Optimization of energy and emissions in high-performance grid computing data centres

Mikko Majanen, Olli Mämmelä

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

At an early stage of information and communications technology and high-performance computing, performance and reliability were two important factors in research and development. It was highly essential that the hardware was able to function adequately, performing strategic operations. Energy consumption was not considered as a serious topic, since the technical characteristics of hardware and software were limited and the amount of computing nodes in a computing cluster, i.e., a data centre was small. Gradually the situation has evolved a lot: nowadays there are multiple data centres located in geographically diverse locations and the software has become more complex. Modern data centres are equipped with a large amount of computing nodes having vast computing power. However, all this progress has not come without a price, since more computing power equals more total power consumption. Consequently, energy consumption has become a major topic nowadays. This work presents two algorithms for optimizing energy and emissions in high-performance grid computing, in which multiple data centres are interconnected to each other. The algorithms are validated in a simulation environment by comparing them to standard round-robin algorithm. Our simulation experiments show that the solution is able to reduce energy consumption and emissions drastically without increase in job turnaround or wait time.
Original languageEnglish
Title of host publicationThe Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten
Pages75-82
Publication statusPublished - 2012
MoE publication typeA4 Article in a conference publication
EventThe Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies, ENERGY 2012 - St. Maarten, Netherlands
Duration: 25 Mar 201230 Mar 2012

Conference

ConferenceThe Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies, ENERGY 2012
Abbreviated titleENERGY 2012
CountryNetherlands
CitySt. Maarten
Period25/03/1230/03/12

Fingerprint

Grid computing
Energy utilization
Cluster computing
Hardware
Electric power utilization
Communication
Experiments

Keywords

  • HPC
  • grid computing
  • energy
  • emissions

Cite this

Majanen, M., & Mämmelä, O. (2012). Optimization of energy and emissions in high-performance grid computing data centres. In The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten (pp. 75-82)
Majanen, Mikko ; Mämmelä, Olli. / Optimization of energy and emissions in high-performance grid computing data centres. The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten. 2012. pp. 75-82
@inproceedings{17f1b338300b43c1a76b415a18380d1a,
title = "Optimization of energy and emissions in high-performance grid computing data centres",
abstract = "At an early stage of information and communications technology and high-performance computing, performance and reliability were two important factors in research and development. It was highly essential that the hardware was able to function adequately, performing strategic operations. Energy consumption was not considered as a serious topic, since the technical characteristics of hardware and software were limited and the amount of computing nodes in a computing cluster, i.e., a data centre was small. Gradually the situation has evolved a lot: nowadays there are multiple data centres located in geographically diverse locations and the software has become more complex. Modern data centres are equipped with a large amount of computing nodes having vast computing power. However, all this progress has not come without a price, since more computing power equals more total power consumption. Consequently, energy consumption has become a major topic nowadays. This work presents two algorithms for optimizing energy and emissions in high-performance grid computing, in which multiple data centres are interconnected to each other. The algorithms are validated in a simulation environment by comparing them to standard round-robin algorithm. Our simulation experiments show that the solution is able to reduce energy consumption and emissions drastically without increase in job turnaround or wait time.",
keywords = "HPC, grid computing, energy, emissions",
author = "Mikko Majanen and Olli M{\"a}mmel{\"a}",
note = "Project code: 70170",
year = "2012",
language = "English",
isbn = "978-1-61208-189-2",
pages = "75--82",
booktitle = "The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten",

}

Majanen, M & Mämmelä, O 2012, Optimization of energy and emissions in high-performance grid computing data centres. in The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten. pp. 75-82, The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies, ENERGY 2012, St. Maarten, Netherlands, 25/03/12.

Optimization of energy and emissions in high-performance grid computing data centres. / Majanen, Mikko; Mämmelä, Olli.

The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten. 2012. p. 75-82.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Optimization of energy and emissions in high-performance grid computing data centres

AU - Majanen, Mikko

AU - Mämmelä, Olli

N1 - Project code: 70170

PY - 2012

Y1 - 2012

N2 - At an early stage of information and communications technology and high-performance computing, performance and reliability were two important factors in research and development. It was highly essential that the hardware was able to function adequately, performing strategic operations. Energy consumption was not considered as a serious topic, since the technical characteristics of hardware and software were limited and the amount of computing nodes in a computing cluster, i.e., a data centre was small. Gradually the situation has evolved a lot: nowadays there are multiple data centres located in geographically diverse locations and the software has become more complex. Modern data centres are equipped with a large amount of computing nodes having vast computing power. However, all this progress has not come without a price, since more computing power equals more total power consumption. Consequently, energy consumption has become a major topic nowadays. This work presents two algorithms for optimizing energy and emissions in high-performance grid computing, in which multiple data centres are interconnected to each other. The algorithms are validated in a simulation environment by comparing them to standard round-robin algorithm. Our simulation experiments show that the solution is able to reduce energy consumption and emissions drastically without increase in job turnaround or wait time.

AB - At an early stage of information and communications technology and high-performance computing, performance and reliability were two important factors in research and development. It was highly essential that the hardware was able to function adequately, performing strategic operations. Energy consumption was not considered as a serious topic, since the technical characteristics of hardware and software were limited and the amount of computing nodes in a computing cluster, i.e., a data centre was small. Gradually the situation has evolved a lot: nowadays there are multiple data centres located in geographically diverse locations and the software has become more complex. Modern data centres are equipped with a large amount of computing nodes having vast computing power. However, all this progress has not come without a price, since more computing power equals more total power consumption. Consequently, energy consumption has become a major topic nowadays. This work presents two algorithms for optimizing energy and emissions in high-performance grid computing, in which multiple data centres are interconnected to each other. The algorithms are validated in a simulation environment by comparing them to standard round-robin algorithm. Our simulation experiments show that the solution is able to reduce energy consumption and emissions drastically without increase in job turnaround or wait time.

KW - HPC

KW - grid computing

KW - energy

KW - emissions

UR - https://www.iaria.org/conferences2012/ENERGY12.html

M3 - Conference article in proceedings

SN - 978-1-61208-189-2

SP - 75

EP - 82

BT - The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten

ER -

Majanen M, Mämmelä O. Optimization of energy and emissions in high-performance grid computing data centres. In The Second International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies. ENERGY 2012. St. Maarten. 2012. p. 75-82