Intelligent Framework for Anomaly Identification and Mitigation in Cyber-physical Inverter-based Systems

Modern cyber-physical systems (CPS) have become more autonomous and distributed with advanced control architectures and communication networks. Power electronics-based inverters that employ extensive communication structures are integral to such systems. The distributed cooperative controllers for inverter-based systems rely on communication networks that make them vulnerable to cyber-physical anomalies. The cyber anomalies occur due to malicious attacks targeting the communication layer, and physical anomalies are caused by power system faults in the physical layer of the microgrid. An effective defense mechanism should detect and mitigate such anomalies in modern CPS for sustained normal operation. Therefore, this project proposes identifying and mitigating cyber-physical anomalies using data-driven intelligent techniques. In the first part of the project, an intelligent anomaly identification technique for such systems is presented utilizing data-driven artificial intelligence tools that employ multi-class support vector machines for anomaly classification and localization. The next part focuses on making traditional control structures resilient against cyber-physical anomalies by utilizing artificial neural network's strong learning and mapping capabilities. Real-time simulations are performed to demonstrate the proposed technique's performance on a real-time digital simulator OPAL-RT for an AC microgrid.