Self-Healing Control of Nuclear Power Plants Under False Data Injection Attacks

Abstract

The transition from analog to digital instrumentation and control (I&C) systems introduces new threats caused by cyberattacks in the nuclear industry. This paper proposes a self-healing strategy to respond to a false data injection attack that targets digital I&C systems, which is a type of cyberattack commonly targeting nuclear power plants with the potential to cause serious physical impacts. This resilience strategy for self-healing control contains three components: (1) an anomaly detection model that can detect false data injection attacks, (2) a device-level control that utilizes inferred values to perform control under a detected false data injection, and (3) a system-level control that leverages another controller that is not under attack to lead the system back to a safe operation state when the device-level control is unavailable. Anomaly detection and device-level control use an autoencoder while system-level control utilizes reinforcement learning. The proposed self-healing resilience strategy is demonstrated with a generic pressurized water reactor (GPWR) simulator under false data injections, targeting the steam generator water level. The results show that the proposed strategy effectively leads the system back to a normal operation state under various false data injection cases.