Simulation and experimental research on the optimization of airflow organization and energy saving in data centers using air deflectors

Author:

Ma Boyang,Liu Haiyong,Du Yahui,Yang Xiaochen,Zhou Zhihua,Lu Jie,Chen Ying

Abstract

The airflow organization of the data center directly affects the temperature control performance and the energy efficiency of the cooling equipment. The servers at the bottom of the rack usually suffer from insufficient airflow rate and poor cooling effect. This is because of the limited distance between the bottom servers and the perforated floor, and the small horizontal velocity of the supply air flow. This study aims to improve the uniformity of the cooling airflow in the vertical direction of the rack by the air deflectors, thereby further improving the overall airflow organization in the data center. The size and installation of the deflectors in the data center were optimized according to both the experiment and numerical simulation results. From the results, it is recommended to install the deflector with a width of 100 mm at an angle of 45° under the perforated floor for the rack with the single-side airflow supply. For the rack with the double-side airflow supply, the width of the deflector should be 100 mm and installed at an angle of 30° to the perforated floor to achieve the best airflow distribution. Consequently, the intake airflow rate for the bottom servers significantly increased, and the occurrence of the local hot spots was effectively reduced. The numerical simulation of the airflow organization with and without the deflector was conducted by ANSYS. The results show that, the installation of the deflectors increased the inlet airflow rate for the rack by 16.98% and improved the energy efficiency of the dater center air conditioners by 1.98%.

Publisher

Universe Scientific Publishing Pte. Ltd.

Reference36 articles.

1. China Refrigeration Society Data Center Cooling Working Group. China Data Center Cooling Technology Annual Development Research Report 2019 (Chinese). China Architecture & Building Press; 2020.

2. Ajayi O, Heymann R. Data centre day-ahead energy demand prediction and energy dispatch with solar PV integration. Energy Reports. 2021; 7: 3760–3774. doi: 10.1016/j.egyr.2021.06.062

3. Du Y, Zhou Z, Yang X, et al. Dynamic thermal environment management technologies for data center: A review. Renew Sustain Energy Rev. 2023; 187: 113761. doi: 10.1016/j.rser.2023.113761

4. Ristic B, Madani K, Makuch Z. The water footprint of data centers. Sustain. 2015; 7: 11260–11284. doi: 10.3390/su70811260

5. Shehabi A, Horvath A, Nazaroff W, et al. Energy implications of economizer use in California data centers. In: Proceedings of the 2008 ACEEE Conference, Asilomar Conference Center; 17–22 August 2008; Pacific Grove, CA, USA. pp. 319–30.

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3