A hybrid evolutionary algorithm with adaptive multi-population strategy for multi-objective optimization problems

Hongfeng Wang; Yaping Fu; Min Huang; George Huang; Junwei Wang

doi:10.1007/s00500-016-2414-5

A hybrid evolutionary algorithm with adaptive multi-population strategy for multi-objective optimization problems

Hongfeng Wang, Yaping Fu, Min Huang, George Huang, Junwei Wang

Research output: Journal article publication › Journal article › Academic research › peer-review

21 Citations (Scopus)

Abstract

In this paper, a new multi-objective evolutionary algorithm (MOEA) named hybrid MOEA with adaptive multi-population strategy (HMOEA-AMP) is proposed for multi-objective optimization problems (MOPs).In the framework of HMOEA-AMP, the particle swarm optimization and differential evolution are hybridized to guide the exploitation of the Pareto optimal solutions and the exploration of the optimal distribution of the achieved solutions, respectively. Multiple subpopulations are constructed in an adaptive fashion according to a number of scalar subproblems, which are decomposed from a MOP through a set of predefined weight vectors. Comprehensive experiments using a set of benchmark are conducted to investigate the performance of HMOEA-AMP in comparison with several state-of-the-art MOEAs. The experimental results show the advantage of the proposed algorithm.

Original language	English
Pages (from-to)	5975-5987
Number of pages	13
Journal	Soft Computing
Volume	21
Issue number	20
DOIs	https://doi.org/10.1007/s00500-016-2414-5
Publication status	Published - 1 Oct 2017
Externally published	Yes

Keywords

Differential evolution
Evolutionary multi-objective optimization
Hybrid evolutionary algorithm
Multi-objective optimization problem
Multi-population
Particle swarm optimization

ASJC Scopus subject areas

Theoretical Computer Science
Software
Geometry and Topology

More information

10.1007/s00500-016-2414-5

Cite this

@article{e0317b2ea11c40f6aed889a443097fcb,

title = "A hybrid evolutionary algorithm with adaptive multi-population strategy for multi-objective optimization problems",

abstract = "In this paper, a new multi-objective evolutionary algorithm (MOEA) named hybrid MOEA with adaptive multi-population strategy (HMOEA-AMP) is proposed for multi-objective optimization problems (MOPs).In the framework of HMOEA-AMP, the particle swarm optimization and differential evolution are hybridized to guide the exploitation of the Pareto optimal solutions and the exploration of the optimal distribution of the achieved solutions, respectively. Multiple subpopulations are constructed in an adaptive fashion according to a number of scalar subproblems, which are decomposed from a MOP through a set of predefined weight vectors. Comprehensive experiments using a set of benchmark are conducted to investigate the performance of HMOEA-AMP in comparison with several state-of-the-art MOEAs. The experimental results show the advantage of the proposed algorithm.",

keywords = "Differential evolution, Evolutionary multi-objective optimization, Hybrid evolutionary algorithm, Multi-objective optimization problem, Multi-population, Particle swarm optimization",

author = "Hongfeng Wang and Yaping Fu and Min Huang and George Huang and Junwei Wang",

note = "Funding Information: This study was supported in part by the HKSAR RGC GRF project under Grant No. 712513, by the ITF Innovation and Technology Support Programme under Grant No. ITP/045/13LP, by the National Natural Science Foundation of China (NSFC) under Grant No. 71671032 and No. 71571156, by the Major International Joint Research Project of NSFC under Grant No. 71620107003, and by the Open Project funded by State Key Laboratory of Synthetical Automation for Process Industries under Grant No. PAL-N201505. Publisher Copyright: {\textcopyright} 2016, Springer-Verlag Berlin Heidelberg.",

year = "2017",

month = oct,

day = "1",

doi = "10.1007/s00500-016-2414-5",

language = "English",

volume = "21",

pages = "5975--5987",

journal = "Soft Computing",

issn = "1432-7643",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "20",

}

TY - JOUR

T1 - A hybrid evolutionary algorithm with adaptive multi-population strategy for multi-objective optimization problems

AU - Wang, Hongfeng

AU - Fu, Yaping

AU - Huang, Min

AU - Huang, George

AU - Wang, Junwei

N1 - Funding Information: This study was supported in part by the HKSAR RGC GRF project under Grant No. 712513, by the ITF Innovation and Technology Support Programme under Grant No. ITP/045/13LP, by the National Natural Science Foundation of China (NSFC) under Grant No. 71671032 and No. 71571156, by the Major International Joint Research Project of NSFC under Grant No. 71620107003, and by the Open Project funded by State Key Laboratory of Synthetical Automation for Process Industries under Grant No. PAL-N201505. Publisher Copyright: © 2016, Springer-Verlag Berlin Heidelberg.

PY - 2017/10/1

Y1 - 2017/10/1

N2 - In this paper, a new multi-objective evolutionary algorithm (MOEA) named hybrid MOEA with adaptive multi-population strategy (HMOEA-AMP) is proposed for multi-objective optimization problems (MOPs).In the framework of HMOEA-AMP, the particle swarm optimization and differential evolution are hybridized to guide the exploitation of the Pareto optimal solutions and the exploration of the optimal distribution of the achieved solutions, respectively. Multiple subpopulations are constructed in an adaptive fashion according to a number of scalar subproblems, which are decomposed from a MOP through a set of predefined weight vectors. Comprehensive experiments using a set of benchmark are conducted to investigate the performance of HMOEA-AMP in comparison with several state-of-the-art MOEAs. The experimental results show the advantage of the proposed algorithm.

AB - In this paper, a new multi-objective evolutionary algorithm (MOEA) named hybrid MOEA with adaptive multi-population strategy (HMOEA-AMP) is proposed for multi-objective optimization problems (MOPs).In the framework of HMOEA-AMP, the particle swarm optimization and differential evolution are hybridized to guide the exploitation of the Pareto optimal solutions and the exploration of the optimal distribution of the achieved solutions, respectively. Multiple subpopulations are constructed in an adaptive fashion according to a number of scalar subproblems, which are decomposed from a MOP through a set of predefined weight vectors. Comprehensive experiments using a set of benchmark are conducted to investigate the performance of HMOEA-AMP in comparison with several state-of-the-art MOEAs. The experimental results show the advantage of the proposed algorithm.

KW - Differential evolution

KW - Evolutionary multi-objective optimization

KW - Hybrid evolutionary algorithm

KW - Multi-objective optimization problem

KW - Multi-population

KW - Particle swarm optimization

UR - http://www.scopus.com/inward/record.url?scp=84994242451&partnerID=8YFLogxK

U2 - 10.1007/s00500-016-2414-5

DO - 10.1007/s00500-016-2414-5

M3 - Journal article

AN - SCOPUS:84994242451

SN - 1432-7643

VL - 21

SP - 5975

EP - 5987

JO - Soft Computing

JF - Soft Computing

IS - 20

ER -

A hybrid evolutionary algorithm with adaptive multi-population strategy for multi-objective optimization problems

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this