As the penetration of renewable increases and conventional generators retire, the reliability concerns on balancing real-time demand and supply motivate the utilization of demand-side resources. However, residential demands which consist the most significant share of electricity demand are still underutilized in grid operation. Although both industrial and academia are conducting pilot studies and developing theoretical works respectively, they have not been serendipitously connected. Thus, this work performed studies based on actual demand response pilots and the dataset of social-psychology survey. Specifically, we build a model to assess the potential capacity of controllable residential demands based on survey data; we train neural networks to model users’ behavior to enhance DR performance for peak load reduction; and, we implement multi-armed bandit algorithm to exploit demands while exploring stochastic models of these demands. Our preliminary results show that the application of modern learning techniques can help improve the performance of DR pilots in practice. We hope that this work can bridge the gap between DR pilots and theoretical analysis, and eventually unlocking the potential residential demands in grid operation.
Qinran Hu received a B.S degree in electrical engineering from Chien-Shiung Wu College, Southeast University, Nanjing, China in 2010, an M.S. degree and a Ph.D. degree in electrical engineering from The University of Tennessee Knoxville in 2013 and 2015, respectively. From 2015-2018, he worked as a postdoc at Harvard School of Engineering and Applied Science. In Oct. 2018, Dr. Hu joined the School of Electrical Engineering, Southeast University, Nanjing, China.
Dr. Hu’s current research focus includes demand aggregation, power system optimal operation, and electricity market. In the related field, Dr. Hu published 30+ papers (h-index 13), 1 book chapter, 1 patent. He participated many projects from Oak Ridge National Laboratory (ORNL), US Department of Energy, US Electric Power Research Institute, etc., and he, as PI, was awarded the research funds from Harvard provost office on “The technical pathways toward a reliable carbon-free energy system” (USD 112k) and SAC-ABB on “Optimal bidding and assets allocation strategy for generation companies” (USD 260k). Dr. Hu also has some industrial experience. He did internships at ABB Cooperate Research Center (CRC), Raleigh, NC in 2013 and Oak Ridge National Laboratory, Oak Ridge, TN in 2015.