Power grid abnormal flow detection method, device and equipment and computer medium

Abstract

The invention discloses a power grid abnormal flow detection method, device and equipment and a computer medium, and the method comprises the steps: determining an attack vector according to collected network attack behavior data; extracting behavior characteristics in the attack vector through a static analysis method and a dynamic detection method; performing feature processing on the extracted behavior features by using a deep network model to generate discriminative features, wherein the discriminative features are used for representing the correlation between the attack vectors; and classifying the discriminative features, and determining abnormal traffic data in the network attack behavior data based on a classification result. According to the method, the data features of the network traffic are extracted from the historical network attack behavior data by adopting the deep network module, the analysis period of an abnormal traffic detection algorithm can be effectively shortened, the detection efficiency is improved, meanwhile, the hierarchical relationship of the data can be mined, and the accuracy of a detection result is higher.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method, device, equipment and computer medium for detecting abnormal flow of a power grid. Background technique [0002] With the rapid development and wide application of power grid intelligent technology, the types and numbers of cyber attacks on the power grid system are also increasing significantly. Negative impacts and serious losses. Therefore, studying the attack behavior of the power grid system and detecting abnormal power grid traffic is the key to ensuring the security of power defense. [0003] Existing abnormal traffic detection methods for power grids generally identify the types of abnormal traffic in power grids by formulating various feature extraction schemes on the basis of existing databases, and then using a combination of static and dynamic analysis. The types are complex and diverse. When using the above methods to detect abnormal traffic in the power...

AI Technical Summary

Problems solved by technology

[0003] Existing detection methods for power grid abnormal traffic generally identify the type of power grid abnormal traffic by formulating various feature extraction schemes on the basis of existing databases, and then combining static and dynamic analysis. The types are complex and diverse. When using the above methods to detect abnormal traffic in the power grid, it usually needs to deal with large-scale data, which prolongs the analysis and response time of the system and makes it difficult to obtain more accurate identification results per unit time.

Images