Calibrating building energy models using supercomputer trained machine learning agents

Building Energy Modeling (BEM) is an approach to model the energy usage in buildings for design and retrofit purposes. EnergyPlus is the flagship Department of Energy software that performs BEM for different types of buildings. The input to EnergyPlus can often extend in the order of a few thousand parameters which have to be calibrated manually by an expert for realistic energy modeling. This makes it challenging and expensive thereby making building energy modeling unfeasible for smaller projects. In this paper, we describe the “Autotune” research which employs machine learning algorithms to generate agents for the different kinds c ©2013 Association for Computing Machinery. ACM acknowledges that this contribution was authored or coauthored by an employee, contractor or affiliate of the United States government. As such, the United States Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only. ∗Dr. Sanyal is with the Building Technologies Research and Integration Center at the Oak Ridge National Laboratory, One Bethel Valley Road, P.O. Box 2008, MS-6324, Oak Ridge, TN 37831-6324. †Dr. New is with the Building Technologies Research and Integration Center at the Oak Ridge National Laboratory. ‡Dr. Edwards is with the Ad Products’ Platform Measurement group at Amazon.com, Inc., Wainrright (SEA 23), 535 Terry Ave N., Seattle, WA 98109. §Dr. Parker is professor and associate head of the EECS department at The University of Tennessee in Knoxville, Min H. Kao Building, Suite 401, 1520 Middle Drive, Knoxville, TN 37996. CCPE Journal of Concurrency and Computation Practice and Experience Copyright 2013 ACM 978-1-4503-2170-9/13/07. . . $15.00. of standard reference buildings in the U.S. building stock. The parametric space and the variety of building locations and types make this a challenging computational problem necessitating the use of supercomputers. Millions of EnergyPlus simulations are run on supercomputers which are subsequently used to train machine learning algorithms to generate agents. These agents, once created, can then run in a fraction of the time thereby allowing cost-effective calibration of building models.