Electrical Engineering, Operations Research and Machine Learning for Power Distribution

Joint DSI Sense, Collect & Move Data, EE, and IEOR Seminar
Date:
 2:00pm, February 15, 2018
Location:  EE Conference Room, MUDD 1306
Speaker: Dr. Michael Chertkov Los Alamos National Lab

Abstract:In this three-part talk we will give a subjective perspective of the author on applied mathematics, physics and statistics challenges in control, optimization and operations of resilient electric power distribution.

First, we discuss stochastic optimal control of an aggregated ensemble of flexible, thermostatically controlled electric loads in distribution grids with network constraints. Scenario of limited communications and significant uncertainty due to renewables (solar and wind) is considered. We describe a Markov Decision Process formulation of the problem, discuss an efficient algorithm and demonstrate its performance on IEEE test cases.

Second, we review new ideas and first results on application of the Graphical Models approach to optimization problems of network flow type with additional constraints related to the physics of the flow. We illustrate the general concepts by presenting GM solution for optimal power flow problem.

Third, we present operational application of what can be called “physics informed machine learning” to reconstructing topology and parameters of a power distribution system with minimal observability.

The talk is based on arxiv:1710.10727;1710.09924;1710.09738;1702.01890;1701.04941;1606.06512

Biography: Dr. Chertkov's areas of interest include statistical and mathematical physics applied to energy and communication networks, machine learning, control theory, information theory, computer science, fluid mechanics and optics. Dr. Chertkov received his Ph.D. in physics from the Weizmann Institute of Science in 1996, and his M.Sc. in physics from Novosibirsk State University in 1990.

After his Ph.D., Dr. Chertkov spent three years at Princeton University as a R.H. Dicke Fellow in the Department of Physics. He joined Los Alamos National Lab in 1999, initially as a J.R. Oppenheimer Fellow in the Theoretical Division. He is now a technical staff member in the same division. Dr. Chertkov has published more than 190 papers in these research areas. He is an editor of the Journal of Statistical Mechanics (JSTAT), associate editor of IEEE Transactions on Control of Network Systems, member of the Editorial Board of Scientific Reports (Nature Group), a fellow of the American Physical Society (APS) and a senior member of IEEE.

Host: Professor Dan Bienstock


500 W. 120th St., Mudd 1310, New York, NY 10027    212-854-3105               
©2014 Columbia University