2018/08/21 by Takao Moriyama, Giovanni De Magistris, Moriyama, Takao +9 · 13 citations
Computer Science · Engineering · #Artificial intelligence #Computer science #Control (management) #Evolutionary Algorithms and Applications #FOS: Electrical engineering #Heat Transfer and Optimization #Machine learning #Reinforcement Learning in Robotics #Reinforcement learning #Systems and Control (eess.SY) #Testbed #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1808.10427
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2018/08/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Common approaches to control a data-center cooling system rely on approximated system/environment models that are built upon the knowledge of mechanical cooling and electrical and thermal management. These models are difficult to design and often lead to suboptimal or unstable performance. In this paper, we show how deep reinforcement learning techniques can be used to control the cooling system of a simulated data center. In contrast to common control algorithms, those based on reinforcement learning techniques can optimize a system's performance automatically without the need of explicit model knowledge. Instead, only a reward signal needs to be designed. We evaluated the proposed algorithm on the open source simulation platform EnergyPlus. The experimental results indicate that we can achieve 22% improvement compared to a model-based control algorithm built into the EnergyPlus. To encourage the reproduction of our work as well as future research, we have also publicly released an open-source EnergyPlus wrapper interface directly compatible with existing reinforcement learning frameworks.