(Virtual) Seminar Series | Operations Research Helps the Optimal Bidding of Virtual Power Plants
Virtual Seminar by Dong Gu Choi
Associate Professor, Department of Industrial and Management Engineering
Adjunct Professor, School of Artificial Intelligence Engineering
POSTECH, South Korea
As distributed energy resources (DERs) continue to emerge, a new cloud-based IT platform business model, the virtual power plant (VPP), is being introduced into the electricity market. The competitiveness of VPPs mainly depends on data analytics and operational technologies. In this study, we focus on the optimal bidding decision problem in the day-ahead market. The bidding decision is a VPP's commitment to supply the market with electricity from uncertain DERs, thereby affecting the VPP's profits. Based on a collaboration with a VPP company in South Korea, we formulate a Markov decision process model for the problem and use a stochastic dynamic programming-based solution approach. Through a pilot test based on real data, we verify the performance and practicality of our proposed model and solution approach.
Dong Gu Choi received B.S. in industrial engineering from KAIST, South Korea, and an M.S. and a Ph.D. in industrial engineering from Georgia Institute of Technology, U.S.A. After earning his Ph.D., he worked at the Korea Institute of Energy Research. He is currently an Associate Professor in the Department of Industrial and Management Engineering and Adjunct Professor in the School of Artificial Intelligence Engineering at POSTECH, South Korea. His research interests include multi-period portfolio optimization, reinforcement learning, multi-agent learning, and applications in energy and environmental systems.