home · mobile · calendar · colloquia · 2011-2012 · 

Colloquium - Kolter

Learning, Inference, and Control for Sustainable Energy
MIT Computer Science and Artificial Intelligence Laboratory

Sustainable energy issues pose one of the largest challenges facing society: 84% of the world's energy currently comes from fossil fuels, raising major issues with climate change, energy security, and the long-term availability of these sources. Although energy domains span a huge range of different areas, a common theme in many modern energy tasks is the availability of large amounts of data, and the need to learn models, make inferences, and control the system based upon this data. These are problems that require new methods in machine learning, probabilistic inference, and control, and where such algorithms can have a profound impact on the energy space. In this talk I will look at two particular tasks spanning different extremes of energy consumption and generation and show how new algorithmic methods can play a pivotal role in each.

First, on the energy consumption side, I will present new techniques for energy disaggregation, the task of taking an aggregate power signal and decomposing it into separate devices. This ability helps us understand how energy is consumed in a building, and studies have shown that just presenting this information to users can directly lead to large energy savings. Unlike previous approaches to this problem, my work considers models that look jointly at the entire signal and exploit the rich temporal structure of the data. The key technical challenge here is the task of making inferences in these high-dimensional, factorized, temporal models, and I will present new algorithms I have developed, based upon convex relaxations of inference, that greatly outperform existing approaches on this task. Second, on the energy generation side, I will present work on maximizing power output for wind turbines in low-wind conditions. In particular, I will present a novel policy learning approach, based upon trust-region optimization, which is able to maximize power using much less data than existing learning techniques. We demonstrate that the method produces 30% more power than a purely model-based approach on an experimental wind turbine.

J. Zico Kolter is a postdoctoral fellow in the Computer Science and Artificial Intelligence Laboratory at MIT. He received his his PhD in Computer Science from Stanford University in 2010 and his BS from Georgetown University in 2005. His research revolves around sustainable energy domains, with a focus on core learning, inference, and control tasks within this space. His work in this area include projects in energy disaggregation, wind turbine control, and modeling building energy consumption. His past work also looked at learning and control methods in other domains, including autonomous cars in extreme maneuvers, quadruped locomotion, and feature selection in reinforcement learning. He is the recipient of an NSF Computing Innovation Postdoctoral Fellowship, a former recipient of an NSF Graduate Research Fellowship, and has received best paper awards at the SIGKDD and AIAA Infotech@Aerospace conferences.

Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
May 5, 2012 (14:13)