Skip to main content

Jacobs School Events

Intelligence in the smart grid: Online optimization under uncertainty and a connection to Model Predictive Control

Nov 19, 2012 10.00am - Intelligence in the smart grid: Online optimization under uncertainty and a connection to Model Predictive Control

Location: Booker Conference Room (#2512)
Sponsored By: Prof. Shaya Fainman

Incorporating large quantities of intermittent renewable power into the grid highlights the need for intelligent scheduling of generation, loads and storage requiring inputs from computer scientists, communication engineers and practitioners of operations research. In this talk, we focus on one approach to these problems, showing how to model many smart grid resource allocation problems as a Markov Decision Process with short term predictions of (or lookahead into) future rewards. We show that the natural Model Predictive Control (MPC) based algorithm for this class of problems can perform arbitrarily badly because of  temporal uncertainty. We then describe online algorithms, both randomized and deterministic, to handle time varying uncertainty providing the first known theoretical justification for discounting in MPC. Time permitting we will also talk about recent work on multi-agent models for power systems and highlight important problems that require increased intelligence in the smart grid.
This talk will be accessible to a wide audience since we will give examples and intuition in lieu of detailed proofs. It may be of particular interest to those interested in AI, control theory, machine learning, MDPs and smarter energy systems.

Contact for Event

Aneta Siekiera
Phone: 858-534-7013
Email: asiekiera@eng.ucsd.edu

Speaker Bio

Balakrishnan Narayanaswamy received his PhD from the department of Electrical and Computer Engineering (ECE) at Carnegie Mellon University in 2011, after which he joined the IBM Research Lab in Bangalore, India. His research interests lie at the intersection of AI, optimization, learning and inference particularly using them to understand, model and combat noise and uncertainty in real world applications.

« View Events