Security situation evaluation index selection method and system for electric power monitoring system

Abstract

The invention discloses a security situation evaluation index selection method and system for an electric power monitoring system. The method comprises the steps: collecting the historical data capable of reflecting the security state of the electric power monitoring system, and performing standardized processing to construct a training sample data set; analyzing whether the candidate indexes forsafety assessment in the sample data set have correlation with the safety problem of the power monitoring system or not, and determining whether each candidate index can judge the correlation priorityranking of the safety state of the power monitoring system or not; calculating redundancy between every two candidate indexes, removing characteristic indexes with high redundancy from the correlation priority ranking set, and finally selecting an optimal index set for security situation evaluation of the power monitoring system by comprehensively considering classification accuracy and the scaleof the index set. According to the invention, by carrying out feature selection on the security situation evaluation indexes of the power monitoring system, the accuracy of the evaluation result is improved, the expenditure of data acquisition, storage, transmission and processing resources is reduced, and the performance of implementing evaluation on the security situation of the power monitoring system is improved.

Description

technical field [0001] The invention belongs to the technical field of electric power information security, and in particular relates to a method and system for selecting an index for evaluating a safety situation of an electric power monitoring system. Background technique [0002] In recent years, with the continuous expansion and deepening of various network applications, malicious network attacks such as computer viruses, Trojan horses, and hacker attacks have become increasingly rampant, and network security incidents have entered a period of high incidence and frequency. National and group cyber attacks have seriously affected the production and life of the whole society. As an important infrastructure related to the national economy and people's livelihood, the power grid is a power monitoring system that monitors and controls the smooth operation of the smart grid. Because the power monitoring system has a complex structure, wide distribution, and high importance, on...

AI Technical Summary

Problems solved by technology

This method of feature selection based on the classification learning algorithm is mainly to obtain a classification model with high classification performance, which can well identify the key features related to the classification results, but still fails to remove the redundancy between the features. , and the generalization ability is poor, and the time complexity is high

[0007] Therefore, when using the above method to select the security assessment indicators for evaluating the power monitoring system, there will be problems such as the selected indicators have nothing to do with the security assessment, and there are redundant relationships between indicators, which will lead to problems when evaluating the security situation of the power monitoring system. The overhead of collecting, transmitting, and processing irrelevant and redundant indicators reduces the performance of real-time evaluation and also reduces the accuracy of evaluation

Images