Subset Level Detection of False Data Injection Attacks in Smart Grids

Abstract

State estimation is a critical component in determining whether the power grid is operating properly, or not. Invalid state estimate can have a huge impact on the stability of the grid and can cause severe socioeconomic damage. False data injection attacks (FDIAs) display a prominent threat to the operation of power systems, especially when carefully constructed to bypass traditional bad data detection (BDD). Therefore, an intrusion detection system (IDS) has to be in place to prevent FDIAs from going unnoticed. A major limitation of current approaches is that only coarse-grained attack detection is performed. In order to take effective mitigation actions, it would be more beneficial to detect whether any critical subset of state variables is under attack or not. In this paper, we investigate two state-of-the-art machine learning algorithms for subset level detection of FDIAs. Furthermore, the trade-off between performance and subset size is investigated. The proposed detection algorithms are evaluated by simulating FDIAs on the IEEE 30-bus system using real-world load data for measurement construction.