Bio-Inspired and AI DeepWalk Based Approach to Understand Cyber-Physical Interdependencies of Power Grid Infrastructure

The occurrence of cyber and physical disturbances in power systems is increasing, leading to increased public focus on cyber-physical architectures. It has been observed that disturbances can propagate between cyber and physical systems, highlighting the need to study their interdependencies. In this paper, we present an approach to improve the characterization of cyber-physical interdependencies through modeling techniques. These improved assessments of dependencies can then help optimize system design to improve functional resilience. To achieve this goal, we transform the cyber-physical architecture into a graph and apply bio-inspired network analysis using bipartite network methods to characterize the system during disturbances. Moreover, we apply a DeepWalk-based method to cluster the components based on their interdependencies. A WSCC-9 bus system is used for numerical study and quantification.