一种增强局部搜索能力的改进人工蜂群算法

发布时间：2018-06-07 03:32

本文选题：人工蜂群算法 + 高维混沌系统　；参考：《智能系统学报》2017年05期

【摘要】：针对人工蜂群算法初始化群体分布不均匀和局部搜索能力弱的问题,本文提出了一种增强局部搜索能力的人工蜂群算法(ESABC)。首先,在种群初始化阶段采用高维洛伦兹混沌系统,得到遍历性好、有规律的初始群体,避免了随机初始化的盲目性。然后,采用基于对数函数的适应度评价方式,以增大种群个体间差异,减小选择压力,避免过早收敛。最后,在微分进化算法的启发下,提出了一种新的搜索策略,采用当前种群中的最佳个体来引导下一代的更新,以提高算法的局部搜索能力。通过对12个经典测试函数的仿真实验,并与其他经典的改进人工蜂群算法对比,结果表明:本文算法具有良好的寻优性能,无论在解的精度还是收敛速度方面效果都有所提高。
[Abstract]:In order to solve the problem of uneven population distribution and weak local search ability of artificial bee colony algorithm, an artificial bee colony algorithm is proposed to enhance the local search ability. Firstly, the high dimensional Lorentz chaotic system is used in the initial stage of population initialization, and a good ergodicity and regular initial population is obtained, which avoids the blindness of random initialization. Then, a logarithmic function based fitness evaluation method is used to increase the individual population differences, reduce the selection pressure and avoid premature convergence. Finally, under the inspiration of differential evolution algorithm, a new search strategy is proposed, in which the best individuals in the current population are used to guide the next generation update, so as to improve the local search ability of the algorithm. Through the simulation of 12 classical test functions, and compared with other classical improved artificial bee colony algorithms, the results show that the proposed algorithm has a good performance of optimization, both the accuracy of the solution and the convergence rate are improved.
【作者单位】：华侨大学工学院;华侨大学计算机科学与技术学院;
【基金】：国家自然科学基金资助项目(61203242) 物联网云计算平台建设资助项目(2013H2002) 华侨大学研究生科研创新能力培育计划资助项目(1511322003)
【分类号】：TP18

【相似文献】