摘要
布谷鸟搜索(Cuckoo Search,CS)算法是一种简单易实现的全局优化算法,但也存在局部搜索能力弱,求解精度不高的问题.为了克服这些问题,提出一种新的均匀局部搜索和高斯变异的布谷鸟搜索算法.该算法在基于Levy飞行产生新解后执行均匀局部搜索,从而提高算法的局部开采能力,并对被宿主发现的鸟巢采用高斯变异进行重新更新,从而提高算法的寻优精度以及收敛能力.通过对包括单峰函数、多峰函数的13个基准测试函数的仿真实验和分析,验证了新算法的有效性和可靠性,实验结果表明新算法具有较好的收敛速度和收敛精度,是一种具有竞争力的算法.
CS algorithm is simple and easy to implement for global optimization problems. However,its local search ability is weak,and the precision is not high. In order to improve these defects,a novel cuckoo algorithm of uniform local search and gauss mutation is proposed in this paper. After new solutions are produced based on levy flight,the algorithm perform uniform local search and thereby the local exploitation ability is improved. The bird nest found by the host is renewed with gauss variation and thus the optimization precision and convergence ability of the algorithm are improved. The experimental studies have been conducted on 13 bechmark functions including unimodal,multimodal test functions and the validity and reliability of the new algorithm have been verified,experimental results show that the new algorithm has good convergence speed and convergence accuracy and it is a competitive algorithm.
引文
[1]Yang Xin-she,Deb S.Cuckoo search via Levy flights[C].Proceedins of World Congress on Nature&Biologically Inspired Computing,India:IEEE Publications,2009:210-214.
[2]Walton S,Hassan O,Morgan K,et al.Modified cuckoo search:a new gradient free optimisation algorithm[J].Chaos Solitons&Fractals,2011,44(9):710-718.
[3]Wang Li-jin,Yin Yi-long,Zhong Yi-wen.Cuckoo search algorithm w ith dimension by dimension improvement[J].Journal of Softw are,2013,24(11):2687-2697.
[4]Ma Can,Liu Jian,Yu Fang-ping.Research on cuckoo algorithm w ith simulated annealing[J].Journal of Chinese Computer Systems,2016,9(9):2029-2034.
[5]Peng Hu,Wu Zhi-jian,Deng Chang-shou.Enhancing differential evolution w ith commensal learning and unifrom local search[J].Chinese Journal of Electronics,2017,26(4):725-733.
[6]Qu Chi-wen,Fu Yan-ming.Cuckoo optimization algorithm based on hybrid mutation operator[J].Science Technology and Engineering,2013,27(13):8008-8012.
[7]Wang Zhong,Jia Chen-xi,Sun Yue-hua.Parasitized breeding and nestlings grow th in oriental cuckoo[J].Chinese Journal of Zoology,2004,39(1):103-105.
[8]Yang X S,Deb S.Engineering optimisation by cuckoo search[J].Int Journal of M athematical M odeling&Numerical Optimization,2010,1(4):330-343.
[9]Viswanathan G M,et al.Levy flights search patterns of wandering albatrosses[J].Nature,1996,381(6581):413-415.
[10]Viswanathan G M,et al.Levy flights in random search[J].Physica A Statistical M echanics and Its Applications,2000,282(s 1-2):1-12.
[11]Viswanathan G M,et al.Levy flights search patterns of biological organisms[J].Physica A Statistical M echanics and Its Applications,2001,295(1):85-88.
[12]Wang Yuan,Fang Kai-tai.A note on uniform distribution and experiental design[J].Chinese Science Ulletin,1981,26(6):485-489.
[13]Yao Xin,Liu Yong,Lin Guang-ming.Evolutionary programming made faster[J].IEEE Transactions on Evolutionary Computation,2002,3(2):82-102.
[14]Rosner B,Glynn R J,Lee M L.Incorporation of clustering effects for the Wilcoxon rank sum test:a largesample approach[J].Biometrics,2003,59(4):1089-1098.
[15]Friedman M.The use of ranks to avoid the assumption of normality implicit in the analysis of variance[J].Journal of the American Statistical Association,1937,32(200):675-701.
[16]Rahnamayan S,Tizhoosh H R,MMA Salama.Opposition based differential evolution[J].IEEE Transactions on Evolutionary Compution,2014,12(1):64-79.
[17]Wang Hui,Rahnamayan S,Sun Hui,et al.Gaussian barebones differential evolution[J].IEEE Transactions on Cybernetics,2013,43(2):634-647.
[18]Zhu Guo-pi,Sam K.Gbest-guided artificial bee colony algorithm for numerical function optimization[J].Applied M athematics and Computation,2010,217(7):3166-3173.
[19]Yu S,Zhu S,Ma Y,et al.A variable step size firefly algorithm for numerical optimization[J].Applied M athematics and Computation,2015,263(C):214-220.
[3]王李进,尹义龙,钟一文.逐维改进的布谷鸟搜索算法[J].软件学报,2013,24(11):2687-2697.
[4]马灿,刘坚,余方平.混合模拟退火的布谷鸟算法研究[J].小型微型计算机系统,2016,9(9):2029-2034.
[6]屈迟文,傅彦铭.基于混合变异算子的布谷鸟优化算法[J].科学技术与工程,2013,27(13):8008-8012.
[7]王众,贾陈喜,孙悦华.中杜鹃寄生繁殖及雏鸟生长一例[J].动物学杂志,2004,39(1):103-105.