Skip to Main Content
A Model Predictive based emergency control scheme using TCSC to improve power system transient stability will be described in this paper. Supervised learning (SL) is utilized to predict power system dynamics by assuming each control action has been taken. Furthermore, a feature selection technique, that chooses the most relevant features, is used to improve the performance of the SL prediction. The model predictive control (MPC) technique is performed every discrete time interval, so the optimal control action is always selected. The proposed control scheme has been verified in a two machine four-bus system, and simulation results show it can effectively maintain system synchronism in the aftermath of a large disturbance.