计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (7): 176-181.DOI: 10.3778/j.issn.1002-8331.1610-0126

• 模式识别与人工智能 • 上一篇    下一篇

混合改进搜索策略的鸡群优化算法

黄  霞1,2,叶春明1,郑  军1   

  1. 1.上海理工大学 管理学院,上海 200093
    2.江苏科技大学 张家港校区,江苏 张家港 215600
  • 出版日期:2018-04-01 发布日期:2018-04-16

Chicken swarm optimization algorithm of hybrid evolutionary searching strategy

HUANG Xia1,2, YE Chunming1, ZHENG Jun1   

  1. 1.Business School, University of Shanghai for Science and Technology, Shanghai 200093, China
    2.Jiangsu University of Science and Technology, Zhangjiagang, Jiangsu 215600, China
  • Online:2018-04-01 Published:2018-04-16

摘要: 针对鸡群算法易陷入局部最优和出现早熟收敛的情况,提出一种混合改进搜索策略的鸡群优化算法。该算法通过种内和种间竞争,确定子群规模及等级次序,子群角色通过竞争繁殖进行动态更新。种群进化寻优中引入全局最优引导策略和动态惯性策略,个体的寻食学习通过动态惯性策略进行自我调整,并同时接受子群与种群中的最优个体引导,以平衡局部搜索和全局搜索之间的关系。仿真实验结果表明,与基本鸡群算法和粒子群算法等相比,改进后的鸡群算法能有效提高算法的收敛精度和收敛速度。

关键词: 群体智能, 鸡群算法, 动态惯性策略, 惯性权重

Abstract: Considering the problem that the original chicken swarm optimization algorithm is easy to fall into local optimum and becomes premature convergence, a chicken swarm optimization of hybrid evolutionary searching strategy is proposed. In this algorithm, subgroup size and hierarchy order are determined by interspecific and intraspecific competition, and subgroup roles are dynamically updated by competitive breeding. The global optimal guidance strategy and dynamic inertia strategy are introduced into the evolution optimization of population. Individual learning in search of food is adjusted through dynamic inertia strategy and guided by the optimal individual of the subgroup and populations, in order to balance the relationship between the global search and local search. The simulated experimental results show that the proposed algorithm is able to effectively improve the convergence speed and convergence precision compared with particle swarm optimization and original chicken swarm optimization.

Key words: swarm intelligence, chicken swarm optimization, dynamic inertia strategy, inertia weight