Cooperatively Improving Data Center Energy Efficiency Based on Multi-Agent Deep Reinforcement Learning

doi:10.3390/en14082071

	Cooperatively Improving Data Center Energy Efficiency Based on Multi-Agent Deep Reinforcement Learning
	Chi, Ce 1,4,5; Ji, Kaixuan 1,4,5; Song, Penglei 3; Marahatta, Avinab 2; Zhang, Shikui 3; Zhang, Fa 1,5; Qiu, Dehui 3; Liu, Zhiyong 1,5
刊名	ENERGIES
	2021-04-01
卷号	14 期号:8 页码:32
关键词	data center energy efficiency deep reinforcement learning multi-agent scheduling algorithm cooling system
DOI	10.3390/en14082071
英文摘要	The problem of high power consumption in data centers is becoming more and more prominent. In order to improve the energy efficiency of data centers, cooperatively optimizing the energy of IT systems and cooling systems has become an effective way. In this paper, a model-free deep reinforcement learning (DRL)-based joint optimization method MAD3C is developed to overcome the high-dimensional state and action space problems of the data center energy optimization. A hybrid AC-DDPG cooperative multi-agent framework is devised for the improvement of the cooperation between the IT and cooling systems for further energy efficiency improvement. In the framework, a scheduling baseline comparison method is presented to enhance the stability of the framework. Meanwhile, an adaptive score is designed for the architecture in consideration of multi-dimensional resources and resource utilization improvement. Experiments show that our proposed approach can effectively reduce energy for data centers through the cooperative optimization while guaranteeing training stability and improving resource utilization.
资助项目	National Key Research and Development Program of China[2017YFB1010001] ; National Natural Science Foundation of China[61520106005] ; National Natural Science Foundation of China[61761136014]
WOS研究方向	Energy & Fuels
语种	英语
出版者	MDPI
WOS记录号	WOS:000644128100001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17827]
专题	中国科学院计算技术研究所
通讯作者	Liu, Zhiyong
作者单位	1.6 South Kexueyuan Rd, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China 3.Capital Normal Univ, Informat Engn Coll, Beijing 100048, Peoples R China 4.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, High Performance Comp Res Ctr, Beijing 100095, Peoples R China
推荐引用方式 GB/T 7714	Chi, Ce,Ji, Kaixuan,Song, Penglei,et al. Cooperatively Improving Data Center Energy Efficiency Based on Multi-Agent Deep Reinforcement Learning[J]. ENERGIES,2021,14(8):32.
APA	Chi, Ce.,Ji, Kaixuan.,Song, Penglei.,Marahatta, Avinab.,Zhang, Shikui.,...&Liu, Zhiyong.(2021).Cooperatively Improving Data Center Energy Efficiency Based on Multi-Agent Deep Reinforcement Learning.ENERGIES,14(8),32.
MLA	Chi, Ce,et al."Cooperatively Improving Data Center Energy Efficiency Based on Multi-Agent Deep Reinforcement Learning".ENERGIES 14.8(2021):32.