@www{luo2022controlling,
title = {Controlling Commercial Cooling Systems Using Reinforcement Learning},
author = {Luo, Jerry and Paduraru, Cosmin and Voicu, Octavian and Chervonyi, Yuri and Munns, Scott and Li, Jerry and Qian, Crystal and Dutta, Praneet and Davis, Jared Quincy and Wu, Ningjia and Yang, Xingwei and Chang, Chu-Ming and Li, Ted and Rose, Rob and Fan, Mingyan and Nakhost, Hootan and Liu, Tinglin and Kirkman, Brian and Altamura, Frank and Cline, Lee and Tonker, Patrick and Gouker, Joel and Uden, Dave and Bryan, Warren Buddy and Law, Jason and Fatiha, Deeni and Satra, Neil and Rothenberg, Juliet and Waraich, Mandeep and Carlin, Molly and Tallapaka, Satish and Witherspoon, Sims and Parish, David and Dolan, Peter and Zhao, Chenyu and Mankowitz, Daniel J.},
doi = {10.48550/ARXIV.2211.07357},
url = {https://arxiv.org/abs/2211.07357},
urldate = {2022-12-20},
keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), Systems and Control (eess.SY), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
publisher = {arXiv},
year = {2022},
month = {12},
copyright = {Creative Commons Attribution 4.0 International},
abstract={This paper is a technical overview of DeepMind and Google's recent work on reinforcement learning for controlling commercial cooling systems. Building on expertise that began with cooling Google's data centers more efficiently, we recently conducted live experiments on two real-world facilities in partnership with Trane Technologies, a building management system provider. These live experiments had a variety of challenges in areas such as evaluation, learning from offline data, and constraint satisfaction. Our paper describes these challenges in the hope that awareness of them will benefit future applied RL work. We also describe the way we adapted our RL system to deal with these challenges, resulting in energy savings of approximately 9\% and 13\% respectively at the two live experiment sites.},
}