摘要
针对布谷鸟算法求解复杂的问题时收敛速度过低、全局效果不理想等问题,提出基于反向学习的布谷鸟算法优化搜索方法。对当前布谷鸟群体加入反向学习策略,从全局中找出精英个体,并对个体求反向解,在所得的可行解与反向解中找出最优个体作为下一次迭代的个体。将混沌扰动策略引入鸟巢位置的确定过程,扩大布谷鸟种群的多样性,提高算法整体的收敛精度和搜索能力。最后进行仿真,运用不同方法对四个函数测试的结果中可以看出,所提方法具有更优的搜索能力和收敛速度。
During solving complex problems, cuckoo algorithm has low convergence speed and poor global effect.Therefore, a cuckoo algorithm optimization search method based on reverse learning was proposed in this work. Reverse learning strategy was introduced into the current cuckoo algorithm. The elite individual was found out from the overall situation, and the individual was solved reversely. In the feasible solution and reverse solution, the optimal individual was found as the next iteration individual. In order to expand the diversity of cuckoo population and improve the overall convergence accuracy and search ability of the algorithm, chaos disturbance strategy was introduced into the nest location determination process. Simulation results show that the algorithm has better search ability and convergence speed than the traditional algorithm.
作者
胡安明
李伟
HU An-ming;LI Wei(School of Computer Science&Engineering,Guangzhou Institute of Science and Technology,Guangzhou Guangdong 510540,China;School of Science,Jimei University,Xiamen Fujian 361021,China)
出处
《计算机仿真》
北大核心
2021年第12期276-280,共5页
Computer Simulation
基金
广东教育学会“十三五”教育科研课题(GDES1361)。
关键词
反向学习
精英个体
混沌扰动策略
收敛速度
寻优能力
Reverse learning
Elite individual
Chaos disturbance strategy
Convergence rate
Optimization ability
