A New Method for Stealthy False Data Injection Attack Detection Using Advanced Feasibility Areas Considering Spatial Distribution

The Feasibility Area (FA) in power system applications defines the region within which Power System State Variables (PSSVs) typically exist under normal operating conditions. Accurate characterization of the FA helps enhancing optimal power flow, detecting anomalies, and identifying stealthy False Data Injection Attacks (FDIAs). Traditional FA-based approaches assess the location of PSSVs based on discrete time instances, using a binary flag to indicate whether the PSSVs lie inside or outside the FA. This paper introduces an advanced FA-based stealthy FDIAs detection method that improves upon this by incorporating the spatial distribution of PSSVs relative to the estimated FA. Unlike conventional methods, the advanced FA incorporates spatial distribution to evaluate the proximity of the current PSSV to the expected FA in the complex plane. A sigmoid-expansion flag is employed to represent the probability of the current PSSVs belonging to the expected FA, replacing the conventional binary flag. This sigmoid-expansion flag is then used as an input to a Deep Neural Network (DNN), where both the sigmoid-expansion flag and DNN model parameters are fine-tuned during training to ensure optimal compatibility, thereby improving detection accuracy. The proposed method significantly improves the detection of stealthy FDIAs, offering superior performance over traditional FA. Additionally, it enables the extraction of key attack characteristics, such as type, nature, and magnitude, further strengthening the system’s defense capabilities.