MOEA/D with angle-based constrained dominance principle for constrained multi-objective optimization problems

被引：119

作者：

Fan, Zhun ^{[1
,2
]}

Fang, Yi ^{[1
]}

Li, Wenji ^{[1
]}

Cai, Xinye ^{[3
,4
]}

Wei, Caimin ^{[5
]}

Goodman, Erik ^{[6
]}

机构：

[1] Shantou Univ, Dept Elect Engn, Shantou 515063, Guangdong, Peoples R China

[2] Key Lab Digital Signal & Image Proc Guangdong Pro, Shantou 515063, Guangdong, Peoples R China

[3] Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Nanjing 210016, Jiangsu, Peoples R China

[4] Collaborat Innovat Ctr Novel Software Technol & I, Nanjing 210023, Jiangsu, Peoples R China

[5] Shantou Univ, Dept Math, Shantou 515063, Guangdong, Peoples R China

[6] Michigan State Univ, BEACON Ctr Study Evolut Act, E Lansing, MI 48824 USA

来源：

APPLIED SOFT COMPUTING | 2019年 / 74卷

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Constraint-handling mechanism; Angle-based constrained dominance principle (ACDP); Constrained multi-objective evolutionary algorithms (CMOEAs) Applied; EVOLUTIONARY ALGORITHM; DECOMPOSITION; SELECTION;

D O I：

10.1016/j.asoc.2018.10.027

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes a novel constraint-handling mechanism, namely the angle-based constrained dominance principle (ACDP), to solve constrained multi-objective optimization problems (CMOPs). In this work, the mechanism of ACDP is embedded in a decomposition-based multi-objective evolutionary algorithm (MOEA/D). ACDP uses the angle information among solutions of a population and the proportion of feasible solutions to adjust the dominance relationship, so that it can maintain good convergence, diversity and feasibility of a population, simultaneously. To evaluate the performance of the proposed MOEA/D-ACDP, fourteen benchmark instances and an engineering optimization problem are studied. Six state-of-the-art CMOEAs, including C-MOEA/D, MOEA/D-CDP, MOEA/D-Epsilon, MOEA/D-SR, NSGAII-CDP and SP, are compared. The experimental results illustrate that MOEA/D-ACDP is significantly better than the other six CM0EAs on these benchmark problems and the real-world case, which demonstrates the effectiveness of ACDP. (C) 2018 Published by Elsevier B.V.

引用

页码：621 / 633

页数：13

共 42 条

[21]

Jan M. A., 2010 UK WORKSH COMP

[22] A study of two penalty-parameterless constraint handling techniques in the framework of MOEA/D [J].

Jan, Muhammad Asif ;

Khanum, Rashida Adeeb .

APPLIED SOFT COMPUTING, 2013, 13 (01) :128-148

[23] A Simple and Fast Hypervolume Indicator-Based Multiobjective Evolutionary Algorithm [J].

Jiang, Siwei ;

Zhang, Jie ;

Ong, Yew-Soon ;

Zhang, Allan N. ;

Tan, Puay Siew .

IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (10) :2202-2213

[24]

Jiménez F, 2002, IEEE C EVOL COMPUTAT, P1133, DOI 10.1109/CEC.2002.1004402

[25] Multiobjective Optimization Problems With Complicated Pareto Sets, MOEA/D and NSGA-II [J].

Li, Hui ;

Zhang, Qingfu .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2009, 13 (02) :284-302

[26] Decomposition of a Multiobjective Optimization Problem into a Number of Simple Multiobjective Subproblems [J].

Liu, Hai-Lin ;

Gu, Fangqing ;

Zhang, Qingfu .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2014, 18 (03) :450-455

[27]

Murata T, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2, P289, DOI 10.1109/ICEC.1995.489161

[28] Constrained multi-objective optimization using constrained non-dominated sorting combined with an improved hybrid multi-objective evolutionary algorithm [J].

Ning, Weikang ;

Guo, Baolong ;

Yan, Yunyi ;

Wu, Xianxiang ;

Wu, Jinfu ;

Zhao, Dan .

ENGINEERING OPTIMIZATION, 2017, 49 (10) :1645-1664

[29]

POWELL D, 1993, PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON GENETIC ALGORITHMS, P424

[30] Constrained multi-objective optimization algorithm with an ensemble of constraint handling methods [J].

Qu, B. Y. ;

Suganthan, P. N. .

ENGINEERING OPTIMIZATION, 2011, 43 (04) :403-416

← 1 2 3 4 5 →