Loading...

A Scheduling Algorithm to Improve Energy Consumption in Data Centers

Ebrahimirad, Vahid | 2013

524 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 44738 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Goudarzi, Maziar
  7. Abstract:
  8. The applications that consist ofprecedence-constrained parallel taskshave used in business activities and scientific projects and the energy consumption of these application has become a major concern in datacenters. At the software level, energy-aware task scheduling algorithmsare an effective technique for energy reduction and optimizing performance in data centers. The related works in this areahave traditionally ignore the utilization value of physical machines (PMs) and while the main reason of the energy inefficiency in datacenters is low average utilization of the PMs.In this paper, we propose a new energy-aware scheduling (EASy) algorithm forprecedence-constrained parallel taskswith a low time complexityO(e.m+e.logm)in a virtualized datacenter.Besides optimizing makespan of applications, the EASy algorithm considers the utilization value of PMs and tries to maximize itby using of virtualization technology. Thus, the number of active PMs and total energy consumption will decrease with maximizing utilization value of PMs in datacenters.The extensive experimental results using real-world applications clearly demonstrate that EASy is capable of increasing utilization value of PMs and decreasing energy consumption of PMs respectively by 41% and 28% on average
  9. Keywords:
  10. Virtualization ; Scheduling ; Data Center ; Virtualization Technology ; Energy Aware ; Virtual Machine

 Digital Object List

 Bookmark

No TOC