深度强化学习用于热带空气自由冷却数据中心控制
Deep Reinforcement Learning for Tropical Air Free-Cooled Data Center Control
摘要：
由于全年环境温度和相对湿度（RH）较高的独特挑战，热带地区还没有空气自由冷却数据中心（DC）。由于监管机构要求提高DC温度设定值，因此可以承受更高温度和RH的服务器的可用性不断增加，这揭示了热带地区空气自由冷却DC的可行性。然而，由于复杂的温湿动力学，在热带地区操作空气自由冷却DC通常需要对供应空气条件进行自适应控制以维持服务器的计算性能和可靠性。本文研究了在一个自由冷却的热带直流系统中控制送风温度和相对湿度低于一定阈值的问题。为了实现这一目标，我们将控制问题表述为马尔可夫决策过程，并应用深度强化学习（DRL）来学习控制策略，在满足送风温度和RH要求的同时最大限度地减少冷却能量。我们还开发了一个受约束的日间行车线的解决方案，以提高性能。基于从空气自由冷却试验台收集的真实数据跟踪的广泛评估以及无约束和约束DRL方法以及其他两种基线方法之间的比较显示了我们提出的解决方案的优越性能。
英文摘要：
Air free-cooled data centers (DCs) have not existed in the tropical zone due to the unique challenges of year-round high ambient temperature and relative humidity (RH). The increasing availability of servers that can tolerate higher temperatures and RH due to the regulatory bodies' prompts to raise DC temperature setpoints sheds light upon the feasibility of air free-cooled DCs in tropics. However, due to the complex psychrometric dynamics, operating the air free-cooled DC in tropics generally requires adaptive control of supply air condition to maintain the computing performance and reliability of the servers. This paper studies the problem of controlling the supply air temperature and RH in a free-cooled tropical DC below certain thresholds. To achieve the goal, we formulate the control problem as Markov decision processes and apply deep reinforcement learning (DRL) to learn the control policy that minimizes the cooling energy while satisfying the requirements on the supply air temperature and RH. We also develop a constrained DRL solution for performance improvements. Extensive evaluation based on real data traces collected from an air free-cooled testbed and comparisons among the unconstrained and constrained DRL approaches as well as two other baseline approaches show the superior performance of our proposed solutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
