Towards energy-aware task scheduling (EATS) framework for divisible-load applications in cloud computing infrastructure

Leila Ismail, Abbas A. Fardoun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Cloud computing is an emerging technology which is rapidly being adopted by industries, government and academia. However, the power consumption of the underlying data center has a critical impact for its known impact on the environment and the Cloud electricity bills. Therefore, there is a need for scheduling framework in the Cloud which takes into account the optimization of the power consumption of the Cloud. In this paper, we propose an Energy-Aware Task Scheduling (EATS) cloud computing framework which is responsible to schedule users' tasks considering the energy consumption when running those tasks. This paper describes our framework, and report on workload classifications of energy consumption. The results reveal that CPU-bound applications are the most consumer of energy, and therefore should be accounted for in any framework of energy-efficient scheduling, and that strategies based on shutdowns and startups should be avoided.

Original languageEnglish
Title of host publication11th Annual IEEE International Systems Conference, SysCon 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509046225
DOIs
Publication statusPublished - May 26 2017
Event11th Annual IEEE International Systems Conference, SysCon 2017 - Montreal, Canada
Duration: Apr 24 2017Apr 27 2017

Publication series

Name11th Annual IEEE International Systems Conference, SysCon 2017 - Proceedings

Other

Other11th Annual IEEE International Systems Conference, SysCon 2017
Country/TerritoryCanada
CityMontreal
Period4/24/174/27/17

Keywords

  • Cloud Computing
  • Cloud Computing Services and Middleware
  • Data Center
  • Energy Efficiency
  • Green Computing
  • Scheduling Algorithms

ASJC Scopus subject areas

  • Artificial Intelligence
  • Hardware and Architecture
  • Control and Systems Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'Towards energy-aware task scheduling (EATS) framework for divisible-load applications in cloud computing infrastructure'. Together they form a unique fingerprint.

Cite this