A network security situation awareness system suitable for power system
By designing a network security situation awareness system in the power system, using log information analysis and neural network model, the problem that the existing technology cannot comprehensively evaluate the network security status of the power system is solved, real-time monitoring and risk warning of the network security of the power system is achieved. , improve safety prevention capabilities.
Patent Information
- Application Number
- CN202410571993.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-10
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-05-10
AI Technical Summary
The prior art is difficult to comprehensively evaluate the network security status of the power system and cannot effectively discover potential impacts, resulting in risks in subsequent use.
A network security situation awareness system was designed, including power data acquisition module, network system status analysis module, risk monitoring analysis module, abnormal state analysis module and potential impact analysis module. Through the analysis of log information, classification of abnormal operations, and neural Generation of network models and calculation of loss risks, real-time monitoring and early warning.
Real-time analysis and risk warning of the network security status of the power system are realized, the ability to identify and prevent potential threats is improved, and the overall prevention of network security is ensured.
Smart Images

Figure CN118381650B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of network security of electric power monitoring systems, and in particular to a network security situation awareness system suitable for electric power systems. Background Art
[0002] With the continuous development of power system informatization and the high integration of information technology and business, power system security threats are also tending to be informatized. But at the same time, power system informatization also has the defects of concealment, suddenness and uncertainty, and even causes serious cascading failures. Many countries and regions in the world have suffered huge losses due to such sudden incidents.
[0003] According to the patent with application number CN202210563891.6, the patent includes a server, which collects user historical behavior data through a user behavior data collection module, and uses a behavior database construction module to build a behavior database based on the user historical behavior data. The server performs association analysis on the behavior database through a database association analysis module, and uses a behavior feature set construction module to build a behavior feature set based on user identity based on the association analysis results. The server builds a behavior feature library based on role authorization based on the behavior feature set through a behavior feature library construction module.
[0004] The above patent collects user historical behavior data, builds a behavior database based on the user historical behavior data, performs correlation analysis on the behavior database, and based on the correlation analysis results, builds a behavior feature set based on user identity, and then builds a behavior feature library based on role authorization based on the behavior feature set. Finally, the user behavior is identified and judged based on the behavior database and the behavior feature library, thereby being able to perform fusion correlation analysis on multi-dimensional user behavior data and form an identification and judgment of user behavior.
[0005] However, the above patent only constructs a model by collecting historical user behaviors and identifies user behaviors based on the model. It cannot comprehensively evaluate the current network security status of the power system based on the data, and cannot further analyze the potential impacts, which will cause trouble for subsequent overall use. Summary of the invention
[0006] In view of the deficiencies in the prior art, the present invention provides a network security situation awareness system suitable for power systems, which solves the problem that the network security status of the power system cannot be analyzed and potential problems cannot be discovered well, which will further affect subsequent use.
[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A network security situation awareness system suitable for power systems, comprising:
[0008] A power data acquisition module, used to collect network security related data from the power monitoring system and transmit the related data to the network system status analysis module;
[0009] The network system status analysis module is used to analyze the acquired related data. By analyzing the data situation within the data collection period, a normal signal or an abnormal signal is generated according to the difference of abnormal data changes. At the same time, the normal signal is transmitted to the risk monitoring and analysis module, and the abnormal signal is transmitted to the abnormal status analysis module;
[0010] The risk monitoring and analysis module is used to analyze the acquired normal signals, classify the behavior operations in the log information into normal operations and abnormal operations, determine the data intervals for normal operations and abnormal operations respectively, and generate a risk warning model based on the data intervals combined with neural network technology. Then, according to the risk warning model, the current behavior operation is analyzed to generate a normal monitoring signal or a warning monitoring signal, and both are transmitted to the perception information output module at the same time;
[0011] The abnormal state analysis module is used to analyze the acquired abnormal signals, extract the characteristics of the abnormal operation, and determine the specific cause of the abnormal operation in combination with historical data. At the same time, it generates the difference reason and transmits it to the potential impact analysis module;
[0012] The potential impact analysis module is used to analyze the reasons for the differences obtained. By analyzing the abnormal data corresponding to the reasons for the differences, the network status is analyzed based on the generation time corresponding to the abnormal data to obtain the network value. At the same time, the network security operation loss risk value is calculated based on the network value, and loss risk information is generated, which is then transmitted to the perception information output module.
[0013] As a further solution of the present invention: the specific manner in which the network system status analysis module analyzes the associated data is:
[0014] S1: Obtain the log information within the time period t, then analyze the data of the data collection period corresponding to the time period t, determine the change in the number of abnormal data corresponding to the data collection period within the time period t, and calculate the difference in the number of abnormal data changes, and compare the difference in the number of changes with the preset value;
[0015] S2: When the quantity change difference is greater than the preset value, an abnormal signal is generated; conversely, when the quantity change difference is less than the preset value, a normal signal is generated.
[0016] As a further solution of the present invention: the specific method in which the risk monitoring and analysis module analyzes the normal signal is:
[0017] Obtaining log information and classifying the behavior operations in the log information, the behavior operations that generate abnormal data as abnormal operations, and the behavior operations that do not generate abnormal data as normal operations;
[0018] Obtain all normal operations in the log information, obtain the operation data corresponding to the normal operations, and generate a normal data interval;
[0019] All abnormal operations in the log information are obtained, and the operation data corresponding to the abnormal operations are obtained at the same time. The features of the abnormal operations are extracted, and the abnormal data interval is generated by integrating the operation data.
[0020] As a further solution of the present invention: the specific manner in which the risk monitoring and analysis module analyzes the current behavior operation according to the normal data interval and the abnormal data interval is:
[0021] Then, according to the normal data interval and the abnormal data interval, artificial neural network technology is used to generate a risk warning model, and then the risk prediction model is used to analyze the current behavior operation and generate corresponding analysis results, and the analysis results include: normal monitoring signals or warning monitoring signals.
[0022] As a further solution of the present invention: the specific manner in which the abnormal state analysis module analyzes the abnormal signal is:
[0023] B1: The abnormal operation corresponding to the abnormal signal is obtained, and the features of the abnormal operation are extracted, and the extracted features are recorded as abnormal features. Then, the transmitted historical data is obtained, and the corresponding historical abnormal operations in the historical data are obtained, and the features of the historical abnormal operations are extracted and recorded as historical abnormal features.
[0024] B2: Obtain similar operations of historical abnormal features and abnormal features, record dissimilar operations between the two as difference operations, integrate the difference operations, obtain the difference operations, and obtain the abnormal data corresponding to the difference operations. If the abnormal data corresponding to the difference operations are the same, mark the corresponding difference operations as the difference reasons. Otherwise, if the abnormal data corresponding to the difference operations are different, no processing is performed, and the generated difference reasons are transmitted to the potential impact analysis module.
[0025] As a further solution of the present invention: the specific method of analyzing the cause of the difference by the potential impact analysis module is:
[0026] A1: Obtain the difference reason and label it as i, where i=1, 2, ..., j. At the same time, obtain the number of abnormal data corresponding to the difference reason as Ki, obtain any group of abnormal data as the target object, obtain the generation time of the target object and record it as the analysis point;
[0027] A2: Get the network running speed V and processing speed V1 corresponding to the analysis point, and substitute them into the formula The network value Q corresponding to the analysis point is calculated, where a1 is the preset proportional coefficient. Similarly, the network value Qi corresponding to all abnormal data Ki is calculated, and then the average value of all network values Qi is calculated and recorded as Qp.
[0028] The specific method of generating loss risk information by the potential impact analysis module is as follows:
[0029] Then, the transmission fluctuation duration corresponding to the target object generation time is obtained and recorded as T, and the network mean Qp and fluctuation duration T are substituted into the formula The network security operation loss risk value F is calculated and the loss risk information is generated.
[0030] As a further solution of the present invention: the perception information output module is used to display the acquired analysis results and loss risk information to the operator.
[0031] The present invention provides a network security situation awareness system suitable for power systems. Compared with the prior art, it has the following beneficial effects:
[0032] The present invention analyzes the operations corresponding to the log information, classifies the behavioral operations into normal operations and abnormal operations, analyzes and processes the normal operations and abnormal operations respectively, and conducts a comprehensive analysis on the data corresponding to different operations, establishes a model in combination with neural network technology, judges the behavioral operations through the model, and simultaneously conducts a risk analysis of the overall network security status based on the acquired data, and combines the comprehensive analysis with historical data to achieve the purpose of overall prevention of network security. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION
[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] See also Figure 1The present application provides a network security situation awareness system suitable for power systems, including a power data acquisition module, a network system status analysis module, a risk monitoring and analysis module, an abnormal status analysis module, a potential impact analysis module and a perception information output module. Combined with the accompanying drawings, it can be seen that all the above-mentioned functional modules are unidirectionally electrically connected.
[0036] As embodiment 1 of the present invention
[0037] The power data acquisition module is used to collect network security-related data from the power monitoring system. These related data may include flow data, log information, etc., and transmit the collected related data to the network system status analysis module. The collection of related data is the premise of situational awareness and the basis for obtaining network security information.
[0038] The network system status analysis module is used to analyze the acquired related data, and the specific analysis method is as follows:
[0039] Determine the time period t, obtain the log information within the time period t, and then analyze the data situation of the data collection period corresponding to the time period t. Specifically, the data collection period refers to the time interval between two consecutive data collections. It can be divided into two situations according to the status of the actual data: For real-time detection data, the data collection period should be formulated according to the actual working conditions. For system production basic data, the data collection period can be carried out in a fixed period plus dynamic adjustment manner, determine the change in the number of abnormal data corresponding to the data collection period within the time period t, and calculate the difference in the number of abnormal data changes, and compare the difference in the number of changes with the preset value;
[0040] When the quantity change difference is greater than the preset value, an abnormal signal is generated, and conversely, when the quantity change difference is less than the preset value, a normal signal is generated.
[0041] The generated abnormal signal is transmitted to the abnormal state analysis module, and the generated normal signal is transmitted to the risk monitoring and analysis module.
[0042] The risk monitoring and analysis module is used to analyze the acquired normal signals, and the specific analysis method is as follows:
[0043] Log information is obtained and behavioral operations in the log information are classified, and the classification standard is to determine whether the behavioral operation generates abnormal data, and the behavioral operation that generates abnormal data is classified as an abnormal operation, and the behavioral operation that does not generate abnormal data is classified as a normal operation, and the abnormal operation and normal operation are analyzed; specifically, when the behavioral operation is performed on the power system, different behavioral operations will generate different data, and some abnormal operations will generate abnormal data. The operation that generates abnormal data is recorded as an abnormal operation, and the normal operation is classified in the same way.
[0044] The method of analyzing normal operations is: obtaining all normal operations in the log information, obtaining the operation data corresponding to the normal operations, and generating a normal data interval;
[0045] The method of analyzing abnormal operations is: obtaining all abnormal operations in the log information, obtaining the operation data corresponding to the abnormal operations, extracting the features of the abnormal operations, and generating abnormal data intervals based on the comprehensive operation data.
[0046] Then, according to the normal data interval and the abnormal data interval, the artificial neural network technology is used to generate a risk warning model. Then, the risk prediction model is used to analyze the current behavior operation and generate corresponding analysis results. The analysis results include: normal monitoring signals or warning monitoring signals. At the same time, the generated analysis results are transmitted to the perception information output module.
[0047] Specific neural networks rely on training data to learn and improve their accuracy over time. The training algorithm adjusts the weights and thresholds of the network to minimize the difference between the network's predicted output and the actual output. This is prior art and will not be described in detail here.
[0048] The perception information output module is used to display the acquired analysis results to the operator.
[0049] As the second embodiment of the present invention, this embodiment is implemented on the basis of the first embodiment, and the difference from the first embodiment is that:
[0050] The abnormal state analysis module is used to analyze the acquired abnormal signals, and the specific analysis method is as follows:
[0051] The abnormal operation corresponding to the abnormal signal is obtained, and the features of the abnormal operation are extracted, and the extracted features are recorded as abnormal features. Then, the transmitted historical data is obtained, and the corresponding historical abnormal operations in the historical data are obtained. At the same time, the features of the historical abnormal operations are extracted and recorded as historical abnormal features. The specific historical abnormal operations represent the historical operations corresponding to the abnormal data in the past data, and the historical abnormal features are integrated and analyzed with the abnormal features.
[0052] The similar operations of the historical abnormal features and the abnormal features are obtained, and the dissimilar operations between the two are recorded as difference operations, and the difference operations are integrated. Then, the specific cause of the abnormal data is determined according to the integrated difference operations, and the specific cause is generated in the following way:
[0053] The difference operation is obtained, and the exception data corresponding to the difference operation is obtained, and it is determined whether the exception data are the same. If the exception data corresponding to the difference operation are the same, the corresponding difference operation is marked as the difference cause. Otherwise, if the exception data corresponding to the difference operation are not the same, no processing is performed, and the generated difference cause is transmitted to the potential impact analysis module.
[0054] The potential impact analysis module is used to analyze the causes of the obtained differences, and the specific analysis method is as follows:
[0055] The difference cause is obtained and labeled as i, where i=1, 2, ..., j. Specifically, the number is used here to facilitate subsequent calculations. At the same time, the number of abnormal data corresponding to the difference cause is obtained and recorded as Ki, and any group of abnormal data is obtained and recorded as the target object. The generation time of the target object is obtained and recorded as the analysis point, and the network status corresponding to the analysis point is analyzed and processed;
[0056] Get the network running speed V and processing speed V1 corresponding to the analysis point, and substitute them into the formula The network value Q corresponding to the analysis point is calculated, where a1 is the preset proportional coefficient. Similarly, the network value Qi corresponding to all abnormal data Ki is calculated, and then the average value of all network values Qi is calculated and recorded as Qp;
[0057] Then, the transmission fluctuation duration corresponding to the target object generation time is obtained and recorded as T. The specific transmission fluctuation duration indicates the duration corresponding to the change in network transmission speed. At the same time, the network mean Qp and fluctuation duration T are substituted into the formula The network security operation loss risk value F is calculated and the loss risk information is generated, which is then transmitted to the perception information output module.
[0058] The perception information output module is used to display the acquired loss risk information to the operator.
[0059] As the third embodiment of the present invention, the focus is on combining the implementation processes of the first embodiment and the second embodiment.
[0060] Cybersecurity situation awareness is a process of comprehensively analyzing cybersecurity elements, evaluating cybersecurity status, predicting its development trends, and presenting it to users in a visual way. This process can be divided into the following four steps:
[0061] 1. Data collection: Use various detection tools to detect and collect factors that affect system security. This step is the premise of situational awareness and the basis for obtaining network security information.
[0062] 2. Situational understanding: The collected data is processed and integrated by means of classification, merging, and correlation analysis, and the integrated information is comprehensively analyzed to obtain the overall security status of the network. This step is the basis of situational awareness and requires an in-depth understanding and analysis of the network security status.
[0063] 3. Situation Assessment: Qualitatively and quantitatively analyze the current security status and weak links of the network, and provide corresponding countermeasures. This step is the core of situation awareness, which requires a comprehensive assessment of the network security status to identify existing security issues and risks.
[0064] 4. Situation prediction: By modeling and analyzing the data output by situation assessment, the development trend of network security situation is predicted. This step is the goal of situation awareness, which requires prediction and early warning of future network security situation to provide decision support for network security prevention.
[0065] Cybersecurity situational awareness is of great significance for ensuring network security. It can help enterprises and organizations to timely discover and solve network security problems, improve network security defense capabilities, and reduce security risks. At the same time, cybersecurity situational awareness is also an important research direction in the field of network security, which continuously promotes the innovation and development of network security technology.
[0066] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.
[0067] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims
1. A network security situation awareness system suitable for power systems, characterized in that: include: A power data acquisition module, used to collect network security related data from the power monitoring system and transmit the related data to the network system status analysis module; The network system status analysis module is used to analyze the acquired related data. By analyzing the data situation within the data collection period, a normal signal or an abnormal signal is generated according to the difference of abnormal data changes. At the same time, the normal signal is transmitted to the risk monitoring and analysis module, and the abnormal signal is transmitted to the abnormal status analysis module; The risk monitoring and analysis module is used to analyze the acquired normal signals, classify the behavior operations in the log information into normal operations and abnormal operations, determine the data intervals for normal operations and abnormal operations respectively, and generate a risk warning model based on the data intervals combined with neural network technology. Then, according to the risk warning model, the current behavior operation is analyzed to generate a normal monitoring signal or a warning monitoring signal, and both are transmitted to the perception information output module at the same time; The abnormal state analysis module is used to analyze the acquired abnormal signals, extract the characteristics of the abnormal operation, and determine the specific cause of the abnormal operation in combination with historical data. At the same time, it generates the difference reason and transmits it to the potential impact analysis module; The potential impact analysis module is used to analyze the acquired differences. By analyzing the abnormal data corresponding to the differences, the network status is analyzed based on the generation time of the abnormal data to obtain the network value. At the same time, the network security operation loss risk value is calculated according to the network value, and the loss risk information is generated. Then, it is transmitted to the perception information output module. The specific method of analyzing the differences is as follows: A1: Obtain the difference reason and label it as i, where i=1, 2, ..., j. At the same time, obtain the number of abnormal data corresponding to the difference reason as Ki, obtain any group of abnormal data as the target object, obtain the generation time of the target object and record it as the analysis point; A2: Get the network running speed V and processing speed V1 corresponding to the analysis point, and substitute them into the formula The network value Q corresponding to the analysis point is calculated, where a1 is the preset proportional coefficient. Similarly, the network value Qi corresponding to all abnormal data Ki is calculated, and then the average value of all network values Qi is calculated and recorded as Qp; Then, the transmission fluctuation duration corresponding to the target object generation time is obtained and recorded as T, and the network mean Qp and fluctuation duration T are substituted into the formula The network security operation loss risk value F is calculated and loss risk information is generated, where Ki is the number of abnormal data, Qp is the mean of the abnormal data network value, and the target object is any group of abnormal data.
2. A network security situation awareness system suitable for power system according to claim 1, characterized in that: The specific method in which the network system status analysis module analyzes the associated data is as follows: S1: Obtain the log information within the time period t, then analyze the data of the data collection period corresponding to the time period t, determine the change in the number of abnormal data corresponding to the data collection period within the time period t, and calculate the difference in the number of abnormal data changes, and compare the difference in the number of changes with the preset value; S2: When the quantity change difference is greater than the preset value, an abnormal signal is generated; conversely, when the quantity change difference is less than the preset value, a normal signal is generated.
3. A network security situation awareness system suitable for power system according to claim 1, characterized in that: The specific method in which the risk monitoring and analysis module analyzes normal signals is as follows: Obtaining log information and classifying the behavior operations in the log information, the behavior operations that generate abnormal data as abnormal operations, and the behavior operations that do not generate abnormal data as normal operations; Obtain all normal operations in the log information, obtain the operation data corresponding to the normal operations, and generate a normal data interval; All abnormal operations in the log information are obtained, and the operation data corresponding to the abnormal operations are obtained at the same time. The features of the abnormal operations are extracted, and the abnormal data interval is generated by integrating the operation data.
4. A network security situation awareness system suitable for power system according to claim 1, characterized in that: The specific method in which the risk monitoring and analysis module analyzes the current behavior operation according to the normal data interval and the abnormal data interval is: Then, according to the normal data interval and the abnormal data interval, artificial neural network technology is used to generate a risk warning model, and then the risk prediction model is used to analyze the current behavior operation and generate corresponding analysis results, and the analysis results include: normal monitoring signals or warning monitoring signals.
5. A network security situation awareness system suitable for power system according to claim 1, characterized in that: The specific method in which the abnormal state analysis module analyzes the abnormal signal is as follows: B1: The abnormal operation corresponding to the abnormal signal is obtained, and the features of the abnormal operation are extracted, and the extracted features are recorded as abnormal features. Then, the transmitted historical data is obtained, and the corresponding historical abnormal operations in the historical data are obtained, and the features of the historical abnormal operations are extracted and recorded as historical abnormal features. B2: Obtain similar operations of historical abnormal features and abnormal features, record dissimilar operations between the two as difference operations, integrate the difference operations, obtain the difference operations, and obtain the abnormal data corresponding to the difference operations. If the abnormal data corresponding to the difference operations are the same, mark the corresponding difference operations as the difference reasons. Otherwise, if the abnormal data corresponding to the difference operations are different, no processing is performed, and the generated difference reasons are transmitted to the potential impact analysis module.
6. A network security situation awareness system suitable for power system according to claim 1, characterized in that: The perception information output module is used to display the acquired analysis results and loss risk information to the operator.
