张新明,涂强,康强,程金凤.灰狼优化与差分进化的混合算法及函数优化[J].计算机科学,2017,44(9):93-98, 124
灰狼优化与差分进化的混合算法及函数优化
Hybrid Optimization Algorithm Based on Grey Wolf Optimization and Differential Evolution for Function Optimization
投稿时间:2016-07-02  修订日期:2016-11-13
DOI:10.11896/j.issn.1002-137X.2017.09.019
中文关键词:  优化算法,混合优化算法,灰狼优化算法,差分进化,函数优化
英文关键词:Optimization algorithm,Hybrid optimization algorithm,Grey wolf optimization algorithm,Differential evolution,Function optimization
基金项目:本文受河南省重点科技攻关项目(132102110209),河南省基础与前沿技术研究计划项目(142300410295)资助
作者单位E-mail
张新明 河南师范大学计算机与信息工程学院 新乡453007;河南省高校计算智能与数据挖掘工程技术研究中心 新乡453007 xinmingzhang@126.com 
涂强 河南师范大学计算机与信息工程学院 新乡453007  
康强 河南师范大学计算机与信息工程学院 新乡453007  
程金凤 河南师范大学计算机与信息工程学院 新乡453007  
摘要点击次数: 207
全文下载次数: 137
中文摘要:
      灰狼优化(Grey Wolf Optimization,GWO)算法是近年被提出的一种新型智能优化算法,具有收敛速度快和优化精度高的特点,但对于一些复杂优化问题易陷入局部最优。差分进化(Differential Evolution,DE)算法的全局搜索能力强,但其性能对参数敏感,且局部搜索能力不足。为了发挥二者各自的优点并弥补存在的缺陷,提出了一种灰狼优化与差分进化的混合优化算法。首先使用嵌入趋优算子的GWO算法搜索,以便在更短的过程中获得更高的优化精度和更快的收敛速度;然后采用自适应调节参数的差分进化策略来进一步提高算法对复杂优化函数的寻优性能,从而获得一种高性能的混合优化算法,以便能更高效地解决各种函数优化问题。对12个高维函数的优化结果表明,与标准GWO,ACS,DMPSO及SinDE相比,新的混合优化算法不仅具有更好的收敛速度和优化性能,而且具有更好的普适性,更适用于解决各种函数优化问题。
英文摘要:
      Grey wolf optimizer (GWO) is a novel intelligent optimization algorithm which has proposed resently and it has such merits as fast convergence speed,high optimization precision,but easily entraps in local optima.The differential evolution (DE) algorithm has strong global search ability,but its local search ability is poor and its performance is sensitive to the parameters.To take advantage of the merits of GWO and DE and overcome their defects in dealing with function optimization problems,a hybrid optimization algorithm based on grey wolf optimization and differential evolution (GWODE) was proposed.First,the optima-inclinded operator embedded GWO is utilized which is benefit to improving the optimization precision and convergence rate of the algorithm in a shorter search process.Then,an adaptive differential strategy,which can automatically adjust the value of the parameters,is employed to further improve the optimization performance of the algorithm for complex optimization functions.Thus,a hybrid algorithm with high performance is obtained and it’s more efficient to solve various function optimization problems.The optimization results on 12 benchmark functions show that the new hybrid optimization algorithm has higher search precision,better optimal performance and stronger applicability,and it’s more suitable for solving a variety of optimization problems,compared with the standard GWO,ACS,DMPSO and SinDE.
查看全文  查看/发表评论  下载PDF阅读器