Data Center Cooling Using Model-Predictive Control
Abstract
Despite impressive recent advances in reinforcement learning (RL), its deployment in real-world physical systems is often complicated by unexpected events, limited data, and the potential for expensive failures. In this paper, we describe an application of RL “in the wild” to the task of regulating temperatures and airflow inside a large-scale data center (DC). Adopting a data-driven, model-based approach, we demonstrate that an RL agent with little prior knowledge is able to effectively and safely regulate conditions on a server floor after just a few hours of exploration, while improving operational efficiency relative to existing PID controllers.
Cite
Text
Lazic et al. "Data Center Cooling Using Model-Predictive Control." Neural Information Processing Systems, 2018.Markdown
[Lazic et al. "Data Center Cooling Using Model-Predictive Control." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/lazic2018neurips-data/)BibTeX
@inproceedings{lazic2018neurips-data,
title = {{Data Center Cooling Using Model-Predictive Control}},
author = {Lazic, Nevena and Boutilier, Craig and Lu, Tyler and Wong, Eehern and Roy, Binz and Ryu, Mk and Imwalle, Greg},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {3814-3823},
url = {https://mlanthology.org/neurips/2018/lazic2018neurips-data/}
}