Optimal Design and Modeling of Server Cabinets With In-Row Coolers and Air Conditioning Units in a Modular Data Center

阿什拉1.90 空调 数据中心 计算机科学 环境科学 制冷 能源消耗 工程类 蒸发冷却器 空气冷却 汽车工程 核工程 电气工程 机械工程 气象学 操作系统 物理
作者
Uschas Chowdhury,Walter Adrian Hendrix,Thomas Craft,Willis James,Ankit Sutaria,Dereje Agonafer
标识
DOI:10.1115/ipack2019-6522
摘要

Abstract In a data center, electronic equipment such as server and switches dissipate heat and the corresponding cooling systems contribute to typically 25–35% of total energy consumption. The heat load continues to increase as there is a greater need for miniaturization and convergence. In 2014, data centers in the U.S. consumed an estimated 70 billion kWh, representing about 1.8% of total U.S. electricity consumption. Based on current trend estimates, U.S. data centers are projected to consume approximately 73 billion kWh in 2020 [1]. Many research and strategies are adopted to minimize energy cost. The recommended dry bulb temperature for long-term operation and reliability for air cooling is between 18–27°C and the largest allowable inlet temperature range to operate at is between 5°C and 45°C with American Society of Heating, Refrigeration, and Air-Conditioning Engineers (ASHRAE) enabling much broader allowable zones) [2]. But understanding a proper cooling system is very important especially for thermal management of IT equipment with high heat loads such as 1U or 2U multi-core, high-end servers and blade servers which provide more computing per watt. Many problems like high inlet temperature due to the mixing of hot air with cold air, local hot spots, lower system reliability, increased failure, and downtime may occur. Among many other approaches to managing high-density racks, in-row coolers are used in between racks to provide cold air and minimize local hot spots. This paper describes a computational study being performed by applying in-row coolers for different rack power configuration with and without aisle containment. The power, as well as the number of racks, are varied to study the effect of raised inlet temperature for the IT equipment in a Computational Fluid Dynamics (CFD) model developed in 6SigmaRoom with the help of built-in library items. A comparative analysis is also performed for a typical small-sized non-raised facility to investigate the efficacy and limitations of in-row coolers in thermal management of IT equipment with variation in rack heat load and containment. Several other aspects like a parametric study of variable opening areas of duct between racks and in-row coolers, the variation of operating flow rate and failure scenarios are also studied to find proper flow distribution, uniformity of outlet temperature and predict better performance, energy savings and reliability. The results are presented for general guidance for flexible and quick installation and safe operation of in-row coolers to improve thermal efficiency.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
周小鱼发布了新的文献求助10
3秒前
Kenny发布了新的文献求助30
3秒前
jim完成签到 ,获得积分10
4秒前
文艺的筮完成签到 ,获得积分10
7秒前
w1kend完成签到,获得积分10
7秒前
秋澄完成签到 ,获得积分10
8秒前
Awalong完成签到,获得积分10
9秒前
cc完成签到,获得积分10
9秒前
痛痛痛完成签到,获得积分10
10秒前
灵巧书文发布了新的文献求助10
11秒前
OGB应助WX2024采纳,获得10
11秒前
jack完成签到 ,获得积分10
13秒前
pzc完成签到,获得积分10
14秒前
jun完成签到 ,获得积分10
14秒前
16秒前
开心香岚发布了新的文献求助10
20秒前
22秒前
22秒前
项目多多完成签到,获得积分10
24秒前
25秒前
26秒前
dd发布了新的文献求助10
27秒前
家有宝宝完成签到 ,获得积分10
28秒前
liza完成签到 ,获得积分10
29秒前
yk123发布了新的文献求助10
29秒前
刘一完成签到 ,获得积分10
31秒前
weiwei发布了新的文献求助10
32秒前
跳跃剑心完成签到,获得积分10
32秒前
CodeCraft应助科研小废物采纳,获得10
33秒前
yk123完成签到,获得积分10
37秒前
39秒前
40秒前
41秒前
ran完成签到 ,获得积分10
42秒前
拼搏太英完成签到,获得积分10
43秒前
思源应助眼睛大的冰岚采纳,获得10
43秒前
43秒前
许婉琦发布了新的文献求助10
47秒前
49秒前
50秒前
高分求助中
(禁止应助)【重要!!请各位详细阅读】【科研通的精品贴汇总】 10000
Semantics for Latin: An Introduction 1099
Biology of the Indian Stingless Bee: Tetragonula iridipennis Smith 1000
Robot-supported joining of reinforcement textiles with one-sided sewing heads 700
Thermal Quadrupoles: Solving the Heat Equation through Integral Transforms 500
SPSS for Windows Step by Step: A Simple Study Guide and Reference, 17.0 Update (10th Edition) 500
PBSM: Predictive Bi-Preference Stable Matching in Spatial Crowdsourcing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4126163
求助须知:如何正确求助?哪些是违规求助? 3663727
关于积分的说明 11593076
捐赠科研通 3363425
什么是DOI,文献DOI怎么找? 1848177
邀请新用户注册赠送积分活动 912231
科研通“疑难数据库(出版商)”最低求助积分说明 827935