Anomaly Detection for Cybersecurity of the Substations

Abstract

Cybersecurity of the substations in a power system is a major issue as the substations become increasingly dependent on computer and communication networks. This paper is concerned with anomaly detection in the computer network environment of a substation. An anomaly inference algorithm is proposed for early detection of cyber-intrusions at the substations. The potential scenario of simultaneous intrusions launched over multiple substations is considered. The proposed detection method considers temporal anomalies. Potential intrusion events are ranked based on the credibility impact on the power system. Snapshots of anomaly entities at substations are described. Simulation results using the modified IEEE 118-bus system have shown the effectiveness of the proposed method for systematic identification. The result of this research is a tool to detect cyber-intrusions that are likely to cause significant damages to the power grid.