摘要
传统人工蜂群算法存在收敛速度较慢以及容易陷入局部最优解等不足,本文针对此提出了一种基于自适应随机优化策略的人工蜂群改进算法.在该策略中,首先利用自适应思想定义了新的位置更新公式,由此提高了蜂群间交互的相关性;其次利用双向随机优化机制约束适应度函数的搜索方向,由此提高了算法的局部搜索能力;另外将粒子群算法引入到改进人工蜂群算法的初始阶段,利用其收敛速度快的特性以较少的迭代次数产生全局最优解作为初始蜜源位置,由此提高了算法的收敛速度.最后以三个基准函数作为测试样本进行仿真实验,对算法的寻优精度、收敛速度、执行效率、全局搜索能力和跳出局部极值并避免"早熟"的能力进行了验证分析,结果表明:改进后的算法在搜索性能及收敛速度方面均有明显提高.
The traditional Artificial Bee Colony（ABC）algorithm has some disadvantages such as slow searching speed and easy to fall into local optima solution,in order to this disadvantages,we proposed an improved ABC algorithm based on self-adaptive Random Optimization strategy（SRABC）was proposed.Firstly,the improved algorithm was derived from the self-adaptive method to update the new location of ABC so as to improve the correlation within the bee colony.Secondly,Bidirectional Random Optimization（BRO）mechanism was used to restrain the direction of searching for fitness function in order to improve local searching ability.On the other hand,Particle Swarm Optimization（PSO）algorithm was introduced at the initial stage of the improved ABC algorithm.The global optimal result is produced using the fast convergence process to be the initial position of honey source.The convergence rate is then improved in this way.Finally,the searching precision,convergence rate,execution efficiency,global searching ability are verified respectively.The simulation results in three benchmark functions show that the proposed algorithm has obviously better performance in search ability and convergence rate.
出处
《小型微型计算机系统》
CSCD
北大核心
2018年第2期235-239,共5页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(612020490)资助；航空科学基金项目(20150896010)资助.
关键词
群体智能
人工蜂群
双向随机优化
自适应
粒子群
swarm intelligence artificial bee colony（ABC） bidirectional random optimization（BRO） self-adaptive particle swarm optimization（PSO）
