Detection of Stealthy False Data Injection Attacks Against State Estimation in Electric Power Grids Using Deep Learning Techniques

Abstract

Since communication technologies are being integrated into smart grid, its vulnerability to false data injection is increasing. State estimation is a critical component which is used for monitoring the operation of power grid. However, a tailored attack could circumvent bad data detection of the state estimation, thus disturb the stability of the grid. Such attacks are called stealthy false data injection attacks (FDIAs). This thesis proposed a prediction-based detector using deep learning techniques to detect injected measurements. The proposed detector adopts both Convolutional Neural Networks and Recurrent Neural Networks, making full use of the spatial-temporal correlations in the measurement data. With its separable architecture, three discriminators with different feature extraction methods were designed for the predictor. Besides, a measurement restoration mechanism was proposed based on the prediction. The proposed detection mechanism was assessed by simulating FDIAs on the IEEE 39-bus system. The results demonstrated that the proposed mechanism could achieve a satisfactory performance compared with existing algorithms.