Power cps information attack identification method based on stacked self-encoding network model

Abstract

The invention is a power CPS information attack identification method based on a stack type self-encoding network model. Select and determine the optimal attack feature set; build an information attack identification model based on a stacked self-encoding network, set an unsupervised pre-training encoder and a supervised fine-tuning classifier to train and update network parameters; realize the adaptive cuckoo algorithm-based algorithm. Model initial parameter optimization. It solves the problems of complex data characteristics and relatively low identification accuracy in the process of power CPS information attack identification, and has the advantages of scientific and reasonable method, strong applicability, and good effect.

Description

technical field [0001] The invention relates to the field of electric power information physical systems, and is an electric power CPS information attack identification method based on a stack-type self-encoding network model. Background technique [0002] With the continuous development of information technology, the information side and the physical side of the power system are increasingly coupled interactively, and a cyber-physical system (CPS) integrating computing system, communication network and physical environment is gradually formed. In the process of power grid production management and dispatching control, information systems are more and more inseparable. But at the same time, some loopholes in information systems may be exploited by attackers, posing serious threats to physical systems across space, and even causing temporary paralysis of important infrastructure. The security problem of power CPS information side has gradually attracted people's attention. H...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the problems of complex data features and relatively low identification accuracy in the process of electric power CPS information attack identification, and propose a power system based on stacked self-encoding network model from the perspective of correlation and redundancy of CPS data features. CPS information attack identification method

Images