The increase penetration of smart energy systems in distribution electric grids is continuously bringing challenges to power system operators. The smart systems, which includes distributed energy resources (e.g. PV), smart home and building management systems, smart charging/discharge for electric vehicles, etc., provide extended controllability for power systems on one hand. On the other hand, their "selfish" control targets hardly match the reliability desire of grid operators at any given time. To coordinates the smart systems with quite different temporal characteristics, it is ideal to require a look-ahead of the future system status in order to make proactive control and dispatch decisions. This presentation introduces the initial attempt to use big-data analytics for predictive state estimation, as a step toward proactive dispatch and control.
Yingchen Zhang received the B.S. degree from Tianjin University, Tianjin, China, in 2003, and the Ph.D. degree from Virginia Polytechnic Institute and State University, Blacksburg, VA, USA, in 2010. Currently, he is a Principal Researcher and Manager of the Sensing and Predictive Analytics Group at the National Renewable Energy Laboratory. He is also a visiting research Assistant Professor at the University of Denver and an Adjunct faculty at Colorado State University. He has over 10 years of experience in power industry in the areas of data analytics for power systems, renewable integration, energy management systems. He authored/coauthored over 80 peer reviewed publications and holds one U.S. patent. His key areas of expertise lie in predictive analytics for energy systems, advanced energy management system for future grids, and the impact of large-scale integration of renewable energies on power system operations. Dr. Zhang serves as an editor for the IEEE Transactions on Sustainable Energy.