Cross‐layered distributed data‐driven framework for enhanced smart grid cyber‐physical security

Smart Grid (SG) research and development has drawn much attention from academia, industry government due to the great impact it will have on society, economics environment. Securing SG is a considerably significant challenge increased dependency communication networks assist in physical process control, exposing them various cyber-threats. In addition attacks that change measurement values using False Data Injection (FDI) techniques, network may disrupt power system's real-time operation by intercepting messages, or flooding channels with unnecessary data. Addressing these requires cross-layer approach. this paper cross-layered strategy presented, called Cross-Layer Ensemble CorrDet Adaptive Statistics(CECD-AS), which integrates detection of faulty data as well inconsistent inter-arrival times transmission delays for more reliable accurate anomaly attack interpretation. Numerical results show CECD-AS can detect multiple Injections, Denial Service (DoS) Man The Middle (MITM) high F1-score compared current approaches only use such traditional physics-based State Estimation, ECD-AS other machine learning classification-based schemes.