DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2010-10-26 - Article/Dans un journal avec peer-review - Anglais - 8 page(s)

Mezmaz Mohand , Kessaci Yacine, Lee Young Choon, Melab Nouredine, Talbi El-Ghazali, Zomaya Albert Y., Tuyttens Daniel , "A Parallel Island-based Hybrid Genetic Algorithm for Precedence-constrained Applications to Minimize Energy Consumption and Makespan" in Proceedings - IEEE/ACM International Workshop on Grid Computing 2010, Article number 5697985, Pages 274-281 2010 11th IEEE/ACM International Conference on Grid Computing, 274-281

  • Codes CREF : Recherche opérationnelle (DI1150)
  • Unités de recherche UMONS : Mathématique et Recherche opérationnelle (F151)
  • Instituts UMONS : Institut des Sciences et du Management des Risques (Risques)
Texte intégral :

Abstract(s) :

(Anglais) Task scheduling algorithms are designed mostly with the sole goal of minimizing makespan (completion time). Almost all research works related to this kind of algorithms do not pay much attention to energy consumption. In this paper, we investigate the energy issue in task scheduling particularly on high-performance computing systems (HCSs). We propose a new island-based bi-objective hybrid algorithm that takes into account, not only makespan, but also energy consumption. The proposed approach uses dynamic voltage scaling (DVS) to minimize energy consumption. Our study provides the significance and potential of DVS. The proposed approach is powerful as it profits from the cooperative paradigm of the island model. Indeed, the obtained results show that our approach outperforms previous scheduling methods, in terms of energy consumption, by a noticeable margin. The obtained schedules are also shorter, in terms of completion time, than those of other algorithms.