Servers and data centers energy performance metrics

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

A thermodynamic approach for evaluating energy performance (productivity) of information technology (IT) servers and data centers is presented. This approach is based on the first law efficiency to deliver energy performance metrics defined as the ratio of the useful work output (server utilization) to the total energy expanded to support the corresponding computational work. These energy performance metrics will facilitate proper energy evaluation and can be used as indicators to rank and classify IT systems and data centers regardless of their size, capacity or physical location. The current approach utilizes relevant and readily available information such as the total facility power, the servers' idle power, the average servers' utilization, the cooling power and the total IT equipment power. Experimental simulations and analysis are presented for a single and a dual-core IT server, and similar analysis is extended to a hypothetical data center. The current results show that the server energy efficiency increases with increasing CPU utilization and is higher for a multi-processor server than for a single-processor server. This is also true at the data center level however with a lower relative performance indicator value than for the server level.

Original languageEnglish
Pages (from-to)562-569
Number of pages8
JournalEnergy and Buildings
Volume80
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes

Fingerprint

Servers
Information technology
Program processors
Energy efficiency
Productivity
Thermodynamics
Cooling

Keywords

  • Cooling
  • Data center
  • DC performance metric
  • DC productivity metric
  • Efficiency metric
  • Energy
  • Power
  • PUE
  • Server efficiency

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Cite this

Servers and data centers energy performance metrics. / Beitelmal, Abdlmonem; Fabris, D.

In: Energy and Buildings, Vol. 80, 01.01.2014, p. 562-569.

Research output: Contribution to journalArticle

@article{7f4ed0c522de45b3a9fcc163d8174edd,
title = "Servers and data centers energy performance metrics",
abstract = "A thermodynamic approach for evaluating energy performance (productivity) of information technology (IT) servers and data centers is presented. This approach is based on the first law efficiency to deliver energy performance metrics defined as the ratio of the useful work output (server utilization) to the total energy expanded to support the corresponding computational work. These energy performance metrics will facilitate proper energy evaluation and can be used as indicators to rank and classify IT systems and data centers regardless of their size, capacity or physical location. The current approach utilizes relevant and readily available information such as the total facility power, the servers' idle power, the average servers' utilization, the cooling power and the total IT equipment power. Experimental simulations and analysis are presented for a single and a dual-core IT server, and similar analysis is extended to a hypothetical data center. The current results show that the server energy efficiency increases with increasing CPU utilization and is higher for a multi-processor server than for a single-processor server. This is also true at the data center level however with a lower relative performance indicator value than for the server level.",
keywords = "Cooling, Data center, DC performance metric, DC productivity metric, Efficiency metric, Energy, Power, PUE, Server efficiency",
author = "Abdlmonem Beitelmal and D. Fabris",
year = "2014",
month = "1",
day = "1",
doi = "10.1016/j.enbuild.2014.04.036",
language = "English",
volume = "80",
pages = "562--569",
journal = "Energy and Buildings",
issn = "0378-7788",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Servers and data centers energy performance metrics

AU - Beitelmal, Abdlmonem

AU - Fabris, D.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - A thermodynamic approach for evaluating energy performance (productivity) of information technology (IT) servers and data centers is presented. This approach is based on the first law efficiency to deliver energy performance metrics defined as the ratio of the useful work output (server utilization) to the total energy expanded to support the corresponding computational work. These energy performance metrics will facilitate proper energy evaluation and can be used as indicators to rank and classify IT systems and data centers regardless of their size, capacity or physical location. The current approach utilizes relevant and readily available information such as the total facility power, the servers' idle power, the average servers' utilization, the cooling power and the total IT equipment power. Experimental simulations and analysis are presented for a single and a dual-core IT server, and similar analysis is extended to a hypothetical data center. The current results show that the server energy efficiency increases with increasing CPU utilization and is higher for a multi-processor server than for a single-processor server. This is also true at the data center level however with a lower relative performance indicator value than for the server level.

AB - A thermodynamic approach for evaluating energy performance (productivity) of information technology (IT) servers and data centers is presented. This approach is based on the first law efficiency to deliver energy performance metrics defined as the ratio of the useful work output (server utilization) to the total energy expanded to support the corresponding computational work. These energy performance metrics will facilitate proper energy evaluation and can be used as indicators to rank and classify IT systems and data centers regardless of their size, capacity or physical location. The current approach utilizes relevant and readily available information such as the total facility power, the servers' idle power, the average servers' utilization, the cooling power and the total IT equipment power. Experimental simulations and analysis are presented for a single and a dual-core IT server, and similar analysis is extended to a hypothetical data center. The current results show that the server energy efficiency increases with increasing CPU utilization and is higher for a multi-processor server than for a single-processor server. This is also true at the data center level however with a lower relative performance indicator value than for the server level.

KW - Cooling

KW - Data center

KW - DC performance metric

KW - DC productivity metric

KW - Efficiency metric

KW - Energy

KW - Power

KW - PUE

KW - Server efficiency

UR - http://www.scopus.com/inward/record.url?scp=84904327607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904327607&partnerID=8YFLogxK

U2 - 10.1016/j.enbuild.2014.04.036

DO - 10.1016/j.enbuild.2014.04.036

M3 - Article

AN - SCOPUS:84904327607

VL - 80

SP - 562

EP - 569

JO - Energy and Buildings

JF - Energy and Buildings

SN - 0378-7788

ER -