Ensuring Data Integrity of OPF Module and Energy Database by Detecting Changes in Power Flow Patterns in Smart Grids

Recent studies show that smart grid is vulnerable to cyber anomalies. In this paper, an anomaly detection method is proposed to identify the abnormal patterns in the network power flows, which results from the accidental or deliberate changes of the database. The proposed method utilizes a multivariate time series statistical forecasting technique based on vector autoregressive model. To understand the power flow behavior of the system, a multiphase optimal power flow analysis is conducted. The proposed method is validated using IEEE Power Distribution System Analysis Subcommittee recommended 34-node and 123-node test systems. Three different experiments are performed to test the effectiveness of the proposed approach. Vulnerability and computational complexity issues of this paper are also addressed elaborately. Results obtained from this analysis show that the proposed method successfully captures the network anomalies at a high detection rate allowing only a few number of false alarms.