Covering the cooperative load balancing delivery in collaborative grid environments

  • Authors:
  • Pilar Herrero;José/ Luis Bosque;Marí/a S. Pé/rez

  • Affiliations:
  • (Correspd. Tel.: +34 91 336 74 56/ Fax: +34 91 336 65 95/ E-mail: pherrero@fi.upm.es) Facultad de Informá/tica, Universidad Polité/cnica de Madrid, Madrid, Spain;Dpto. De Electró/nica y Computadores, Universidad de Cantabria, Santander, Spain;Facultad de Informá/tica, Universidad Polité/cnica de Madrid, Madrid, Spain

  • Venue:
  • Multiagent and Grid Systems - New tendencies on agents and grid environments
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Cooperation among computational nodes to solve a common parallel application is one of the most outstanding features of grid environments. However, from the performance point of view, it is very important that this cooperation will be made in an equilibrated way, because otherwise some nodes can be overloaded whereas other nodes can be underused. This paper presents CAMBLE (Cooperative Awareness Model for Balancing the Load in grid Environments), which applies some theoretical principles of awareness models to promote an efficient, autonomous, equilibrate and cooperative task delivery in grid environments. This cooperative task management has been implemented and tested in a real and heterogeneous grid infrastructure, composed of several VO, with very successful results. This paper presents some of these outcomes while emphasizes on the overhead and efficacy of the system using this model.