Data Center Cooling using Model-predictive Control

Tyler Lu
MK Ryu
Eehern Jay Wong
Binz Roy
Greg Imwalle
Proceedings of the Thirty-second Conference on Neural Information Processing Systems (NeurIPS-18), Montreal, QC (2018), pp. 3818-3827

Abstract

Despite the impressive advances in reinforcement learning (RL) algorithms, their deployment to real-world physical systems is often complicated by unexpected events 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 is able to effectively and safely regulate conditions inside a server floor in just a few hours, while improving operational efficiency relative to existing controllers.

Research Areas