基于搜索能力均衡的人工蜂群算法

鉴于标准人工蜂群算法（ABC）局部开发能力不足，提出一种改进搜索策略的人工蜂群算法（IABC）。为提高ABC的局部开发能力，在其雇佣蜂阶段引入了一个新的具有最好个体引导的解搜索方程，为均衡ABC的搜索能力，在ABC跟随蜂阶段的搜索策略中引入了新的随机因素以增强ABC的全局探索能力，为了进一步平衡全局探索和局部开发能力，改进了ABC的侦察蜂搜索机制。为验证IABC的收敛效果，通过在12个复杂基准测试函数上的仿真实验并与其他算法相比较，发现IABC的收敛性能有显著提高。

Improved artificial bee colony algorithm based on balance of searching ability

In view of the defect that Artificial Bee Colony（ABC） algorithm is poor at exploitation, an Improved Artificial Bee Colony（IABC） algorithm is proposed based on two new solution search strategies. A new solution search equation, in which the other individual can be driven under the guidance of the best individual with best fitness value, is introduced so as to improve the capability of exploitation. To achieve a good tradeoff between the exploitation and exploration, a new random item is integrated into the original solution search equation to enhance the ability of exploration on the onlooker bee phase of ABC. To further balance the ability of exploration and exploitation, some modifications are done on the scout bee phase of ABC. In order to validate the convergence performance of IABC, experiments tested on twelve benchmark functions are conducted. And the experimental results show that the convergence performance of IABC is enhanced conspicuously.