A deep learning-based cyber-physical strategy to mitigate false data injection attack in smart grids

Abstract

Application of computing and communications intelligence effectively improves the quality of monitoring and control of smart grids. However, the dependence on information technology also increases vulnerability to malicious attacks, such as false data injection attacks. In this paper, we propose a deep learning-based cyber-physical protocol to identify and mitigate the information corruption in the problem of maintaining the transient stability of Wide Area Monitoring Systems (WAMSs). The proposed strategy implements the deep learning technique to analyze the real-time measurement data from the geographically distributed Phasor Measurement Units (PMUs) and leverages the physical coherence in the power systems to probe and detect the data corruption. We demonstrate the performance of the proposed strategy through the simulation by using the New England 39-bus power system.