An Improved Ant Algorithm for Grid Task Scheduling Strategy

Task scheduling is an important factor that directly influences the performance and efficiency of the system. Grid resources are usually distributed in different geographic locations, belonging to different organizations and resources’ properties are vastly different, in order to complete efficientl...

Full description

Saved in:
Bibliographic Details
Published in:Physics procedia Vol. 24; pp. 1974 - 1981
Main Authors: Wei, Laizhi, Zhang, Xiaobin, Li, Yun, Li, Yujie
Format: Journal Article
Language:English
Published: Elsevier B.V 2012
Subjects:
ant colony algorithm
grid
task scheduling
ant colony algorithm
grid
task scheduling
ISSN:1875-3892, 1875-3892
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Task scheduling is an important factor that directly influences the performance and efficiency of the system. Grid resources are usually distributed in different geographic locations, belonging to different organizations and resources’ properties are vastly different, in order to complete efficiently, intelligently task scheduling, the choice of scheduling strategy is essential. This paper proposes an improved ant algorithm for grid task scheduling strategy, by introducing a new type pheromone and a new node redistribution selection rule. On the one hand, the algorithm can track performances of resources and tag it. On the other hand, add algorithm to deal with task scheduling unsuccessful situations that improve the algorithm's robustness and the successful probability of task allocation and reduce unnecessary overhead of system, shortening the total time to complete tasks. The data obtained from simulation experiment shows that use this algorithm to resolve schedule problem better than traditional ant algorithm.
ISSN:1875-3892
1875-3892
DOI:10.1016/j.phpro.2012.02.290