跳到主要导航 跳到搜索 跳到主要内容

On the use of random weights in MOEA/D

  • Hui Li
  • , Min Ding
  • , Jingda Deng
  • , Qingfu Zhang
  • Xi'an Jiaotong University
  • City University of Hong Kong

科研成果: 书/报告/会议事项章节会议稿件同行评审

34 引用 (Scopus)

摘要

MOEA/D is a decomposition-based multiobjective evolutionary algorithm that has attracted much attention in recent years. Its performance depends on the setting of weight vectors which are used for defining subproblems. In the case of irregular Pareto fronts (e.g, disconnected or degenerated), fixed setting of weight vectors in MOEA/D may not work well. In this paper, we propose an improved MOEA/D with both random and fixed weight vectors. Moreover, an external archive based on a modified ϵ-dominance strategy is used for storing nondominated solutions found by the proposed algorithm and assisting the generation of random weight vectors. Some experiments have been conducted to verify the efficiency and effectiveness of the improved MOEA/D on benchmark multiobjective test problems with irregular Pareto fronts. The experimental results show that the overall performance of the proposed algorithm is better than baseline MOEA/D and NSGA-II.

源语言英语
主期刊名2015 IEEE Congress on Evolutionary Computation, CEC 2015 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
978-985
页数8
ISBN(电子版)9781479974924
DOI
出版状态已出版 - 10 9月 2015
活动IEEE Congress on Evolutionary Computation, CEC 2015 - Sendai, 日本
期限: 25 5月 201528 5月 2015

出版系列

姓名2015 IEEE Congress on Evolutionary Computation, CEC 2015 - Proceedings

会议

会议IEEE Congress on Evolutionary Computation, CEC 2015
国家/地区日本
Sendai
时期25/05/1528/05/15

学术指纹

探究 'On the use of random weights in MOEA/D' 的科研主题。它们共同构成独一无二的指纹。

引用此