多策略混合搜索的人工蜂群算法  

Artificial bee colony algorithm based on multi-strategy hybrid search

作　　者：宋晓宇[1] 赵月 赵明[1] SONG Xiao-yu;ZHAO Yue;ZHAO Ming(School of Information and Control Engineering,Shenyang Jianzhu University,Shenyang 110168,China)

机构地区：[1]沈阳建筑大学信息与控制工程学院,辽宁沈阳110168

出　　处：《计算机工程与设计》2020年第9期2530-2537,共8页Computer Engineering and Design

基　　金：辽宁省自然科学基金项目(2017054767)。

摘　　要：为解决基本人工蜂群算法收敛速度慢、开发能力不足的问题,提出多策略混合搜索的人工蜂群算法。在雇佣蜂阶段采用两个具有不同探索与开发特征的搜索策略,分配不同的混合比例,增加种群多样性;观察蜂阶段将精英解作为搜索起点,修改食物源选择方式,加快种群收敛。利用不同搜索策略的不同特征,以及合适的混合比例,实现算法在探索与开发之间的平衡。22个标准函数测试集的实验对比结果表明,提出算法在搜索精度、稳定性、收敛速度方面均优于其它算法。To solve the low convergence speed and insufficient exploitation ability in the original artificial bee colony algorithm,an artificial bee colony algorithm based on multi-strategy hybrid search(MHABC)was proposed.In the employed bee stage,two search strategies with different exploration and exploitation characteristics were adopted and different hybrid proportions were allocated to increase the population diversity.In the onlooker stage,an elite solution was regarded as the search starting point and the food source selection method was modified,which accelerated the population convergence.Using different search strategies with different characteristics and appropriate hybrid proportion,the balance between exploration and exploitation of the algorithm was achieved.Experimental results of 22 standard functions show that the proposed algorithm is superior to other algorithms in search accuracy,stability and convergence speed.

关 键 词：人工蜂群算法 混合搜索 搜索策略 高斯分布 精英解 探索与开发 混合比例 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]