The overarching goal of the project is to detect spurious or maliciously injected sensor data originating from cyber-attacks that can have similar appearance as system’s dynamic response and correct the same. Energy CPS is chosen as an example system. Thus far we have obtained positive results using principal component pursuit and robust PCA approach. In this poster, a Kernel PCA-based approach is used for event detection, which is resilient to data anomaly due to spurious outliers or false data injection attack on synchrophasor data stream.

The proposed research focuses on innovation in the area of detection and separation of anomaly in sensory data used for real time monitoring and control of cyber-physical systems (CPS). In this work, bulk power grid is considered as an example CPS, which is a critical infrastructure of our nation. The problem of spurious or maliciously injected sensor data originating from cyber-attacks is very important, because it can seriously jeopardize the monitoring and stabilization controls of power grids. This can lead to system-wide blackouts and cost our economy billions of dollars.