Transient Stability Prediction of Power Systems Using Post-disturbance Rotor Angle Trajectory Cluster Features

Abstract

A machine learning-based approach is proposed to predict the transient stability of power systems after a large disturbance. The post-disturbance trajectories of generator rotor angles are taken as a whole cluster, and 19 cluster features are defined to depict the overall transient stability characteristics of the power systems. A hybrid approach, which combines the linear support vector machine with the decision tree, is proposed to generate the final transient stability classifier. Comprehensive studies are conducted on the IEEE 39-bus and IEEE 145-bus test systems to verify the performance of the proposed approach. Test results show that by using the cluster features and the proposed approach, the transient stability of the power system can be predicted accurately with a shorter training time. Furthermore, the prediction classifier is robust to unknown load levels and network topologies, especially under situations when some generator measurements are unavailable and the number of input cluster features is independent of the system scale, making the proposed approach more suitable to transient stability prediction of large-scale power systems.