probability and packet loss rate at different time points, the probability distribution of communication link interruption over the entire predicted time period is obtained.

[0116] Then, this embodiment uses a spatiotemporal correlation analysis method to analyze the dynamic migration law of the electromagnetic field intensity gradient change zone based on the characteristic parameters of the electromagnetic field intensity gradient change zone (such as intensity gradient, spatial distribution range and migration rate). The spatiotemporal correlation analysis method can consider the spatial and temporal variation law of the electromagnetic field intensity gradient change zone, as well as the spatial position relationship with the communication link. Then, based on the analysis results, a spatial position determination matrix is ​​constructed. The spatial position determination matrix is ​​used to determine the possible location of the electromagnetic field intensity gradient change zone in the future. The path of the communication link is planned according to the communication network topology structure, and the communication link path is compared with the spatial position determination matrix to calculate the weight of the communication link and the migration path of the electromagnetic field intensity gradient change zone. The degree of overlap, in this embodiment, the communication link interruption probability distribution can be multiplied element by element by the spatial position determination matrix, and then the multiplication result can be integrated to obtain an indicator that comprehensively reflects the degree of interference to the communication link during the migration of the gradient zone, that is, the degree of overlap. The higher the degree of overlap, the greater the possibility that the communication link will be subject to electromagnetic interference during the migration of the gradient zone. If the degree of overlap exceeds the preset overlap threshold, it is considered that the communication link may be interfered with by the electromagnetic field intensity gradient zone, and then the probability of the communication link being interfered with is obtained by normalizing the degree of overlap or using a probability model to calculate, and the communication security risk prediction result is generated according to the interference probability, including the risk level and the impact range.

[0117] In this embodiment, the step of analyzing the dynamic migration of the electromagnetic field intensity gradient change region using a spatiotemporal correlation analysis method based on the characteristic parameters of the electromagnetic field intensity gradient change region and constructing a spatial position determination matrix includes:

[0118] Based on the characteristic parameters of the electromagnetic field intensity gradient change region, Gaussian process regression is used to analyze the spatial distribution state of the electromagnetic field intensity gradient change region at different time points to obtain a dynamic migration trajectory matrix of the electromagnetic field intensity gradient change region; the characteristic parameters of the electromagnetic field intensity gradient change region include the intensity gradient, spatial distribution range and migration rate of the electromagnetic field intensity gradient change region;

[0119] Determine the time point sequence of the magnetic field intensity gradient change region and its position information at different time points based on the dynamic migration trajectory matrix;

[0120] Using the spatiotemporal correlation analysis method, the time sequence of changes in the electromagnetic field intensity gradient change area and its location information at different time points are analyzed to obtain the device point density and link connectivity between communication devices near the electromagnetic field intensity gradient change area;

[0121] A spatial position determination matrix is ​​constructed using a weighted algorithm according to the device point density and the link connectivity.

[0122] Specifically, this embodiment uses the Gaussian Process Regression (GPR) method to analyze the spatial distribution of characteristic parameters of the electromagnetic field intensity gradient region (such as intensity gradient, spatial distribution range, and migration rate) at different time points. GPR is a non-parametric Bayesian regression method that can handle uncertainty in high-dimensional space and can be used to analyze the spatiotemporal changes of electromagnetic fields. Specifically, this embodiment uses training data to fit a GPR model to obtain a spatial distribution prediction function for the electromagnetic field intensity gradient region. At each time point, this embodiment uses the prediction function to calculate the spatial distribution of the electromagnetic field intensity gradient region, constructs a dynamic migration trajectory matrix, and then traverses the dynamic migration trajectory matrix. By comparing the spatial distribution of the electromagnetic field intensity gradient region at different time points, the sequence of time points at which changes in the magnetic field intensity gradient region occur is determined. For example, when the position, shape, or size of the electromagnetic field intensity gradient region changes significantly between adjacent time points, the time point is recorded as the time point of change. At each change time point, the coordinates of the center point and boundary range of the gradient region are calculated as position information.

[0123] This embodiment uses the time sequence of changes in the electromagnetic field intensity gradient change area and its position information at different time points as input, and uses the time-space correlation analysis method to analyze the communication equipment near the electromagnetic field intensity gradient change area. The time-space correlation analysis method can comprehensively consider time and space factors to explore the correlation between the electromagnetic field intensity gradient change area and the communication equipment. At the same time, during the analysis process, the number of communication equipment per unit area near the gradient change area is calculated to obtain the device point density. At the same time, the number of communication links between the communication equipment in the gradient change area and the quality of the links (such as bandwidth, delay, etc.) are calculated to obtain the link connectivity. The link connectivity reflects the Regarding the connection tightness between communication devices, this embodiment sets corresponding weights based on the importance of device point density and link connectivity. Based on the calculated device point density and link connectivity, a suitable weighting algorithm is selected to construct a spatial position determination matrix. The elements in the matrix can be expressed as the degree to which the communication device is affected by the electromagnetic field intensity gradient zone in its spatial position. By comprehensively considering the device point density and link connectivity, a quantitative matrix that can reflect the spatial relationship between the communication device and the electromagnetic field intensity gradient zone is obtained. In order to unify the dimensions and compare the differences between different communication devices, this embodiment can standardize the determination matrix.

[0124] S6. Based on the communication security risk prediction results, generate an optimal power network protection strategy through a reinforcement learning algorithm.

[0125] In this embodiment, the step of generating an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction result includes:

[0126] Combining the power network operation state and the communication security risk prediction result into a multidimensional state vector, and using the multidimensional state vector as the state space in the reinforcement learning algorithm;

[0127] A protection strategy is defined as an action space according to the protection requirements of the power network, and each action in the action space is encoded to form a discrete action set;

[0128] Initialize the Q-value table of the reinforcement learning algorithm. In the power network simulation environment under the open converged network environment, the control agent selects an action from the action space based on the current state. It iteratively updates the Q-value table based on the reward obtained from executing the action. Repeat the above process until the Q-value converges.

[0129] According to the converged Q-value table, the action with the largest Q-value is selected as the optimal protection strategy in the current state.

[0130] Specifically, this embodiment collects the operating status of the power network, which may include operating parameters of power equipment (such as voltage, current, power, etc.), network topology, power flow distribution and other information. At the same time, the collected data is preprocessed, such as normalization and standardization, to ensure that data of different dimensions can be compared on the same scale. The processed power network operating status data and communication security risk prediction results are combined into a multidimensional state vector. The multidimensional state vector can comprehensively describe the operating status of the power network at a specific moment and the communication security risk situation it faces. The multidimensional state vector is used as the state space in the reinforcement learning algorithm. Each state point in the state space corresponds to the specific operating status and communication security risk situation of the power network at a certain moment, providing a decision-making basis for the agent, and defining a series of protection strategies according to the protection needs of the power network. The protection strategy can Each protection strategy in the action space is encoded to form a discrete action set, including adjusting voltage, current limiting, enabling firewalls, deploying intrusion detection systems, updating security patches, etc. The encoding can be digital encoding or other suitable encoding methods such as binary encoding and symbolic encoding. For example, when using digital encoding, this embodiment can use the number 1 to represent the voltage adjustment strategy, the number 2 to represent the firewall strategy, and so on. The formed discrete action set is used as the action space in the reinforcement learning algorithm, that is, the set of all possible actions that the intelligent agent can perform when making decisions. Then, this embodiment creates a Q-value table, which is used to record the expected reward obtained by the intelligent agent for performing each action in each state. Initially, all values ​​in the Q-value table can be set to 0 or a random value, indicating that in the initial state, the value evaluation of each state-action pair is the same.

[0131] This embodiment builds an electric power network simulation environment in an open and integrated network environment. The simulation environment can simulate the actual operation of the electric power network and can update and feedback the state of the electric power network according to the actions performed by the intelligent agent. This embodiment simulates the actual operation state of the electric power network and the communication security risk through the built electric power network simulation environment. In the simulation environment, the control intelligent agent selects an action to be executed from the action space according to the current multi-dimensional state vector. When selecting an action, this embodiment can use strategies such as the ε-greedy strategy to select the action of the intelligent agent. According to the change in the operation state of the electric power network and the degree of reduction in the communication security risk after the intelligent agent executes the action, the reward value obtained by the intelligent agent is calculated. The reward function is related to the operation state of the electric power network, the degree of reduction in the communication security risk and other objectives. The reward can be a positive number (indicating a reduction in security risk) or a negative number (indicating an increase in security risk or a decrease in the performance of the electric power network). For example, when the probability of interference in the communication link is reduced and the operating efficiency of the power equipment is improved after a certain action is executed, then A higher reward value is given; conversely, if the probability of communication link interruption increases or power equipment failure occurs, a lower reward value is given. Finally, based on the obtained reward value and the current state and action, a reinforcement learning algorithm such as a deep Q-network (DQN) is used to update the Q-value table. The above process is repeated until the Q-value table converges, that is, the change in the Q-value tends to be stable. The judgment condition for Q-value convergence can be set as that the change in the Q-value in the Q-value table is less than a preset threshold in several consecutive iterations. After the Q-value table converges, the action with the largest Q-value in the row corresponding to the current multidimensional state vector is selected as the optimal protection strategy for the current state. This can minimize communication security risks and ensure the stable operation of the power network. This embodiment applies the selected optimal protection strategy to an actual power network, and adjusts and optimizes the operating state and communication system of the power network accordingly to reduce communication security risks and effectively improve the communication security and reliability of the power network under complex situations such as dynamic migration of electromagnetic field intensity gradient zones.

[0132] An embodiment of the present invention provides an active defense method for an electric power network in an open and integrated network environment. The method analyzes the spatial intensity gradient of the electromagnetic field based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of an ultra-high voltage converter station, and identifies the electromagnetic field intensity gradient zone; analyzes the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient zone, and generates an electromagnetic interference relationship topology map; collects port link quality data between communication equipment near the electromagnetic field intensity gradient zone according to the migration direction of the electromagnetic field intensity gradient zone; obtains the co-evolution relationship between the port link quality and the electromagnetic field topology structure based on the port link quality data and the electromagnetic interference relationship topology map; analyzes the potential impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtains a communication security risk prediction result; and generates an optimal electric power network protection strategy based on the communication security risk prediction result through a reinforcement learning algorithm. Compared with the existing technology, this method accurately analyzes the impact of the dynamic migration of electromagnetic field intensity gradient zones on communication security by monitoring the electromagnetic field distribution in the valve hall of the ultra-high voltage converter station, and combines the electromagnetic interference relationship topology map and co-evolution relationship to achieve active defense of the power network in an open and integrated environment, effectively reducing the risk of communication failures caused by electromagnetic interference, and ensuring the communication security and stable operation of the power network in a complex electromagnetic environment.

[0133] It should be noted that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of this application.

[0134] In one embodiment, Figure 2 As shown, an embodiment of the present invention provides an active defense system for a power network in an open and integrated network environment, the system comprising:

[0135] Gradient change identification module 101 is used to analyze the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the ultra-high voltage converter station in an open and integrated network environment, and identify the electromagnetic field intensity gradient change area;

[0136] The electromagnetic analysis module 102 is used to analyze the spatial propagation attenuation characteristics of the electromagnetic field according to the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, and generate an electromagnetic interference relationship topology map;

[0137] The migration analysis module 103 is used to determine the migration direction of the electromagnetic field intensity gradient change area and collect port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area;

[0138] The co-evolution module 104 is configured to obtain a co-evolution relationship between the port link quality and the electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map;

[0139] The risk prediction module 105 is used to analyze the potential impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtain a communication security risk prediction result;

[0140] The strategy generation module 106 is used to generate an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction result.

[0141] For the specific definition of the active defense system for an electric power network in an open and integrated network environment, please refer to the above-mentioned definition of the active defense method for an electric power network in an open and integrated network environment, which will not be repeated here. A person of ordinary skill in the art will appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0142] An embodiment of the present invention provides an active defense system for an electric power network in an open and integrated network environment, wherein a gradient change identification module of the system analyzes the spatial intensity gradient of the electromagnetic field based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of an ultra-high voltage converter station, and identifies the electromagnetic field intensity gradient area; the electromagnetic analysis module analyzes the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, and generates an electromagnetic interference relationship topology map; the migration analysis module collects port link quality data between communication equipment near the electromagnetic field intensity gradient area according to the migration direction of the electromagnetic field intensity gradient area; the co-evolution module obtains the co-evolution relationship between the port link quality and the electromagnetic field topology structure based on the port link quality data and the electromagnetic interference relationship topology map; the risk prediction module analyzes the potential impact of the dynamic migration of the electromagnetic field intensity gradient area on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtains a communication security risk prediction result; the strategy generation module generates an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction result. Compared with existing technologies, this system monitors the electromagnetic field distribution in the valve hall of the UHV converter station to accurately analyze the impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security, and combines the electromagnetic interference relationship topology map and co-evolution relationship to achieve active defense of the power network in an open and integrated environment, effectively reducing the risk of communication failures caused by electromagnetic interference, and ensuring the communication security and stable operation of the power network in a complex electromagnetic environment.

[0143] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A method for active defense of power network in an open and integrated network environment, characterized in that: The following steps are involved: In an open and integrated network environment, the electromagnetic field spatial intensity gradient is analyzed based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of an ultra-high voltage converter station, and the electromagnetic field intensity gradient change area is identified. According to the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, the spatial propagation attenuation characteristics of the electromagnetic field are analyzed to generate an electromagnetic interference relationship topology map; Determining the migration direction of the electromagnetic field intensity gradient change area, and collecting port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area; Acquire a co-evolution relationship between port link quality and electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map; Based on the co-evolutionary relationship between port link quality and electromagnetic field topology, the potential impact of dynamic migration of electromagnetic field intensity gradient zones on communication security is analyzed, and communication security risk prediction results are obtained. Based on the communication security risk prediction results, an optimal power network protection strategy is generated through a reinforcement learning algorithm.

2. The method for active defense of a power network in an open and integrated network environment according to claim 1, characterized in that: The step of analyzing the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the ultra-high voltage converter station to identify the electromagnetic field intensity gradient change area includes: The electromagnetic field distribution data between several groups of valve towers collected by the electromagnetic field sensor array in the valve hall of the UHV converter station are divided into different monitoring areas to obtain the electromagnetic field distribution data of each monitoring area; According to the electromagnetic field distribution data between adjacent monitoring areas, the electromagnetic field intensity difference between different monitoring areas is obtained by using spatial divergence calculation; Dynamically analyzing the electromagnetic field intensity difference using a sliding time window to calculate the gradient change rate of the electromagnetic field intensity between regions; The monitoring area where the rate of change of the electromagnetic field intensity gradient between the areas exceeds a preset electromagnetic field intensity gradient change threshold range is determined as an electromagnetic field intensity gradient change area.

3. The method for active defense of power network in an open and integrated network environment according to claim 1, characterized in that: The step of analyzing the spatial propagation attenuation characteristics of the electromagnetic field according to the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area to generate the electromagnetic interference relationship topology map includes: A vector electromagnetic field model of the valve tower array is constructed based on Maxwell's equations, and the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient region is calculated according to the vector electromagnetic field model; The shielding strength parameter is introduced and the spatial attenuation coefficient of the electromagnetic field between each group of valve towers is calculated according to the electromagnetic field coupling strength. According to the spatial attenuation coefficient, an exponential attenuation function is used to fit the attenuation of the electromagnetic field intensity at different propagation distances to obtain an electromagnetic field propagation attenuation characteristic curve; The electromagnetic wave propagation path loss is calculated based on the electromagnetic field propagation attenuation characteristic curve, and the electromagnetic wave propagation path loss is used as a weight to search for the shortest propagation path between each path node using the Dijkstra algorithm. The shortest propagation path and electromagnetic field distribution data are analyzed using a graph neural network to calculate the topological correlation between each group of valve towers, and a topological map of the electromagnetic interference relationship between the valve towers is constructed based on the topological correlation.

4. The method for active defense of a power network in an open and integrated network environment according to claim 1, characterized in that: The step of determining the migration direction of the electromagnetic field intensity gradient change zone includes: Based on the electromagnetic field distribution data, a sliding time window is used to calculate the field intensity mean of the electromagnetic field intensity gradient change area in each time window to obtain a field intensity mean sequence of the electromagnetic field intensity gradient change area; Calculating the standard deviation of the field intensity in each time window based on the field intensity mean value sequence of the electromagnetic field intensity gradient region to obtain a standard deviation time series; Performing wavelet analysis on the standard deviation time series to extract characteristic vectors of electromagnetic field intensity changes; Based on the electromagnetic field intensity change characteristic vector, a time series analysis method is used to model and predict the electromagnetic field intensity change trend to generate an electromagnetic field intensity change trend matrix; A Kalman filter is used to perform real-time estimation on the electromagnetic field intensity variation trend matrix to determine the migration direction of the electromagnetic field intensity gradient variation zone.

5. The method for active defense of electric power network in an open and integrated network environment according to claim 1, characterized in that: The step of collecting port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area includes: Based on the migration direction of the electromagnetic field intensity gradient change area, the port data packet transmission rate between the communication devices near the electromagnetic field intensity gradient change area is collected; Calculate the port link bandwidth utilization rate based on the port data packet transmission rate and the port physical bandwidth; According to the port link bandwidth utilization and the pre-acquired link quality index, the port link quality data between the communication devices near the electromagnetic field intensity gradient change area is obtained.

6. The method for active defense of electric power network in an open and integrated network environment according to claim 1, characterized in that: The step of obtaining the co-evolution relationship between the port link quality and the electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map includes: Analyzing the relationship topology graph of the port link quality data and the electromagnetic interference using a graph mining method to extract time-varying feature sequences of the relationship topology graph of the port link quality data and the electromagnetic interference at different time points; The time-varying characteristic sequence is modeled and analyzed using the differential autoregressive moving average method to obtain a topological evolution trend vector; Based on the topology evolution trend vector, a dynamic mode decomposition algorithm is used to identify the co-evolution relationship between the port link quality and the electromagnetic field topology structure.

7. The method for active defense of electric power network in an open and integrated network environment according to claim 1, characterized in that: The step of analyzing the potential impact of dynamic migration of electromagnetic field intensity gradient zones on communication security based on the co-evolution relationship between port link quality and electromagnetic field topology to obtain a communication security risk prediction result includes: A co-evolution state transition matrix is ​​constructed based on the co-evolution relationship between the port link quality and the electromagnetic field topology, and a long short-term memory network is used to learn and predict the co-evolution state transition matrix to obtain the bandwidth limitation probability and packet loss rate; Using the Markov method to perform state prediction on the bandwidth limitation probability and the packet loss rate to obtain a communication link interruption probability distribution; According to the characteristic parameters of the electromagnetic field intensity gradient change area, the dynamic migration of the electromagnetic field intensity gradient change area is analyzed using a spatiotemporal correlation analysis method to construct a spatial position determination matrix; Calculating the degree of overlap between the communication link and the transition zone migration path according to the communication link interruption probability distribution and the spatial position determination matrix; If the degree of overlap exceeds a preset overlap threshold, the probability of the communication link being interfered with is calculated based on the degree of overlap, and a communication security risk prediction result is generated based on the probability of the communication link being interfered with.

8. The method for active defense of electric power network in an open and integrated network environment according to claim 7, characterized in that: The step of analyzing the dynamic migration of the electromagnetic field intensity gradient change region using a spatiotemporal correlation analysis method based on the characteristic parameters of the electromagnetic field intensity gradient change region and constructing a spatial position determination matrix comprises: Based on the characteristic parameters of the electromagnetic field intensity gradient change region, Gaussian process regression is used to analyze the spatial distribution state of the electromagnetic field intensity gradient change region at different time points to obtain a dynamic migration trajectory matrix of the electromagnetic field intensity gradient change region; the characteristic parameters of the electromagnetic field intensity gradient change region include the intensity gradient, spatial distribution range and migration rate of the electromagnetic field intensity gradient change region; Determine the time point sequence of the magnetic field intensity gradient change region and its position information at different time points based on the dynamic migration trajectory matrix; Using the spatiotemporal correlation analysis method, the time sequence of changes in the electromagnetic field intensity gradient change area and its location information at different time points are analyzed to obtain the device point density and link connectivity between communication devices near the electromagnetic field intensity gradient change area; A spatial position determination matrix is ​​constructed using a weighted algorithm according to the device point density and the link connectivity.

9. The method for active defense of electric power network in an open and integrated network environment according to claim 1, characterized in that: The step of generating an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction result includes: Combining the power network operation state and the communication security risk prediction result into a multidimensional state vector, and using the multidimensional state vector as the state space in the reinforcement learning algorithm; A protection strategy is defined as an action space according to the protection requirements of the power network, and each action in the action space is encoded to form a discrete action set; Initialize the Q-value table of the reinforcement learning algorithm. In the power network simulation environment under the open converged network environment, the control agent selects an action from the action space based on the current state. It iteratively updates the Q-value table based on the reward obtained from executing the action. Repeat the above process until the Q-value converges. According to the converged Q-value table, the action with the largest Q-value is selected as the optimal protection strategy in the current state.

10. An active defense system for power network in an open and integrated network environment, characterized in that: The system comprises: The gradient change identification module is used to analyze the electromagnetic field spatial intensity gradient based on the monitored electromagnetic field distribution data between several groups of valve towers in the valve hall of the UHV converter station in an open and integrated network environment, and identify the electromagnetic field intensity gradient change area; The electromagnetic analysis module is used to analyze the spatial propagation attenuation characteristics of the electromagnetic field based on the electromagnetic field coupling strength between each group of valve towers in the electromagnetic field intensity gradient area, and generate an electromagnetic interference relationship topology map; A migration analysis module is used to determine the migration direction of the electromagnetic field intensity gradient change area and collect port link quality data between communication devices near the electromagnetic field intensity gradient change area according to the migration direction of the electromagnetic field intensity gradient change area; A co-evolution module, configured to obtain a co-evolution relationship between port link quality and electromagnetic field topology structure according to the port link quality data and the electromagnetic interference relationship topology map; The risk prediction module is used to analyze the potential impact of the dynamic migration of the electromagnetic field intensity gradient zone on communication security based on the co-evolution relationship between the port link quality and the electromagnetic field topology structure, and obtain the communication security risk prediction results; A strategy generation module is used to generate an optimal power network protection strategy through a reinforcement learning algorithm based on the communication security risk prediction results.

Images