多阶段动态扰动和动态惯性权重的布谷鸟算法

doi:10.3778/j.issn.1002-8331.2012-0281

摘要/Abstract

摘要： 针对布谷鸟仿生智能优化算法存在着的易陷入局部最优、求解精度低以及收敛速度慢等问题，提出了基于多阶段动态扰动和动态惯性权重的布谷鸟搜索算法（MACS）。利用多阶段动态扰动策略对布谷鸟算法的全局位置的最优鸟巢位置根据方差可调的正态随机分布进行扰动，有利于增加种群的多样性和鸟窝位置的灵活性，提高算法全局搜索能力。在局部位置处引入动态惯性权重，使得算法有效克服易陷入局部最优的缺陷，提高局部寻优搜索能力。引入了动态切换概率[p]代替固定概率，可以动态平衡全局搜索和局部搜索。通过与4种算法相比和11个测试函数的仿真结果表明：改进布谷鸟算法（MACS）的寻优性能明显提高，收敛速度更快，求解精度更高，具有更强的全局搜索能力和跳出局部最优能力。

关键词: 布谷鸟算法, 多阶段动态扰动, 动态惯性权重, 自适应

Abstract: The bionic intelligent optimization algorithm of cuckoo bird is prone to fall into the problems of low local optimal solution accuracy and slow convergence speed, This paper presents a cuckoo search algorithm based on multi-stage dynamic disturbance and dynamic inertia weight（MACS）. Firstly, the multi-stage dynamic disturbance strategy is used to disturb the optimal nest position of the global position of cuckoo algorithm according to the normal random distribution with adjustable variance. It is beneficial to increase the diversity of the population and the flexibility of the nest location, and improve the global searching ability of the algorithm. Secondly, the dynamic inertia weight is introduced in the local position, which makes the algorithm overcome the defect of falling into the local optimum effectively and improve the local optimization search ability. Finally, dynamic switching probability [p] is introduced instead of fixed probability, which can dynamically balance global searching and local searching. This paper compares with 4 algorithms and 11 test functions. The simulation results show that the improved cuckoo algorithm（MACS） has better optimization performance, faster convergence speed, higher solution accuracy, stronger global searching ability and jumping out of local optimal ability.

Key words: cuckoo algorithm, multi-stage dynamic disturbance, dynamic inertia weight, self-adaption

张珍珍, 贺兴时, 于青林, 杨新社. 多阶段动态扰动和动态惯性权重的布谷鸟算法[J]. 计算机工程与应用, 2022, 58(1): 79-88.

ZHANG Zhenzhen, HE Xingshi, YU Qinglin, YANG Xinshe. Cuckoo Algorithm for Multi-stage Dynamic Disturbance and Dynamic Inertia Weight[J]. Computer Engineering and Applications, 2022, 58(1): 79-88.

参考文献

[1] PAN X Q，XUE L M，LI R X.A new and efficient firefly algorithm for numerical optimization problems[J].Neural Computing and Applications，2019，31：1445-1453.
[2] MIRJALILI S.Moth-flame optimization algorithm：a novel nature-inspired beuristicparadigm[J].Knowledge Based Systems，2015，89（1）：228-249.
[3] JUANG C F.A hybrid of genetic algorithm and particle swarm optimization for recurrent network design[J].Systems Man and Cybernetics Society，2004，34（2）：997-1006.
[4] 第五杨萌，贺兴时.基于随机惯性权重的自适应花粉算法[J].纺织高校基础科学学报，2020，33（3）：81-85.
DIWU Y M，HE X S.Adaptive flower pollination algorithm based on random inertial weights[J].Journal of Basic Science of Textile Universities，2020，33（3）：81-85.
[5] SAYED G I，KHORIBA G，HAGGAG M H.A novel chaotic salp swarm algorithm for global optimization and feature Selection[J].Applied Intelligence，2018，48（10）：3462-3481.
[6] YANG X S，DEB S.Cuckoo search via levy flight[C]//Proceedings of World Congress on Nature & Biologically Inspired Computing，2009：210-214.
[7] 柳新妮，马苗.布谷鸟搜索算法在多阈值图像分割中的应用[J].计算机工程，2013，39（7）：274-278.
LIU X N，MA M.Application of cuckoo search algorithm in multi-threshold image segmentation[J].Computer Engineering，2013，39（7）：274-278.
[8] LIU X Y，FU H.PSO-based support vector machine with cuckoo search technique for clinical disease diagnoses[J].The Scientific World Journal，2014（4）：548483.
[9] OUAARAB A，AHIOD B，YANG X S.Discrete cuckoo search algorithm for thetravelling salesman problem[J].Neural Computing and Applications，2014，24（7/8）：1659-1669.
[10] SETHI R，PANDA S，SAHOO B P.Cuckoo search algorithm based optimal tuning of PID structured TCSC control[M]//Computational Intelligence in Data Mining-Volume 1.Odisha：Springer，2015：251-263.
[11] YANG X S，DEB S.Engineering optimization by cuckoo search[J].Int’l Journal of Mathematical Modeling and Numerical Optimization，2010，1（4）：330-343.
[12] GARG A，SAHU O P.Cuckoo search based optimal mask generation for noise suppression and enhancement of speech signal[J].Journal of King Saud University Computer and Information Sciences，2015，27（3）：269-277.
[13] GHERBOUDJ A，LAYEB A.Solving 0-1 Knapsack problems by a discrete-binary version of cuckoo search algorithm[J].International Journal of Bio-Inspired Computation，2012，4（4）：229-236.
[14] KANAGARAJ G，PONNAMBALAM S G，JAWAHAR N.A hybrid cuckoo search and genetic algorithm for reliability redundancy allocation problems[J].Computers & Industrial Engineering，2013，66（4）：1115-1124.
[15] 王凡，贺兴时，王燕，等.基于CS算法的Markov模型及收敛性分析[J].计算机工程，2012，38（11）：180-182.
WANG F，HE X S，WANG Y，et al.Markov model and convergence analysis based on CS algorithm[J].Computer Engineering，2012，38（11）：180-182.
[16] 宋庆庆，贺兴时，郭旭.基于混沌序列的布谷鸟算法改进[J].纺织高校基础科学学报，2017，30（3）：423-428.
SONG Q Q，HE X S，GUO X.An improvment Cuckoo search algorithm based on chaotic sequence[J].Journal of Basic Science of Textile Universities，2017，30（3）：423-428.
[17] 陈程，贺兴时，杨新社.动态调整概率的双重布谷鸟搜索算法[J].计算机科学与探索，2021，15（5）：859-880.
CHEN C，HE X S，YANG X S.Double Cuckoo search algorithm with dynamically adjusted probability[J].Journal of Frontiers of Computer Science and Technology，2021，15（5）：859-880.
[18] 孙敏，韦慧.一种改进的自适应惯性权重布谷鸟算法[J].长江大学学报（自然科学版），2019，16（7）：81-87.
SUN M，WEI H.An improved adaptive inertial weight cuckoo algorithm[J].Journal of Changjiang University（Natural Science Edition），2019，16（7）：81-87.
[19] 高文欣，刘升，肖子雅，等.柯西变异和自适应权重优化的蝴蝶算法[J].计算机工程与应用，2020，56（15）：43-50.
GAO W X，LIU S，XIAO Z Y，et al.Butterfly optimization algorithm based on Cauchy variation and adaptive weight[J].Computer Engineering and Applications，2020，56（15）：43-50.