Optimizing energy consumption for a performance-aware cloud data center in the public sector

Kyungmee Chang, Sangun Park, Hyesoo Kong, Wooju Kim

Research output: Contribution to journalArticle

Abstract

In general, cloud environments are based on the pay-per-use model, whereby clients pay for the information resources provided by cloud service providers. Users rent and use resources as needed while avoiding the high costs of large-scale resource acquisitions, and providers maximize their profits by managing information resources at a minimum cost while upholding service-level agreements. As the number of resources gradually increases, power supply shortages may arise. This study focuses on the fact that the CPU utilization rate of the server running in the data center is less than 30% and idle servers running only the OS consume more than half of the power consumed by hosts running with maximum CPU utilization and speed. Therefore, this study proposes an approach to enhance data center efficiency through improved management of energy consumption. We present a method to minimize energy consumption while processing the same workload, i.e., ultimately reducing the energy consumed by operating servers. Energy consumption and SLA violation rate were used as evaluation metrics of the optimization model to meet the minimum performance target.

Original languageEnglish
Pages (from-to)34-45
Number of pages12
JournalSustainable Computing: Informatics and Systems
Volume20
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Servers
Energy utilization
Program processors
Costs
Profitability
Processing

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{c9e99906262749e5ae3ebacde004c39f,
title = "Optimizing energy consumption for a performance-aware cloud data center in the public sector",
abstract = "In general, cloud environments are based on the pay-per-use model, whereby clients pay for the information resources provided by cloud service providers. Users rent and use resources as needed while avoiding the high costs of large-scale resource acquisitions, and providers maximize their profits by managing information resources at a minimum cost while upholding service-level agreements. As the number of resources gradually increases, power supply shortages may arise. This study focuses on the fact that the CPU utilization rate of the server running in the data center is less than 30{\%} and idle servers running only the OS consume more than half of the power consumed by hosts running with maximum CPU utilization and speed. Therefore, this study proposes an approach to enhance data center efficiency through improved management of energy consumption. We present a method to minimize energy consumption while processing the same workload, i.e., ultimately reducing the energy consumed by operating servers. Energy consumption and SLA violation rate were used as evaluation metrics of the optimization model to meet the minimum performance target.",
author = "Kyungmee Chang and Sangun Park and Hyesoo Kong and Wooju Kim",
year = "2018",
month = "12",
day = "1",
doi = "10.1016/j.suscom.2018.10.003",
language = "English",
volume = "20",
pages = "34--45",
journal = "Sustainable Computing: Informatics and Systems",
issn = "2210-5379",
publisher = "Elsevier USA",

}

Optimizing energy consumption for a performance-aware cloud data center in the public sector. / Chang, Kyungmee; Park, Sangun; Kong, Hyesoo; Kim, Wooju.

In: Sustainable Computing: Informatics and Systems, Vol. 20, 01.12.2018, p. 34-45.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Optimizing energy consumption for a performance-aware cloud data center in the public sector

AU - Chang, Kyungmee

AU - Park, Sangun

AU - Kong, Hyesoo

AU - Kim, Wooju

PY - 2018/12/1

Y1 - 2018/12/1

N2 - In general, cloud environments are based on the pay-per-use model, whereby clients pay for the information resources provided by cloud service providers. Users rent and use resources as needed while avoiding the high costs of large-scale resource acquisitions, and providers maximize their profits by managing information resources at a minimum cost while upholding service-level agreements. As the number of resources gradually increases, power supply shortages may arise. This study focuses on the fact that the CPU utilization rate of the server running in the data center is less than 30% and idle servers running only the OS consume more than half of the power consumed by hosts running with maximum CPU utilization and speed. Therefore, this study proposes an approach to enhance data center efficiency through improved management of energy consumption. We present a method to minimize energy consumption while processing the same workload, i.e., ultimately reducing the energy consumed by operating servers. Energy consumption and SLA violation rate were used as evaluation metrics of the optimization model to meet the minimum performance target.

AB - In general, cloud environments are based on the pay-per-use model, whereby clients pay for the information resources provided by cloud service providers. Users rent and use resources as needed while avoiding the high costs of large-scale resource acquisitions, and providers maximize their profits by managing information resources at a minimum cost while upholding service-level agreements. As the number of resources gradually increases, power supply shortages may arise. This study focuses on the fact that the CPU utilization rate of the server running in the data center is less than 30% and idle servers running only the OS consume more than half of the power consumed by hosts running with maximum CPU utilization and speed. Therefore, this study proposes an approach to enhance data center efficiency through improved management of energy consumption. We present a method to minimize energy consumption while processing the same workload, i.e., ultimately reducing the energy consumed by operating servers. Energy consumption and SLA violation rate were used as evaluation metrics of the optimization model to meet the minimum performance target.

UR - http://www.scopus.com/inward/record.url?scp=85056534876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056534876&partnerID=8YFLogxK

U2 - 10.1016/j.suscom.2018.10.003

DO - 10.1016/j.suscom.2018.10.003

M3 - Article

VL - 20

SP - 34

EP - 45

JO - Sustainable Computing: Informatics and Systems

JF - Sustainable Computing: Informatics and Systems

SN - 2210-5379

ER -