An Improved Genetic Algorithm for Task Scheduling in Distributed Computing System

DOI

10.2991/aiea-16.2016.41How to use a DOI?

Keywords

Distributed computing system; job scheduling; genetic algorithm.

Abstract

In distributed computing environment, task scheduling is one of the most important factors that affect the overall efficiency of the system. Task scheduling has been proved to be a NP-completeness problem, and the only way to solve this kind of problem is the method of exhaustion. Genetic algorithm is one of the best algorithms can solve the NP-completeness problem, which has the ability to quickly approach the optimal solution. However, there are still some shortcomings of genetic algorithm, such as the problem of premature convergence. In this paper, an improved genetic algorithm called genetic algorithm with geographical isolation is proposed. It restrains the excessive growth phenomenon of individuals by dividing the population, effectively solves the problem of premature convergence in genetic algorithm. In this paper, several sets of experiments are made to compare the operating efficiency and the final allocation effect of the algorithm and other scheduling algorithms, which prove that the algorithm can improve the efficiency of the algorithm without affecting the quality of the final solution.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuhao Cui
AU  - Hua Zhang
PY  - 2016/11
DA  - 2016/11
TI  - An Improved Genetic Algorithm for Task Scheduling in Distributed Computing System
BT  - Proceedings of the 2016 International Conference on Artificial Intelligence and Engineering Applications
PB  - Atlantis Press
SP  - 218
EP  - 222
SN  - 2352-538X
UR  - https://doi.org/10.2991/aiea-16.2016.41
DO  - 10.2991/aiea-16.2016.41
ID  - Cui2016/11
ER  -