Evidence-based analysis of cyber attacks to security monitored distributed energy resources

Abstract

This work proposes an approach based on dynamic Bayesian networks to support the cybersecurity analysis of network-based controllers in distributed energy plants. We built a system model that exploits real world context information from both information and operational technology environments in the energy infrastructure, and we use it to demonstrate the value of security evidence for time-driven predictive and diagnostic analyses. The innovative contribution of this work is in the methodology capability of capturing the causal and temporal dependencies involved in the assessment of security threats, and in the introduction of security analytics supporting the configuration of anomaly detection platforms for digital energy infrastructures.