Data security assessment method and system based on clustering processing

Abstract

The invention discloses a data security assessment method and system based on clustering processing. The method comprises the steps of data acquisition, data coherence detection, clustering processing and data security assessment. The invention belongs to the field of data processing, and particularly relates to a data security assessment method and system based on clustering processing, according to the scheme, the correlation between each pair of buses is calculated, and a graph model is introduced to represent a power network, so that key paths and potential fault points can be identified; the partition of the preliminary abnormal area is further optimized through self-adaptive genetic manipulation, a weight matrix is dynamically updated based on the influence of real-time data and external factors, and the capacity of coping with a complex and changing electric power system environment is improved; the abnormal condition of the to-be-detected area is accurately evaluated based on the adaptive projection measurement, so that the data security evaluation effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a data security assessment method and system based on clustering processing. Background Art

[0002] Data security assessment methods analyze and evaluate data areas for normality, thereby identifying potential safety hazards. Once an abnormal area is detected, the system issues an alert, enabling managers to take appropriate measures to ensure safe system operation. However, conventional data security assessment methods are unable to adapt promptly to changes in the power system's operating conditions and environmental conditions, resulting in poor safety assessment accuracy. They also suffer from low accuracy in detecting faulty areas, leading to misjudgments. Furthermore, they fail to reflect the power system's operating status in real time, resulting in poor safety assessment results. Summary of the Invention

[0003] In response to the above situation, in order to overcome the defects of the existing technology, the present invention provides a data security assessment method and system based on clustering processing. In view of the problem that general data security assessment methods cannot adapt to changes in the operating conditions and environmental conditions of the power system in a timely manner, which leads to poor accuracy of security assessment, this scheme calculates the correlation between each pair of buses and introduces a graphical model to represent the power network, which helps to identify critical paths and potential fault points; by introducing dynamic edge weight coefficients and environmental change factors, the accuracy of data security detection is improved; in view of the problem that general data security assessment methods have low accuracy in fault area detection, which leads to misjudgment; and cannot reflect the operating conditions of the power system in real time, which leads to poor security assessment effect; this scheme further optimizes the partitioning of preliminary abnormal areas through adaptive genetic operations, dynamically updates the weight matrix based on the influence of real-time data and external factors, and improves the ability to cope with complex and changing power system environments; accurately evaluates the abnormal conditions of the area to be detected based on adaptive projection metrics, thereby improving the data security assessment effect.

[0004] The technical solution adopted by the present invention is as follows: The data security assessment method based on clustering processing provided by the present invention comprises the following steps:

[0005] Step S1: data collection;

[0006] Step S2: data coherence detection;

[0007] Step S3: clustering processing;

[0008] Step S4: Data security assessment.

[0009] Furthermore, in step S1, the data collection is to collect power system operation data; and perform data conversion, denoising and normalization processing to obtain a data set; the power system operation data includes bus operation data, system topology data, meteorological data, equipment aging data, load data and communication network data.

[0010] Furthermore, in step S2, the data coherence detection is to construct a correlation coefficient sensitivity matrix; extract the bus operation data from the power system, and calculate the correlation between each pair of buses, which is expressed as: ; Build a graph model based on the correlation matrix, where the busbar is the node and the weighted edge betweenness is introduced to build the edge weight , the edge weight is expressed as: ; Use the Newman algorithm to perform clustering, calculate the edge betweenness, delete the edge with the largest edge betweenness until it is split into k2 subclusters; evaluate the clustering effect and output the normal and abnormal data areas of the power system; the evaluation of clustering effect is expressed as: ; A clustering threshold and a correlation threshold are set in advance, and clusters with correlation higher than the correlation threshold and clustering effect higher than the clustering threshold are marked as normal areas, otherwise they are marked as preliminary abnormal areas; Among them, is to remove and Data set; data points correspond to busbar data; is the i-th bus data and the jth busbar data Correlation coefficient of and is the standard deviation of the parent data; Cov(·|·) is the partial covariance; Q is the clustering effect; m is the total number of edges in the graph; A ij is the busbar correlation; k i and k j is the sum of the edge weights connecting the busbar to other busbars; is the busbar set; is an indicator function, which is 1 if the buses belong to the same cluster, and 0 otherwise; and is the cluster to which the busbar belongs; and is the edge weight coefficient; s, t and v are nodes; is the number of shortest paths from node s to node t that pass through node v; is the number of all shortest paths from node s to node t.

[0011] Furthermore, in step S3, the clustering process specifically includes the following steps:

[0012] Step S31: Embed clustering, build a multi-layer graph model for the preliminary abnormal area data, represent the busbar and data as a single vertex set, and use different attributes as edges of independent layers. Each layer of the graph is represented by an adjacency matrix to construct a normalized Laplace matrix. ; expressed as: ; Construct a multi-objective optimization function by minimizing the impact of data anomalies, including minimizing active power flow interruption, expressed as: ; Minimize reactive power flow interruption, expressed as: ; Solve for the eigenvectors of the normalized Laplace matrix, expressed as: ; Where A is the adjacency matrix, which represents the connection relationship between buses; D is the degree matrix, which is the diagonal matrix of node degree values; is the set of busbars in the preliminary abnormal region; and are the active power flow and reactive power flow between buses respectively; E is the eigenvector matrix;

[0013] Step S32: performing k-means clustering on the row vectors of the eigenvector matrix; specifically comprising:

[0014] Step S321: Initialize the population; use the row vector of the eigenvector matrix E as the initial data; randomly generate K1 initial cluster centers C k ;

[0015] Step S322: define the objective function, which is: ; Define individual fitness value , expressed as: ; It is an individual representation; is the clustering objective function value; is the j1-th dimension eigenvalue of the i1-th data point; is the j1-th dimension center value of the k-th cluster; d is the total number of dimensions; n is the total number of data points; Is an indicator variable for whether a data point belongs to a cluster;

[0016] Step S323: Adaptive genetic operation: Use the roulette wheel method to select the next generation of individuals according to the fitness value, expressed as: ; Dynamically adjust crossover probability , expressed as: ; Dynamically adjust the mutation probability , expressed as: ;in, is the probability of an individual being selected; is the individual fitness value; and are the maximum and minimum values ​​of the crossover probability, respectively; and are the minimum and maximum fitness values ​​of the original population respectively; is the average fitness value of the population; is the crossover probability before adjustment;

[0017] Step S324: Cluster optimization; retain the 30% individuals with the highest fitness values ​​in the current population to the next generation, and do not participate in crossover mutation; if the fitness value of the individual after mutation is higher than the fitness value of the individual before mutation, then the mutation is retained, otherwise dynamic replacement is performed; dynamic replacement is expressed as: ;in, It is the position after dynamic replacement; is the maximum fitness value of the current population; M is the amplitude coefficient;

[0018] Step S33: Adjust the weight matrix according to the change of data flow. Based on real-time data, introduce the influence of external factors and dynamically update the weight matrix, which is expressed as: ;in, is the updated inter-bus weight; and They are the meteorological factor weight coefficient and the equipment aging factor weight coefficient; and is the characteristic mean of meteorological factors and equipment aging factors corresponding to the bus;

[0019] Step S34: Data anomaly identification; specifically: calculating the adaptive projection metric of the area to be detected ; expressed as: ; ; A distance threshold is set in advance, and the area to be detected whose projection distance is higher than the distance threshold is identified as an abnormal area, otherwise it is identified as a normal area; where N is the number of buses in the area to be detected; is the eigenvector matrix of the region to be detected; tr(·) is the trace of the matrix; is a neighborhood set; is the adaptive coefficient; Var(·) is the variance; is the busbar weight; x k is the feature of the kth data point.

[0020] Furthermore, in step S4, the data security assessment is based on the final clustering result, and the data corresponding to the normal area is assessed as safe data, and the data corresponding to the abnormal area is assessed as abnormal data; and early warning processing is performed on the management personnel.

[0021] The data security assessment system based on clustering processing provided by the present invention includes a data acquisition module, a data coherence detection module, a clustering processing module and a data security assessment module;

[0022] The data acquisition module collects power system operation data and sends the data to the data coherence detection module;

[0023] The data coherence detection module calculates the correlation between the power system buses, constructs a graph model and detects potential data anomaly areas through cluster analysis; and sends the data to the cluster processing module;

[0024] The clustering processing module performs multi-layer graph model optimization on the data of the preliminary abnormal area, minimizes the power flow interruption using the normalized Laplace matrix, and optimizes the clustering results through K-means clustering and genetic algorithm; and sends the data to the data security assessment module;

[0025] The data security assessment module evaluates normal and abnormal areas in the power system based on the clustering results and provides early warning processing to management personnel.

[0026] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0027] (1) In view of the problem that general data security assessment methods cannot adapt to changes in the operating conditions and environmental conditions of the power system in a timely manner, which leads to poor accuracy of security assessment, this scheme calculates the correlation between each pair of buses and introduces a graphical model to represent the power network, which helps to identify critical paths and potential fault points; by introducing dynamic edge weight coefficients and environmental change factors, the accuracy of data security detection is improved.

[0028] (2) The general data security assessment method has the problems of low accuracy in fault area detection, which leads to misjudgment; it cannot reflect the operation status of the power system in real time, which leads to poor security assessment results; this scheme further optimizes the partitioning of the initial abnormal area through adaptive genetic operations, dynamically updates the weight matrix based on the influence of real-time data and external factors, and improves the ability to cope with complex and changing power system environments; accurately evaluates the abnormal conditions of the area to be detected based on adaptive projection metrics, thereby improving the data security assessment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of the process of the data security assessment method based on clustering processing provided by the present invention;

[0030] Figure 2 A schematic diagram of a data security assessment system based on clustering processing provided by the present invention;

[0031] Figure 3 Schematic diagram of the process of step S3.

[0032] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] In the description of the present invention, it should be understood that terms such as "up", "down", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the system or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0035] Example 1, see Figure 1 The data security assessment method based on clustering processing provided by the present invention comprises the following steps:

[0036] Step S1: Data collection: collecting power system operation data;

[0037] Step S2: Data coherence detection: by calculating the correlation between the power system buses, a graphical model is constructed and potential data anomaly areas are detected through cluster analysis;

[0038] Step S3: Clustering processing; performing multi-layer graph model optimization on the data of the preliminary abnormal area, minimizing the power flow interruption using the normalized Laplace matrix, and optimizing the clustering results through K-means clustering and genetic algorithm;

[0039] Step S4: Data security assessment: Based on the clustering results, the normal and abnormal areas in the power system are assessed, and early warning processing is provided to management personnel.

[0040] Example 2, see Figure 1This embodiment is based on the above embodiment. In step S1, the collected data is converted, denoised and normalized to obtain a data set; the power system operation data includes bus operation data, system topology data, meteorological data, equipment aging data, load data and communication network data; the bus operation data includes voltage, current, power flow, frequency and phase; the system topology data includes bus connection relationship, transformer and transmission line connection; the meteorological data includes temperature, humidity, wind speed and precipitation; the equipment aging data includes equipment service life, equipment operating hours and failure rate; the load data includes peak load and base load; the communication network data includes delay and packet loss rate.

[0041] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, data coherence detection is to identify potential data anomaly areas by detecting low-coherence groups in the data set. Specifically, the following steps are performed: constructing a correlation coefficient sensitivity matrix; extracting bus operation data from the power system, and calculating the correlation between each pair of buses, which is expressed as: ; Build a graph model based on the correlation matrix, where the busbar is the node and the weighted edge betweenness is introduced to build the edge weight , which is used to reflect the relationship between buses in the power network and the key path of data flow, and dynamically adapt to environmental changes. The edge weight is expressed as: ; Use the Newman algorithm to perform clustering, calculate the edge betweenness, delete the edge with the largest edge betweenness until it is split into k2 subclusters; evaluate the clustering effect and output the normal and abnormal data areas of the power system; the evaluation of clustering effect is expressed as: ; A clustering threshold and a correlation threshold are set in advance, and clusters with correlation higher than the correlation threshold and clustering effect higher than the clustering threshold are marked as normal areas, otherwise they are marked as preliminary abnormal areas; Among them, is to remove and Data set; data points correspond to busbar data; is the i-th bus data and the jth busbar data Correlation coefficient of and is the standard deviation of the parent data; Cov(·|·) is the partial covariance; Q is the clustering effect; m is the total number of edges in the graph; A ij is the busbar correlation; k i and k j is the sum of the edge weights connecting the busbar to other busbars; is the busbar set; is an indicator function, which is 1 if the buses belong to the same cluster, and 0 otherwise; and is the cluster to which the busbar belongs; and is the edge weight coefficient; s, t and v are nodes; is the number of shortest paths from node s to node t that pass through node v; is the number of all shortest paths from node s to node t.

[0042] By performing the above operations, we address the problem that general data security assessment methods are unable to adapt to changes in the operating conditions and environmental conditions of the power system in a timely manner, which leads to poor security assessment accuracy. By calculating the correlation between each pair of buses and introducing a graphical model to represent the power network, this solution helps to identify critical paths and potential failure points; by introducing dynamic edge weight coefficients and environmental change factors, the accuracy of data security detection is improved.

[0043] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, the clustering process specifically includes the following steps:

[0044] Step S31: Embed clustering, further optimize data partitioning for the preliminary abnormal area, and detect potential fault areas of the power system; specifically: construct a multi-layer graph model for the preliminary abnormal area data, represent the bus and data as a single vertex set, and use different attributes as edges of independent layers. Each layer of the graph is represented by an adjacency matrix to construct a normalized Laplace matrix. ; expressed as: ; Construct a multi-objective optimization function by minimizing the impact of data anomalies, including minimizing active power flow interruption, expressed as: ; Minimize reactive power flow interruption, expressed as: ; Solve for the eigenvectors of the normalized Laplace matrix, expressed as: ; Where A is the adjacency matrix, which represents the connection relationship between buses; D is the degree matrix, which is the diagonal matrix of node degree values; is the set of busbars in the preliminary abnormal region; and are the active power flow and reactive power flow between buses respectively; E is the eigenvector matrix;

[0045] Step S32: performing k-means clustering on the row vectors of the eigenvector matrix; specifically comprising:

[0046] Step S321: Initialize the population; use the row vector of the eigenvector matrix E as the initial data; randomly generate K1 initial cluster centers C k ;

[0047] Step S322: define the objective function, which is: ; Define individual fitness value , expressed as: ; It is an individual representation; is the clustering objective function value; is the j1-th dimension eigenvalue of the i1-th data point; is the j1-th dimension center value of the k-th cluster; d is the total number of dimensions; n is the total number of data points; Is an indicator variable for whether a data point belongs to a cluster;

[0048] Step S323: Adaptive genetic operation: Use the roulette wheel method to select the next generation of individuals according to the fitness value, expressed as: ; Dynamically adjust crossover probability , expressed as: ; Dynamically adjust the mutation probability , expressed as: ;in, is the probability of an individual being selected; is the individual fitness value; and are the maximum and minimum values ​​of the crossover probability, respectively; and are the minimum and maximum fitness values ​​of the original population respectively; is the average fitness value of the population; is the crossover probability before adjustment;

[0049] Step S324: Cluster optimization; retain the 30% individuals with the highest fitness values ​​in the current population to the next generation, and do not participate in crossover mutation; if the fitness value of the individual after mutation is higher than the fitness value of the individual before mutation, then the mutation is retained, otherwise dynamic replacement is performed; dynamic replacement is expressed as: ;in, It is the position after dynamic replacement; is the maximum fitness value of the current population; M is the amplitude coefficient;

[0050] Step S33: Adjust the weight matrix according to the change of data flow. Based on real-time data, introduce the influence of external factors and dynamically update the weight matrix, which is expressed as: ;in, is the updated inter-bus weight; and They are the meteorological factor weight coefficient and the equipment aging factor weight coefficient; and is the characteristic mean of meteorological factors and equipment aging factors corresponding to the bus;

[0051] Step S34: Data anomaly identification; using detection and clustering results, combined with real-time data to achieve security assessment; specifically: calculating the adaptive projection metric of the area to be detected ; expressed as: ; ; A distance threshold is set in advance, and the area to be detected whose projection distance is higher than the distance threshold is identified as an abnormal area, otherwise it is identified as a normal area; where N is the number of buses in the area to be detected; is the eigenvector matrix of the region to be detected; tr(·) is the trace of the matrix; is a neighborhood set; is the adaptive coefficient; Var(·) is the variance; is the busbar weight; x k is the feature of the kth data point.

[0052] By performing the above operations, the problems of low accuracy in fault area detection, which leads to misjudgment, and inability to reflect the operation status of the power system in real time, which leads to poor security assessment results, are addressed in general data security assessment methods. This scheme further optimizes the partitioning of preliminary abnormal areas through adaptive genetic operations, dynamically updates the weight matrix based on the influence of real-time data and external factors, and improves the ability to cope with complex and changing power system environments. It also accurately evaluates the abnormal conditions of the area to be detected based on adaptive projection metrics, thereby improving the data security assessment effect.

[0053] Example 5, see Figure 1 This embodiment is based on the above embodiment. In step S4, data security assessment is based on the final clustering result, and the data corresponding to the normal area is assessed as safe data, and the data corresponding to the abnormal area is assessed as abnormal data; and early warning processing is performed on the management personnel.

[0054] Example 6, see Figure 2 , this embodiment is based on the above embodiment, and the data security assessment system based on clustering processing provided by the present invention includes a data acquisition module, a data coherence detection module, a clustering processing module and a data security assessment module;

[0055] The data acquisition module collects power system operation data and sends the data to the data coherence detection module;

[0056] The data coherence detection module calculates the correlation between the power system buses, constructs a graph model and detects potential data anomaly areas through cluster analysis; and sends the data to the cluster processing module;

[0057] The clustering processing module performs multi-layer graph model optimization on the data of the preliminary abnormal area, minimizes the power flow interruption using the normalized Laplace matrix, and optimizes the clustering results through K-means clustering and genetic algorithm; and sends the data to the data security assessment module;

[0058] The data security assessment module evaluates normal and abnormal areas in the power system based on the clustering results and provides early warning processing to management personnel.

[0059] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0060] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0061] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A data security assessment method based on clustering processing, characterized by: The method comprises the following steps: Step S1: Data collection: collecting power system operation data; Step S2: data coherence detection; Step S3: clustering processing; Step S4: Data security assessment; Step S3 includes step S31: embedding clustering, building a multi-layer graph model for the preliminary abnormal area data, representing the busbar and data as a single vertex set, and using different attributes as edges of independent layers. The graph of each layer is represented by an adjacency matrix, and a normalized Laplace matrix is ​​constructed. ; expressed as: ; Construct a multi-objective optimization function by minimizing the impact of data anomalies, including minimizing active power flow interruption, expressed as: ; Minimize reactive power flow interruption, expressed as: ; Solve for the eigenvectors of the normalized Laplace matrix, expressed as: ; Where A is the adjacency matrix, which represents the connection relationship between buses; D is the degree matrix, which is the diagonal matrix of node degree values; is the set of busbars in the preliminary abnormal region; and are the active power flow and reactive power flow between buses respectively; E is the eigenvector matrix; i and j are the bus indices.

2. The data security assessment method based on clustering processing according to claim 1, characterized in that: In step S2, the data coherence detection is to construct a correlation coefficient sensitivity matrix; extract the bus operation data from the power system, and calculate the correlation between each pair of buses, which is expressed as: ; Build a graph model based on the correlation matrix, where the busbar is the node and the weighted edge betweenness is introduced to build the edge weight , the edge weight is expressed as: Use the Newman algorithm to perform clustering, calculate edge betweenness, and delete the edge with the largest edge betweenness until it is split into k2 subclusters; evaluate the clustering effect and output the normal and abnormal data areas of the power system; The evaluation of clustering effect is expressed as: ; A clustering threshold and a correlation threshold are set in advance, and clusters with correlation higher than the correlation threshold and clustering effect higher than the clustering threshold are marked as normal areas, otherwise they are marked as preliminary abnormal areas; Among them, is to remove and Data set; data points correspond to busbar data; is the i-th bus data and the jth busbar data Correlation coefficient of and is the standard deviation of the parent data; Cov(·|·) is the partial covariance; Q is the clustering effect; m is the total number of edges in the graph; A ij is the busbar correlation; k i and k j is the sum of the edge weights connecting the busbar to other busbars; is the busbar set; is an indicator function, which is 1 if the buses belong to the same cluster, and 0 otherwise; and is the cluster to which the busbar belongs; and is the edge weight coefficient; s, t and v are nodes; is the number of shortest paths from node s to node t that pass through node v; is the number of all shortest paths from node s to node t.

3. The data security assessment method based on clustering processing according to claim 2, characterized in that: In step S3, the clustering process specifically includes the following steps: Step S31: embedding clustering; Step S32: performing k-means clustering on the row vectors of the eigenvector matrix; Step S33: Adjust the weight matrix according to the change of data flow. Based on real-time data, introduce the influence of external factors and dynamically update the weight matrix, which is expressed as: ;in, is the updated inter-bus weight; and They are the meteorological factor weight coefficient and the equipment aging factor weight coefficient; and is the characteristic mean of meteorological factors and equipment aging factors corresponding to the bus; Step S34: Data anomaly identification; specifically: calculating the adaptive projection metric of the area to be detected ; expressed as: ; ; A distance threshold is set in advance, and the area to be detected whose projection distance is higher than the distance threshold is identified as an abnormal area, otherwise it is identified as a normal area; where N is the number of buses in the area to be detected; is the eigenvector matrix of the region to be detected; tr(·) is the trace of the matrix; is a neighborhood set; is the adaptive coefficient; Var(·) is the variance; is the busbar weight; x k is the feature of the kth data point.

4. The data security assessment method based on clustering processing according to claim 3 is characterized in that: In step S32, performing k-means clustering on the row vectors of the eigenvector matrix specifically includes: Step S321: Initialize the population; use the row vector of the eigenvector matrix E as the initial data; randomly generate K1 initial cluster centers C k ; Step S322: define the objective function, which is: ; Define individual fitness value , expressed as: ; It is an individual representation; is the clustering objective function value; is the j1-th dimension eigenvalue of the i1-th data point; is the j1-th dimension center value of the k-th cluster; d is the total number of dimensions; n is the total number of data points; Is an indicator variable for whether a data point belongs to a cluster; Step S323: Adaptive genetic operation: Use the roulette wheel method to select the next generation of individuals according to the fitness value, expressed as: ; Dynamically adjust crossover probability , expressed as: ; Dynamically adjust the mutation probability , expressed as: ;in, is the probability of an individual being selected; is the individual fitness value; and are the maximum and minimum values ​​of the crossover probability, respectively; and are the minimum and maximum fitness values ​​of the original population respectively; is the average fitness value of the population; is the crossover probability before adjustment; Step S324: Cluster optimization; retain the 30% individuals with the highest fitness values ​​in the current population to the next generation, and do not participate in crossover mutation; if the fitness value of the individual after mutation is higher than the fitness value of the individual before mutation, then the mutation is retained, otherwise dynamic replacement is performed; dynamic replacement is expressed as: ;in, It is the position after dynamic replacement; is the maximum fitness value of the current population; M is the amplitude coefficient.

5. The data security assessment method based on clustering processing according to claim 4 is characterized in that: In step S1, the collected data is converted, denoised and normalized to obtain a data set; the power system operation data includes bus operation data, system topology data, meteorological data, equipment aging data, load data and communication network data.

6. The data security assessment method based on clustering processing according to claim 1, characterized in that: In step S4, the data security assessment is based on the final clustering result, and the data corresponding to the normal area is assessed as safe data, and the data corresponding to the abnormal area is assessed as abnormal data; And provide early warning to management personnel.

7. A data security assessment system based on clustering processing, for implementing the data security assessment method based on clustering processing according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, data coherence detection module, clustering processing module and data security assessment module; The data acquisition module collects power system operation data and sends the data to the data coherence detection module; The data coherence detection module calculates the correlation between the power system buses, constructs a graph model and detects potential data anomaly areas through cluster analysis; and sends the data to the cluster processing module; The clustering processing module performs multi-layer graph model optimization on the data of the preliminary abnormal area, minimizes the power flow interruption using the normalized Laplace matrix, and optimizes the clustering results through K-means clustering and genetic algorithm; And send the data to the data security assessment module; The data security assessment module evaluates normal and abnormal areas in the power system based on the clustering results and provides early warning processing to management personnel.

Images