We collected a building energy dataset (2 years, hourly data) of unprecedented size (3829 buildings) and variety (75 programs). And using machine learning, we discovered three fundamental load shape profiles that characterize the temporal energy use in any of the buildings. The existence of Read more 

The journal Sustainable Cities and Society has published our paper Fusing TensorFlow with building energy simulation for intelligent energy management in smart cities led by our awesome PhD student Jose. We have developed CitySim, a framework to study multi-agent reinforcement learning using Read more 

Our paper Reinforcement learning for demand response: A review of algorithms and modeling techniques led by IEL's PhD student Jose has been published in Applied Energy. We're thrilled that it has been selected by the editors to be included into the Special Section Progress in Applied Energy. J.R. Read more 

We have investigated experimentally the use of Reinforcement Learning for lighting control in our own offices. The results are awesome and now published in Building & Environment. J. Park, T. Dougherty, H. Fritz, Z. Nagy, LightLearn: An adaptive and occupant centered controller for lighting Read more 

Our paper in collaboration with Prof. Leibowicz has been accepted for publication in Applied Energy. It address decarbonization pathways of residential building systems using Austin, TX as an example. Leibowicz, B.D.,  Lanham, C.M.,  Brozynski, M.T.Vázquez-Canteli, J.R., Castillo, N., and Nagy, Read more