基于族群机制的花朵授粉算法  

Improved Flower Pollination Algorithm Based on Ethnic Group Mechanism

作　　者：肖辉辉[1,2] 段艳明[1] XIAO Hui-hui;DUAN Yan-ming(School of Computer and Information Engineering,Hechi University,Yizhou 546300,China;School of Information and Technology,Jiangxi University of Finance and Economics,Nanchang 330013,China)

机构地区：[1]河池学院计算机与信息工程学院,广西宜州546300 [2]江西财经大学信息管理学院,南昌330013

出　　处：《火力与指挥控制》2017年第4期23-28,共6页Fire Control & Command Control

基　　金：国家自然科学基金(61173146);广西自然科学基金(2013GXNSFBA019022);校级青年科研基金(XJ2015QN003);江西省研究生创新基金(YC2015-B054);河池学院计算机网络与软件新技术重点实验室基金资助项目(院科研(2013)3号)

摘　　要：针对花朵授粉算法易陷入局部极值、收敛速度慢等不足,提出一种具有族群机制的花朵授粉算法。该算法把种群分成多个族群,各族群的最优个体再组成新的种群,进而促进种群间的信息交流,有效地协调种群进化过程中的全局搜索和局部搜索能力,避免个体的早熟收敛,提高算法的全局寻优能力及收敛速度。通过8个CEC2005benchmark测试函数进行测试比较,仿真结果表明,改进算法的寻优性能明显优于基本的花朵授粉算法、粒子群算法和蝙蝠算法,其收敛精度、收敛速度、鲁棒性均较对比算法有较大提高。In order to overcome the problems of easily relapsing into local extremum and low speed of convergence,a improved flower pollination algorithm based on ethnic group mechanism is presented in the paper.The algorithm divided the population into multiple ethnic groups,and the optimal individual of those ethnic groups formed a new population,so as to promote the information communication between the populations,effectively coordinate the global search and local search in the process of population evolution.It can effectively avoid local optimum,and enhance the capacity of global optimization,improve the convergence speed.The comparison and analysis results of the8CEC2005benchmark functions,the simulation results show that the proposed algorithm has the advantages of better global searching ability,faster convergence and more precise convergence than those of the basic flower pollination algorithm,particle swarm algorithm and bat algorithm.

关 键 词：花朵授粉算法 寻优性能 收敛速度 族群机制 适应度值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]