一种自适应骨干细菌觅食优化算法  

An adaptive bare-bone bacterial foraging optimization algorithm

作　　者：朱永杰 李冰晓 万睿之 赵新超[1] 左兴权[2] ZHU Yongjie;LI Bingxiao;WAN Ruizhi;ZHAO Xinchao;ZUO Xingquan(School of Science,Beijing University of Posts and Telecommunications,Beijing 100876,China;School of Computer Science,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京邮电大学理学院,北京100876 [2]北京邮电大学计算机学院,北京100876

出　　处：《商丘师范学院学报》2022年第6期1-7,共7页Journal of Shangqiu Normal University

基　　金：国家自然科学基金资助项目(61973042,71772060);北京市自然科学基金资助项目(1202020)。

摘　　要：细菌觅食优化算法趋化操作中的固定步长导致收敛速度偏慢,复制操作中以一半优质细菌进行复制,降低了种群多样性,从而影响算法的寻优性能.针对以上问题,在细菌觅食优化算法的趋向操作中使游动步长随着游动次数的增加而减小,希望保持前期较大步长侧重全局勘探与后期较小步长侧重局部开发的平衡搜索;复制操作中利用骨干思想对一半优质细菌的重心和方差信息实施实时调整的高斯变异,在半种群精英搜索邻域的基础上增加了种群的多样性,提高了细菌觅食优化算法的总体性能.为了验证该自适应骨干细菌觅食优化算法,采用CEC2014基准测试函数进行仿真实验,并与其他细菌觅食算法进行比较,证明提出的改进算法具有更强的全局搜索能力和总体性能.The fixed step size in the chemotaxis operation of the bacterial foraging optimization algorithm results in a slow convergence rate.In the replication operation, a half of the high-quality bacteria are used for replication, which reduces the population diversity and affects the optimization performance of the algorithm.In response to the above problems, this article reduces the walking step length as the number of swimming increases in the trend operation of the bacterial foraging optimization algorithm.It is hoped that the larger step length in the early stage will focus on global exploration and the smaller step size in the later stage will focus on local development.In the replication operation, the backbone idea is used to perform Gaussian mutation with real-time changing in the center and variance of half of the high-quality bacteria, which increases the diversity of the population on the basis of the semi-population elite idea, and improves the comprehensive performance of the algorithm.In order to verify the adaptive bare-bone bacterial foraging optimization algorithm(BBBFO),the CEC2014 benchmark functions were used to carry out simulation experiments and compared with other bacterial foraging algorithms, which proved that the proposed BBBFO algorithm has stronger global search capabilities and comprehensive performance.

关 键 词：细菌觅食算法 骨干算法 群体智能 平衡搜索 数值优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]