Huaguang Zhang
Title: Self-learning Optimal Control for Power Systems by Using ADP: Recent Results and Applications
Abstract: As is known, it is often computationally untenable to run dynamic programming due to “curse of dimensionality”. Adaptive dynamic programming (ADP) is a powerful tool in solving the optimal control problems of complex nonlinear systems based on the principle of optimality and neural networks. In this talk, the self-learning optimal control issues will be addressed as follows: 1) The fundamental theory and recent development of ADP-based optimal control; 2) The event-triggered ADP for multi-player games is proposed in an on-line fashion, which can remove the requirement of control information in the triggering condition; 3) Considering the practical applications, we further study the optimal control of the multi-area power system and hybrid wind/solar systems to solve the accurate current sharing and realize the voltage and frequency regulation. Some examples are provided to show that the proposed method has good robustness to the uncertainty and unmodelled dynamics of the power systems.
Biography: Huaguang Zhang received the Ph.D. degree from Southeast University, Nanjing, China, in 1991. From 1992 to 1994, he did his postdoctoral research at Northeastern University, Shenyang, China. He has been with Northeastern University since 1991, and is currently as a Full Professor and Ph.D. advisor. He has authored and coauthored over 300 journal and conference papers, four monographs and co-invented more than 50 patents. He has been severing as an associate Editor of Automatica since 2008, an associate Editor of IEEE Transactions on neural networks since 2010, an associate Editor of IEEE Transactions on Cybernetics since 2007, an associate editor of Neurocomputing since 2007. In addition, he is a fellow of IEEE, the former E-letter Chair, and the former Chair of Adaptive Dynamic Programming & Reinforcement Learning Technical Committee in IEEE Computational Intelligence Society. Besides those he has been a member of the Neural Systems and Applications (NSA) Committee of IEEE Circuits and Systems Society, a member of the Blind Signal Processing (BSP) Committee of IEEE Circuits and Systems Society, a member of the Technical Committee on Computational Intelligence of the Systems, Man, and Cybernetics Society since 2007. He was awarded the Outstanding Youth Science Foundation Award from the National Natural Science Foundation Committee of China in 2003. He was named the Cheung Kong Scholar by the Education Ministry of China in 2005. He is a recipient of the IEEE Transactions on Neural Networks Outstanding Paper Award (2012) and Andrew P. Sage Best Transactions Paper Award (2015) with IEEE SMC Society. His current research interests include Adaptive Dynamic Programming, Fuzzy System Theory, Fuzzy Control, Neural Network-Based Control, Adaptive Control, Complex Industry Process Automation, Electric Power System Automation, Motor Driving System Automation, Integrated Energy System Optimization.
Abstract: As is known, it is often computationally untenable to run dynamic programming due to “curse of dimensionality”. Adaptive dynamic programming (ADP) is a powerful tool in solving the optimal control problems of complex nonlinear systems based on the principle of optimality and neural networks. In this talk, the self-learning optimal control issues will be addressed as follows: 1) The fundamental theory and recent development of ADP-based optimal control; 2) The event-triggered ADP for multi-player games is proposed in an on-line fashion, which can remove the requirement of control information in the triggering condition; 3) Considering the practical applications, we further study the optimal control of the multi-area power system and hybrid wind/solar systems to solve the accurate current sharing and realize the voltage and frequency regulation. Some examples are provided to show that the proposed method has good robustness to the uncertainty and unmodelled dynamics of the power systems.
Biography: Huaguang Zhang received the Ph.D. degree from Southeast University, Nanjing, China, in 1991. From 1992 to 1994, he did his postdoctoral research at Northeastern University, Shenyang, China. He has been with Northeastern University since 1991, and is currently as a Full Professor and Ph.D. advisor. He has authored and coauthored over 300 journal and conference papers, four monographs and co-invented more than 50 patents. He has been severing as an associate Editor of Automatica since 2008, an associate Editor of IEEE Transactions on neural networks since 2010, an associate Editor of IEEE Transactions on Cybernetics since 2007, an associate editor of Neurocomputing since 2007. In addition, he is a fellow of IEEE, the former E-letter Chair, and the former Chair of Adaptive Dynamic Programming & Reinforcement Learning Technical Committee in IEEE Computational Intelligence Society. Besides those he has been a member of the Neural Systems and Applications (NSA) Committee of IEEE Circuits and Systems Society, a member of the Blind Signal Processing (BSP) Committee of IEEE Circuits and Systems Society, a member of the Technical Committee on Computational Intelligence of the Systems, Man, and Cybernetics Society since 2007. He was awarded the Outstanding Youth Science Foundation Award from the National Natural Science Foundation Committee of China in 2003. He was named the Cheung Kong Scholar by the Education Ministry of China in 2005. He is a recipient of the IEEE Transactions on Neural Networks Outstanding Paper Award (2012) and Andrew P. Sage Best Transactions Paper Award (2015) with IEEE SMC Society. His current research interests include Adaptive Dynamic Programming, Fuzzy System Theory, Fuzzy Control, Neural Network-Based Control, Adaptive Control, Complex Industry Process Automation, Electric Power System Automation, Motor Driving System Automation, Integrated Energy System Optimization.