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.
Additional information
Notes on contributors
Yanzhen Zhou
Yanzhen Zhou received her B.S. from Dalian University of Technology, Liaoning, China, in 2012. She is currently working toward her Ph.D. in the School of Electrical Engineering, Beijing Jiaotong University, Beijing, China. Her research interests include power system transient stability and machine learning techniques and their applications in power system stability.
Junyong Wu
Junyong Wu received his B.S., M.S., and Ph.D. in electrical engineering from Huazhong University of Science and Technology, Hubei, China, in 1987, 1989, and 1993, respectively. From 1998 to 2004, he was a postdoctoral researcher with University of Tokyo, Tokyo, Japan. Currently, he is a professor of electrical engineering at Beijing Jiaotong University, Beijing, China. His research interests are power system analysis and control, smart grids, renewable energy generation, and microgrids.
Liangliang Hao
Liangliang Hao received his Ph.D. in electric machines and systems from Tsinghua University, Beijing, China, in 2012. He is an assistant professor in the School of Electrical Engineering, Beijing Jiaotong University, Beijing, China. His research interests include inter-turn short circuits of field windings in large synchronous generators and the analysis for electric machines and their systems.
Luyu Ji
Luyu Ji received his M.S. in 2011 from the School of Electrical Engineering, Beijing Jiaotong University, Beijing, China, where he is currently pursuing his Ph.D. His main research interest is transient stability analysis in power systems.
Zhihong Yu
Zhihong Yu received her B.S. and M.S. in electrical engineering from Xinjiang University, China, in 1997 and 2000, respectively, and her Ph.D. in electrical engineering from Harbin Institute of Technology, China, in 2004. She is currently working with China Electric Power Research Institute (CEPRI) and is a principal engineer in the dynamic security assessment studies group. Her current research interests include power system stability simulation, analysis, and control and data mining and its engineering applications in power systems.