一种快速高效的人工蜂群算法

针对人工蜂群算法收敛速度慢和易陷入局部最优的缺点,在雇佣蜂搜索阶段提出了一种基于多维搜索和一维搜索的混合搜索策略,能克服单一一维搜索下收敛速度慢的缺点,有效加快收敛速度;提出了新的跟随蜂蜜源选择策略,可保证种群多样性,增强算法全局搜索能力。通过对12个基准测试函数进行仿真实验并与原算法进行比较,其结果表明改进的算法在收敛速度和精度上均优于人工蜂群算法。

A Fast and Efficient Artificial Bee Colony Algorithm

For the slow convergence and susceptibility to local minima of the artificial bee colony algorithm,a hybrid search strategy based on multi-dimensional search and linear search in the employment bee search is presented,which improves convergence rate of the algorithm under single one-dimensional search strategy.A new selection strategy for following the bees is also proposed to enhance the diversity of population and strengthen global searching ability.Finally,the improved algorithm is compared with standard algorithms through simulation experiment on twelve benchmark test functions,the results show that the improved algorithm outperform the standard algorithm in both convergence rate and searching precision.