The Design and Analysis of an Improved Parallel Genetic Algorithm Based on Distributed System

DOI

10.2991/emeit.2012.3How to use a DOI?

Keywords

genetic algorithm, parallel genetic algorithm, distributed system, migration, adaptive migration strategy,

Abstract

Genetic Algorithm (GA) is a powerful global optimization search algorithm imitating natural selection and genetic mechanism, but it has low search efficiency in the late evolving period. Parallel genetic algorithm (PGA) can improve computational efficiency and accuracy greatly, so it has become one of the main research fields of GA. This paper introduces the procedure of PGA in detail, analyses the migration limitations of traditional PGA, and puts forward an improved coarse-grained PGA based on distributed system, which adopts adaptive migration strategy to evolve. This implementation can fully tap the computing capability of distributed system to improve the convergence speed and ameliorate the population diversity in order to restrain premature convergence. The experiments show that this algorithm not only has faster convergent speed but also has more accurate calculation precision as well as higher parallel speedup.

Copyright

© 2012, 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  - Yan Chen
AU  - Zhimei Li
PY  - 2012/09
DA  - 2012/09
TI  - The Design and Analysis of an Improved Parallel Genetic Algorithm Based on Distributed System
BT  - Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)
PB  - Atlantis Press
SP  - 11
EP  - 15
SN  - 1951-6851
UR  - https://doi.org/10.2991/emeit.2012.3
DO  - 10.2991/emeit.2012.3
ID  - Chen2012/09
ER  -