Autonomous Buildings: Data-Driven Control of HVAC Systems

Abstract: Buildings account for 75% of the electricity and 34% of the primary energy consumed in the US. A large fraction of that energy is due to HVAC (heating, ventilation, and air conditioning) equipment. Optimal control of building HVAC equipment can reduce energy use in a cost-effective manner with existing equipment. Yet, deployment of such control techniques has been slow.

We argue that the slow adoption is due to lack of autonomy. In particular, the models used in the controllers need considerable human expertise to tune to a specific building, and cannot adapt to the changes in a building over time. Due to the impact the indoor climate has on occupant health and comfort, any climate control system must operate reliably 24 hours a day, 7 days a week, and 365 days a year, without requiring frequent intervention from human expert(s).

In this talk we describe an approach to achieving autonomy through a purely data-driven identification of control-oriented models. Because of the structural properties of these models, they can be updated (learned) on the fly from data, and thus they can form the backbone of an autonomous control system. The identification method uses recent advances from the field of compressed sensing in which $\ell_1$ regularization is used to seek sparse solutions to an optimization problem. The optimization problem is formulated in a way to include both temperature and humidity (sensible and latent heat) considerations, which is ignored by most optimal control formulations until now. Apart from simulation results, we describe a living-laboratory at the University of Florida to test the control techniques.

Bio: Prabir Barooah is an Associate Professor of Mechanical and Aerospace Engineering at the University of Florida, where he has been since 2007. He received the Ph.D. degree in Electrical and Computer Engineering in 2007 from the University of California, Santa Barbara. From 1999 to 2002 he was a research engineer at United Technologies Research Center, East Hartford, CT. He received the M. S. degree in Mechanical Engineering from the University of Delaware in 1999 and the B. Tech.  degree in Mechanical Engineering from the Indian Institute of Technology, Kanpur, in 1996. Dr. Barooah is the winner of the ASEE-SE (American Society of Engineering Education, South East Section) outstanding researcher award (2012), NSF CAREER award (2010), General Chairs' Recognition Award for Interactive papers at the 48th IEEE Conference on Decision and Control (2009), best paper award at the 2nd Int. Conf. on Intelligent Sensing and Information Processing (2005), and NASA group achievement award (2003).