摘要
提出基于反向学习的人工蜂群算法(简称OABC算法).在人工蜂群算法的跟随蜂阶段,种群依概率进行反向学习代替跟随蜂搜索方案.保留标准人工蜂群算法中雇佣蜂和侦察蜂阶段以保证种群的探索能力以及种群的多样性,增设参数控制一般的反向学习过程中对位搜索范围,充分利用种群信息和个体信息优化种群,提高对位点的有效性,从而提高反向学习的成功率.仿真实验结果表明,OABC算法有效提升了算法寻优速度和收敛精度.
An improved artificial bee colony algorithm with opposition-based learning(OABC algorithm for short)is proposed.In the following bee phase of the artificial bee colony algorithm,the population implement opposition-based learning according to probability instead of following bee search,retains the employed bee phase and scout bee phase in the standard artificial bee colony algorithm to ensure the exploration ability and diversity of the population,and adds parameters to control the contraposition search range in the general opposition-based learning process,It makes full use of population information and individual information to optimize the population,improves the effectiveness of counterpoint,and improves the success rate of opposition-based learning.Simulation results show that the OABC algorithm effectively improves the optimization speed and convergence accuracy of the algorithm.
作者
王剑
王冰
葛孟珂
WANG Jian;WANG Bing;GE Mengke(College of Mathematical Sciences,Mudanjiang Normal University,Mudanjiang 157011,China)
出处
《牡丹江师范学院学报（自然科学版）》
2022年第1期23-30,共8页
Journal of Mudanjiang Normal University：Natural Sciences Edition
基金
国家自然科学基金项目(11871097)
牡丹江师范学院国家级课题培育项目(GP2020003)。
关键词
人工蜂群算法
反向学习
对位邻域
函数优化
artificial bee colony algorithm
opposition-based learning
counterpoint neighborhood
function optimization
