False Data Injection Attacks Detection and Defense for Frequency Regulation of Smart Grid

With the increasing complexity and connectivity of modern power systems, the risk of cyber-attacks, particularly false data injection (FDI) attacks, has become a significant concern. This paper introduces a strategy for detecting and defending against FDI attacks in the frequency regulation of smart grids. By employing a combination of Kalman Filter (KF) and Artificial Neural Network (ANN), our strategy involves real-time monitoring of the power system's operational state with KF, and using ANN for data estimation and real value prediction when potential FDI attacks are detected. The proposed strategy is applied to a traditional three-region load frequency control system and validated through simulations. Results indicate its effectiveness in detecting and defending against various FDI attacks, highlighting its potential for widespread application.