PI: Dr. Sami El-Ferik
CoI: Dr. Muhammad Gulzar, Dr. Salman Habib

The advancement in centralized power systems has elevated the power grid into an advanced smart grid, emblematic of cyber-physical systems (CPS), susceptible to diverse type of false data injection (FDI) and cyber threats. Among these threats, load frequency control (LFC) systems, crucial for regulating power in tie-lines and ensuring frequency synchronization, are particularly vulnerable to FDI attacks. These attacks pose substantial risks to system continuity, stability, and reliability. In response, this project will introduce a robust control algorithm to optimize LFC on multiple load deviations. Subsequently, an AI/ML-based model will be trained to detect FDI attacks in a two-area network of centralized renewable energy power systems controlled by a supervisory control and data acquisition system. Initially, utilizing an AI/ML- based model will be trained on data pertaining to renewable centralized power generation, frequency aberrations, tie-line power deviations, electrical vehicles recharging and active power load deviations in both areas. Finally, the detection of FDI involves comparing the output control signal of the trained AI/ML model with actual plant output to discern residuals indicative of FDI attacks achieving a remarkable efficiency, distinguishing between systems under attack and those operating normally. The efficacy of the proposed technique will be demonstrated through real-time grid simulators such as OPAL-RT considering centralized power generation from solar, wind and thermal power plants. This approach will be a promising solution for improving the resilience of centralized power grids against FDI attacks, and maintaining their operational integrity and security.