Research on the Multi-population Differential Evolution Algorithm and the Performance

DOI

10.2991/mmsta-19.2019.22How to use a DOI?

Keywords

multi-population differential evolution algorithm; optimization algorithm; optimal substitution strategy; elite immigration strategy

Abstract

The original differential evolution algorithm (DE) is a single-population differential evolution algorithm (SPDE). DE converges very quickly, and takes the advantage of robustness. The improved DE has a better performance, but there are premature problems in optimizing complex problems. The multi-population differential evolution algorithm (MPDE) is proposed to overcome premature problems in this paper. The optimal substitution strategy (OSS) and the elite immigration strategy (EIS) are studied to maintain the diversity of populations. The simulation concludes that MPDE converges faster than SPDE in optimizing the ultra-high dimensional problems, and the EIS is superior to the OSS. However, the efficiency of DE is more effective than that of MPDE when the algorithms converge. Research shows that multi-population strategy is a feasible and effective way to the premature problems of DE.

Copyright

© 2019, 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  - Renquan Huang
AU  - Jing Tian
AU  - Juanjuan Wang
AU  - Junmin Kang
PY  - 2019/12
DA  - 2019/12
TI  - Research on the Multi-population Differential Evolution Algorithm and the Performance
BT  - Proceedings of the 2019 2nd International Conference on Mathematics, Modeling and Simulation Technologies and Applications (MMSTA 2019)
PB  - Atlantis Press
SP  - 103
EP  - 108
SN  - 2352-538X
UR  - https://doi.org/10.2991/mmsta-19.2019.22
DO  - 10.2991/mmsta-19.2019.22
ID  - Huang2019/12
ER  -