Data Center Cooling Using Model-predictive Control

Authors:
Nevena Lazic Google
Craig Boutilier Google
Tyler Lu Google
Eehern Wong Google
Binz Roy Google
MK Ryu Google
Greg Imwalle Google

Introduction:

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, the authors describe an application of RL “in the wild” to the task of regulating temperatures and airflow inside a large-scale data center (DC).

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.

You may want to know: