面向数据中心绿色可靠运行的强化学习方法

doi:10.11959/j.issn.2096-6652.202036

Abstract

Abstract:

It is of significant social and economical impact to achieve green and reliable operation of data center.The optimization and control methods for green and reliable data center were reviewed briefly.An event-based reinforcement learning approach for improving the energy efficiency was developed.And a method to improve the accuracy of battery lifetime forecasting was developed.

Key words: data center, cyber physical energy system, reinforcement learning, event-based optimization

CLC Number:

TP29

Qing-Shan JIA, Jingxian TANG, Junjie WU, et al. Reinforcement learning for green and reliable data center[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 341-347.

Figures/Tables 7

References 16

[1]	NICOLA J . How to stop data centres from gobbling up the world’s electricity[J]. Nature, 2018,561(7722): 163-166.
[2]	ISO/IEC. Information technology - data ceners - key performance indicators - part 2:power usage effectiveness:30134-2:2016[S]. 2016.
[3]	BULLARD N . Energy efficiency is a hot problem for big tech’s data centers[Z]. 2019.
[4]	SHEHABI A , SMITH S , SARTOR D ,et al. United states data center energy usage report[R]. 2016.
[5]	张泉, 李震 . 数据中心节能技术与应用[M]. 北京: 机械工业出版社, 2018.
	ZHANG Q , LI Z . Energy saving technology for data center and applicaitons[M]. Beijing: China Machine Press, 2018.
[6]	腾讯数据中心. 致敬经典——腾讯第三代数据中心[Z]. 2020.
	Tencent Data Centers. To classic - three generations of Tencent data centers[Z]. 2020.
[7]	LI Y L , WEN Y G , GUAN K L ,et al. Transforming cooling optimization for green data center via deep reinforcement learning[J]. IEEE Transactions on Cybernetics, 2019,50(5): 2002-2013.
[8]	RAN Y Y , HU H , ZHOU X ,et al. DeepEE:joint optimization of job scheduling and cooling control for data center energy efficiency using deep reinforcement learning[C]// IEEE 39th International Conference on Distributed Computing Systems. Piscataway:IEEE Press, 2019: 645-655.
[9]	YI D L , ZHOU X , WEN Y G ,et al. Toward efficient compute-intensive job allocation for green data centers:a deep reinforcement learning approach[C]// IEEE 39th International Conference on Distributed Computing Systems. Piscataway:IEEE Press, 2019: 634-644.
[10]	PE/ESSB-Energy Storage ＆ Stationary Battery Committee. IEEE 1188-2005-IEEE recommended practice for maintenance,testing,and replacement of valve-regulated lead-acid (VRLA) batteries for stationary applications[S]. 2006.
[11]	贾庆山, 杨玉, 夏俐 ,等. 基于事件的优化方法简介及其在能源互联网中的应用[J]. 控制理论与应用, 2018,35(1): 32-40.
	JIA Q S , YANG Y , XIA L ,et al. A tutorial on event-based optimization with application in energy Internet[J]. Control Theory and Applications, 2018,35(1): 32-40.
[12]	JIA Q S , WU J J , WU Z J ,et al. Event-based HVAC control-a complexity-based approach[J]. IEEE Transactions on Automation Science and Engineering, 2018,15(4): 1909-1919.
[13]	NEWMAN R H . Advantages and disadvantages of valve-regulated,lead/acid batteries[J]. Journal of Power Sources, 1994,52(1): 149-153.
[14]	TANG J X , DU J H , LIN Y T ,et al. Predictive maintenance of VRLA batteries in UPS towards reliable data centers[C]// IFAC World Congress.[S.l.:s.n.], 2020.
[15]	夏元清, 高润泽, 林敏 ,等. 绿色能源互补智能电厂云控制系统研究[J]. 自动化学报, 2020,46(9): 1844-1868.
	XIA Y Q , GAO R Z , LIN M ,et al. Green energy complementary based on intelligent power plant cloud control system[J]. Acta Automatica Sinica, 2020,46(9): 1844-1868.
[16]	王飞跃, 曹东璞, 魏庆来 . 强化学习:迈向知行合一的智能机制与算法[J]. 智能科学与技术学报, 2020,2(2): 101-106.
	WANG F Y , CAO D P , WEI Q L . Reinforcement learning:toward action-knowledge merged intelligent mechanisms and algorithms[J]. Chinese Journal of Intelligent Science and Technology, 2020,2(2): 101-106.

Metrics

Recommended 0

No Suggested Reading articles found!

对比项	参数类型	参数名称	参数值
房间	设定值	尺寸/m²	36
	设定值	天花板高度/m	4.5
	设定值	高架地板高度/m	0.64
空调	设定值	最大显冷量/kW	45
	设定值	冷却水进水温度/℃	14
	设定值	冷却水最大流量/(m³/s)	0.002 9
	设定值	总标称制冷流量/(m³/s)	3.6
	控制值	送风温度设定点/℃	18～27
	控制值	风机转速	0～100%
机柜	设定值	数量/个	3
	设定值	插槽数/个	52
	设定值	IT设备数/台	1.5
	设定值	单台IT设备最大功率/ kW	0.6
	设定值	单台IT设备负载率	0～100%

Reinforcement learning for green and reliable data center

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 16

Related Articles 15

Metrics

Recommended 0

[1]	Zhou YU, Jing BI, Haitao YUAN. A path planning method for complex naval battle field based on an improved DQN algorithm [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(3): 418-425.
[2]	Shuai MA, Qiming FU, Jianping CHEN, Fan FENG, You LU, Zhengwei LI, Shunian QIU. HVAC model-free optimal control method based on double-pools DQN [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(3): 426-444.
[3]	Yuxiang SUN, Yihui PENG, Bin LI, Jiawei ZHOU, Xinlei ZHANG, Xianzhong ZHOU. Overview of intelligent game:enlightenment of game AI to combat deduction [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(2): 157-173.
[4]	De XU, Fangbo QIN. Research development on automated robotic peg-in-hole assembly [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(2): 200-211.
[5]	Jiacheng LIU, Xiangwen ZHANG. TD3-based energy management strategy for hybrid energy storage system of electric vehicle [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(2): 277-287.
[6]	Pu FENG, Wenjun WU, Jie LUO, Xin YU, Yongkai TIAN. Emergence measurement of robot swarm intelligence based on swarm entropy [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(1): 65-74.
[7]	Han WANG, Yang YU, Yuan JIANG. A cooperative multi-agent reinforcement learning algorithm based on dynamic self-selection parameters sharing [J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(1): 75-83.
[8]	Zhiqiang HU. The framework model on internal mechanism of big data intelligent command and control [J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(1): 101-109.
[9]	Zhaoyang LIU, Chaoxu MU, Changyin SUN. An overview on algorithms and applications of deep reinforcement learning [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 314-326.
[10]	Jinna LI, Weiran CHENG. An overview of optimal consensus for data driven multi-agent system based on reinforcement learning [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 327-340.
[11]	Tao LI, Qinglai WEI. Intelligent heating temperature control system based on deep reinforcement learning [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 348-353.
[12]	Rizhong WANG, Huiping LI, Di CUI, Demin XU. Depth control of autonomous underwater vehicle using deep reinforcement learning [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 354-360.
[13]	Huiqiao FU, Kaiqiang TANG, Guizhou DENG, Xinpeng WANG, Chunlin CHEN. Motion planning for hexapod robot using deep reinforcement learning [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 361-371.
[14]	Yingying LIU, Zhanshan WANG. Output synchronization of heterogeneous multi-agent system:a reinforcement learning approach based on data [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 394-400.
[15]	Yu SHEN,Jinpeng HAN,Lingxi LI,Fei-Yue WANG. AI in game intelligence—from multi-role game to parallel game [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(3): 205-213.