J4 ›› 2012, Vol. 30 ›› Issue (2): 131-137.

• 论文 • 上一篇    下一篇

基于新型Memetic算法的多目标优化

刘伟1|赵丹1|孙宏伟2   

  1. 1.东北石油大学 电气信息工程学院,黑龙江 大庆 163318;2.中国石油集团 辽河石化公司|辽宁 盘锦 124022
  • 收稿日期:2011-09-23 出版日期:2012-03-28 发布日期:2012-04-19
  • 作者简介:刘伟(1971—)|男|哈尔滨人|东北石油大学教授|博士|硕士生导师|主要从事电力系统智能控制研究|(Tel)86-13845966361(E-mail)oliuwei@163.com。
  • 基金资助:

    黑龙江省普通高等学校青年学术骨干基金资助项目(1055G04)

Multi-Objective Optimization Based on Memetic Algorithm

LIU Wei1|ZHAO Dan1|SUN Hong-wei2   

  1. 1.College of Electricity Information Engineering,Northeast Petroleum University,Daqing 163318,China;
    2.Liao He Petrochemical Company|China Petroleum,Panjin 124022,China
  • Received:2011-09-23 Online:2012-03-28 Published:2012-04-19

摘要:

为了更好地解决多目标优化问题,提出一种求解多目标优化问题的新型memetic算法。该算法利用微粒子群算法的全局搜索能力和同步启发式局部搜索相结合进行局部微
调;利用基于模糊全局极值的概念处理种群中过早出现收敛以及解多样性保持等问题。通过进一步检测得出新算法的特点并展示其在多目标优化问题上的独立性和综合效应。同时应用新型算法对IEEE14节点标准电网进行无功优化计算。结果证明,该新型memetic算法具有很好的寻优能力,验证了该算法的有效性及科学性。

关键词: memetic算法, 多目标优化, 粒子群算法

Abstract:

In order to  solve multi-objective optimization problems,a new memetic algorithm is proposed,which combines the global search ability of particle swarm optimization with synchronous local search heuristic for directed local fine-tuning.A new particle updating strategy is presented to deal with the problem of premature convergence and diversity maintenance in the swarm based upon the concept of fuzzy global-best.The proposed new features are verified to show their individual and combined effect in multi-objective optimization.The reactive power optimization result of IEEE14 node system by the new memetic shows that it has a good astringency and efficiency.

Key words: memetic algorithm, multi-objective optimization, particle swarm optimization

中图分类号: 

  • TM714