Traditionally, the scheduling and control of large-scale systems, such as power grids, microgrids, and naval shipboard power systems, have been managed independently. Enhanced coordination between these processes has the potential to significantly improve both energy efficiency and dynamic system performance.
“Scheduling provides short-term optimal references but is affected by prediction inaccuracies, necessitating real-time control to make necessary adjustments,” explains Wenxin Liu, a professor of electrical and computer engineering in Lehigh University’s P.C. Rossin College of Engineering and Applied Science. “Without proper coordination, even minor changes in operating conditions can lead to deviations from optimal performance.”
Liu recently received an $800,000 grant from the Office of Naval Research to develop a deep reinforcement learning (DRL)-based algorithm that integrates energy scheduling with power control. This novel approach addresses a longstanding challenge that traditional optimization and control theories have been unable to resolve.
“Although DRL has been successfully applied to scheduling and control independently, this project marks the first attempt to use DRL for the optimal coordination of these two operations,” Liu notes.
To validate the algorithm, Liu and his research team will utilize real-time simulation and hardware experimentation.
For the U.S. Navy, these advancements could significantly enhance the energy efficiency, reliability, and survivability of shipboard power systems, enabling vessels to operate more safely and travel greater distances.
“I have conducted Navy-funded research on real-time control for more than 13 years,” says Liu. “This project presents an exciting opportunity to broaden my research focus and further improve the performance of naval shipboard power systems.”
About Wenxin Liu
Wenxin Liu is a professor of Electrical and Computer Engineering and the director of ECE graduate studies at Lehigh University. He joined the faculty of the P.C. Rossin College of Engineering and Applied Science in 2014 and leads the Smart Microgrid and Renewable Technology (SMRT) Research Laboratory. His research interests include power systems, power electronics, controls, and deep reinforcement learning. He performs both advanced algorithm designs and hardware development/experimentation.
Liu holds degrees in industrial automation (BS, 1996) and control theory and applications (MS, 2000) from Northeastern University, in Shenyang, China. He earned a PhD in electrical engineering from the Missouri University of Science and Technology (formerly the University of Missouri–Rolla) in 2005.
From 2005 to 2009, he was a postdoc and then an assistant scholar scientist with the Center for Advanced Power Systems at Florida State University. From 2009 to 2014, he was an assistant professor in the Klipsch School of Electrical and Computer Engineering at New Mexico State University (NMSU).
Liu has published more than 80 journal papers (mostly in IEEE Transactions with his students) and received over $4.5 million in research funding from the Department of Defense/Office of Naval Research, National Science Foundation, Department of Energy, National Laboratorires, and California Energy Commission, as well as from industry. While at NMSU, he was named ConocoPhillips Faculty Fellow (2011) and received the Dean's Recognition Award (2012) and Early Career Award (2013). He was named to a P.C. Rossin professorship at Lehigh in 2016 and a Class of ’61 professorship in 2019.
Liu has served as an editor/associate editor for IEEE Transactions on Power Systems, IEEE Transactions on Smart Grid, IEEE Transactions on Industrial Informatics, and Journal of Electrical Engineering & Technology.
