基于改进人工蜂群算法的高维多目标优化

来源期刊:中南大学学报(自然科学版)2015年第6期

论文作者:王艳娇 肖婧

文章页码:2109 - 2118

关键词:高维多目标优化;人工蜂群算法;适应值评价方式;分布性维护方法

Key words:large-dimensional multi-objective optimization; artificial bee colony algorithm; fitness evaluation method; diversity-maintaining scheme

摘    要:为了提高高维多目标优化算法的收敛性和分布性,提出基于改进人工蜂群算法的高维多目标优化算法。首先,利用一种改进的适应值评价方式定量比较高维多目标中个体的优劣;其次,改进人工蜂群算法,使种群迅速收敛于最优的非支配前沿;最后,建立新的分布性维护机制使所获得的非支配解分布均匀、覆盖整个最优前沿。研究结果表明:对于3~8个目标的DTLZ系列测试函数,与PISA算法等几种较流行的高维多目标算法相比,本文方法收敛性好,解集覆盖范围广且分布均匀.

Abstract: In order to improve the convergence and diversity of large-dimensional multi-objective optimization algorithms, a novel large-dimensional multi-objective optimization algorithm based on an improved artificial bee colony algorithm was proposed. Firstly, an improved fitness evaluation method was employed to measure the superiority of every individual quantitatively. Secondly, artificial bee colony algorithm was improved to make the population converge reach the true Pareto front quickly. Finally, a novel diversity-maintaining scheme was established to make the solution set distribute uniformly and cover the whole Pareto front. The results show that the diversities and convergence of the proposed algorithm are better than other state-of-the-art large-dimensional multi-objective optimization algorithms such as PISA.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号