Learning-Based Detection of Intraday False Data Injection Attacks on DER Dispatch Signals

The urgent need for the decarbonization of power grids has accelerated the integration of renewable energy. Concurrently the increasing distributed energy resources (DERs) and advanced metering infrastructures (AMIs) have transformed the power grids into a more sophisticated cyber-physical system with numerous communication devices. While these transitions provide economic and environmental value, they also impose increased risk of cyber attacks and operational challenges. This paper investigates the vulnerability of power grids with high renewable penetration against an intraday false data injection (FDI) attack on DER dispatch signals, and proposes a convolutional neural network (CNN) based detection model as a countermeasure. The intraday FDI attack scenario and the detection model are demonstrated in case studies using the real-world 187-bus test system with daily generation and load profiles from Holy Cross Energy (HCE), a power utility in Colorado. Extensive experiments and parameter sensitivity analyses are conducted to provide suggestions on model selection and parameter tuning.