求解高维优化问题的混合灰狼优化算法
DOI:
CSTR:
作者:
作者单位:

1. 贵州财经大学
2. 贵州财经学院
3. 长沙理工大学能源与动力工程学院新能源系

作者简介:

龙文

通讯作者:

中图分类号:

TP273

基金项目:

国家自然科学基金:节能型永磁悬浮系统的实现机理与特性研究;教育部人文社会科学研究规划基金项目;贵州省教育厅125重大科技专项


Hybrid Grey Wolf Optimization Algorithm for High- dimensional Optimization
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对基本灰狼优化算法在求解高维优化问题时存在解精度低、收敛速度慢和易陷入局部最优的缺点,提出一种基于混沌映射和的精英反向学习策略的混合灰狼优化算法用于解决无约束高维函数优化问题. 该混合算法首先采用混沌序列产生初始种群为算法进行全局搜索奠定基础;对当前种群中的精英个体分别执行精英反向学习策略以协调算法的勘探和开采能力;在搜索过程中对决策层个体进行混沌扰动,以避免算法陷入局部最优的可能性. 选取10个高维(100维、500维和1000维)标准测试函数进行数值实验,结果表明混合灰狼优化算法在求解精度及收敛速度指标上明显优于对比算法.

    Abstract:

    The standard grey wolf optimization (GWO) algorithm has a few disadvantages in the high-dimensional function optimization, including low solution precision, slow convergence speed and high possibility of being trapped in local optimum. A hybrid grey wolf optimization (HGWO) algorithm combined chaotic mapping and elite opposition- based learning strategy was proposed for solving unconstrained high-dimensional function optimization problems. In proposed HGWO algorithm, chaotic sequence was used to initiate individuals’ position, which strengthened the diversity of global searching. Elite opposition-based learning strategy was applied to the current elite individuals, which coordinated the exploration and exploitation ability of the proposed HGWO algorithm. It then disturbed the first three best individuals by chaotic mapping in the process of the search so as to avoid the possibility of falling into local optimum. Numerical experiments were conducted on the 10 high-dimensional (100, 500, and 1000 dimension) classical test functions. The simulation results demonstrate that the proposed HGWO algorithm has better performance in solution precision and convergence speed.

    参考文献
    相似文献
    引证文献
引用本文

龙文 蔡绍洪 焦建军 张文专 唐明珠.求解高维优化问题的混合灰狼优化算法[J].控制与决策,2016,31(11):1991-1997

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2015-09-23
  • 最后修改日期:2015-12-25
  • 录用日期:
  • 在线发布日期: 2016-11-20
  • 出版日期:
文章二维码