A Hybrid Method for False Data Injection Attack Detection in Smart Grid Based on Variational Mode Decomposition and OS-ELM

Accurate state estimation is critical to wide-area situational awareness of smart grid. However, recent research found that power system state estimators are vulnerable to a new type of cyber-attack, called false data injection attack (FDIA). In order to ensure the security of power system operation and control, a hybrid FDIA detection mechanism utilizing temporal correlation is proposed. The proposed mechanism combines Variational Mode Decomposition (VMD) technology and machine learning. For the purpose of identifying the features of FDIA, VMD is used to decompose the system state time series into an ensemble of components with different frequencies. Furthermore, due to the lack of online model updating ability in a traditional extreme learning machine, an OS-extreme learning machine (OS-ELM) which has sequential learning ability is used as a detector for identifying FDIA. The proposed detection mechanism is evaluated on the IEEE-14 bus system using real load data from an independent system operator in New York. Apart from detection accuracy, the impact of attack intensity and environment noise on the performance of the proposed method are tested. The simulation results demonstrate the efficiency and robustness of our method.