WGAN-Based Synthetic Data Generation for Modeling Cyberattacks in Power Transmission Systems

The integration of diverse infrastructures in modern-day power systems facilitates unauthorized access and data manipulation by adversaries, as these systems heavily rely on Information and Communication Technology (ICT) for monitoring and control. A significant challenge within these power networks is the risk of operational disruptions, such as congestion and voltage instability, resulting from stealthy false data injection (FDI) cyberattacks. Different from the existing work, this paper proposes a solution by introducing a defense framework that utilizes a Wasserstein Generative Adversarial Network (WGAN) to generate synthetic data. This synthetic data closely resembles the output from actual Phasor Measurement Units (PMU) and is developed by training the WGAN with extensive real PMU datasets. Additionally, mixing synthetic and real data when sending it to the Supervisory Control and Data Acquisition (SCADA) system adds layers of complexity and obscures the data landscape for attackers, thereby hindering their ability to detect vulnerabilities and anomalies.