均衡单进化布谷鸟算法
|
摘要
针对布谷鸟算法采用整体评价策略处理多维度自变量相关优化问题时,维度耦合现象会恶化算法的搜索速度和收敛精度,提出均衡单进化的布谷鸟算法(ESCES).该算法给出一种新型的均衡单进化函数评价策略,即每一代进化只随机更新目标函数的单个维度,并且随机更新的维度服从均匀分布,避免多维度之间互相干扰.同时,提出两种新型随机游动步长更新学习律,提高了优化算法的全局搜索速度和收敛精度.实验测试结果和显著性统计结果表明,ESCES算法与5个改进CS算法及7个其它最新智能优化算法相比,在全局寻优性能、搜索速度和收敛精度上均获得较大的改进.
For the whole evaluation strategy in cuckoo search algorithm in the face of multi-dimension function optimization problems, the coupling phenomena among dimensions will deteriorate the search speed and convergence accuracy.Therefore,a new cuckoo search algorithm based on the equilibrium single evolution mechanism is proposed. Then,a new equilibrium single evolution evaluation strategy is also used to update randomly the single dimension of the objective function on each iteration. Note that the randomly updated dimensions obey the uniform distribution to avoid mutual interference between dimensions. Furthermore, two new random walking update laws are proposed to improve the global search speed and convergence accuracy. The results of the 10 benchmark functions and statistical significance demonstrate that ESCES algorithm has a great improvement in global optimization performance, search speed and convergence accuracy compared with the five modified CS algorithms and seven other state-of-the art algorithms.
For the whole evaluation strategy in cuckoo search algorithm in the face of multi-dimension function optimization problems, the coupling phenomena among dimensions will deteriorate the search speed and convergence accuracy.Therefore,a new cuckoo search algorithm based on the equilibrium single evolution mechanism is proposed. Then,a new equilibrium single evolution evaluation strategy is also used to update randomly the single dimension of the objective function on each iteration. Note that the randomly updated dimensions obey the uniform distribution to avoid mutual interference between dimensions. Furthermore, two new random walking update laws are proposed to improve the global search speed and convergence accuracy. The results of the 10 benchmark functions and statistical significance demonstrate that ESCES algorithm has a great improvement in global optimization performance, search speed and convergence accuracy compared with the five modified CS algorithms and seven other state-of-the art algorithms.
引文
[1] Yang X S,Deb S. Engineeringoptimisation by Cuckoosearch[J]. International Journal of M athematical M odel-ling&Numerical Optimisation,2010,1(4):330-343.
[2]Basu M,Chowdhury A. Cuckoo search algorithm for eco-nomic dispatch[J]. Energy,2013,60(7):99-108.
[3]El-Maleh A H,Sait S M,Bala A. State assignment for areaminimization of sequential circuits based on cuckoo searchoptimization[J]. Computers&Electrical Engineering,2015,44(14):13-23.
[4]Zhu X,Wang N. Cuckoo search algorithm with membranecommunication mechanism for modeling overhead cranesystems using RBF neural netw orks[J]. Applied Soft Com-puting,2017,56:458-471.
[5]Xiao L,Shao W,Yu M,et al. Research and application of ahybrid w avelet neural netw ork model w ith the improvedcuckoo search algorithm for electrical pow er system fore-casting[J]. Applied Energy,2017,198:203-222.
[6]Sun W,Sun J. Daily PM2. 5 concentration prediction basedon principal component analysis and LSSVM optimized bycuckoo search algorithm[J]. Journal of Environmental Man-agement,2017,188(1):144-152.
[7]Aziz M A E. Source localization using TDOA and FDOAmeasurements based on modified cuckoo search algorithm[J]. Wireless Networks,2017,23(2):487-495.
[8] Radovan R. Bulatovic,Stevan R. Dordevic,Vladimir S.Dordevic. Cuckoo search algorithm:A metaheuristic ap-proach to solving the problem of optimum synthesis of asix-bar double dw ell linkage[J]. M echanism and M achineTheory,2013,61(1):1-13.
[9]Han W,Xu J,Zhou M,et al. Cuckoo search and particle fil-ter-based inversing approach to estimating defects via mag-netic flux leakage signals[J]. IEEE Transactions on M ag-netics,2016,52(4):1-11.
[10] Srivastav A,Agrawal S. Multi-objective optimization ofslow moving inventory system using cuckoo search[J].Intelligent Automation&Soft Computing,2017,3(6):1-7.
[11]Yamany W,El-Bendary N,Hassanien A E,et al. Multi-objective cuckoo search optimization for dimensionalityreduction[J]. Procedia Computer Science,2016,96(8):207-215.
[12]Wang Z,Li Y. Irreversibility analysis for optimization de-sign of plate fin heat exchangers using a multi-objectivecuckoo search algorithm[J]. Energy Conversion&M an-agement,2015,10(1):126-135.
[13] Piechocki J,Ambroziak D,Palkowski A,et al. Use ofmodified cuckoo search algorithm in the design process ofintegrated pow er systems for modern and energy self-suf-ficient farms[J]. Applied Energy,2014,114(114):901-908.
[14] Nadjemi O,Nacer T,Hamidat A,et al. Optimal hybridPV/w ind energy system sizing:Application of cuckoosearch algorithm foralgerian dairy farms[J]. Renew able&Sustainable Energy Review s,2017,70:1352-1365.
[15] Walton S,Hassan O,Morgan K,et al. Modified cuckoosearch:A new gradient free optimization algorithm[J].Chaos Solitons&Fractals,2011,44(9):710-718.
[16]Valian E,Tavakoli S,Mohanna S,et al. Improved cuckoosearch for reliability optimization problems[J]. Comput-ers&Industrial Engineering,2013,64(1):459-468.
[17]Li X T,Yin M H. Modified cuckoo search algorithm withself adaptive parameter method[J]. Information sciences,2015,298(12):80-97.
[18] Walton S,Hassan O,Morgan K,et al. Modified cuckoosearch:A new gradient free optimisation algorithm[J].Chaos Solitons&Fractals,2011,44(9):710-718.
[19]Fateen S E K,Bonilla-Petriciolet A. A note on effectivephase stability calculations using a Gradient-Based CuckooSearch algorithm[J]. Fluid Phase Equilibria,2014,375(6):360-366.
[20]Xiao L,Shao W,Yu M,et al. Research and application ofa hybrid w avelet neural netw ork model w ith the improvedcuckoo search algorithm for electrical pow er system fore-casting[J]. Applied Energy,2017,198:203-222.
[21]Cheung N J,Ding X M,Shen H B. A nonhomogeneouscuckoo search algorithm based on quantum mechanism forreal parameter optimization[J]. IEEE Transactions on Cy-bernetics,2017,47(2):391-402.
[22]Zhong Y,Liu X,Wang L,et al. Particle swarm optimisati-on algorithm w ith iterative improvement strategy formulti-dimensional function optimisation problems[J]. In-ternational Journal of Innovative Computing&Applica-tions,2012,4(3):223-232.
[23] Ren W J,Pan Q K,Liang J J. An improved harmonysearch algorithm for multi-dimensional function optimiza-tion problem[A]. IEEE Fifth International Conference onBio-Inspired Computing:Theories and Applications[C].IEEE,2010. 391-395.
[24]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):2687-2698.Wang L J,Yi Y L,Zhong Y W. Cuckoo search algorithmw ith dimension by dimension improvement[J]. Journal ofSoftw are,2013,24(11):2687-2698.(in Chinese)
[25]Valian E,Tavakoli S,Mohanna S,et al. Improved cuckoosearch for reliability optimization problems[J]. Comput-ers&Industrial Engineering,2013,64(1):459-468.
[26]Li X,Yin M. A particle swarm inspired cuckoo search al-gorithm for real parameter optimization[J]. Soft Compu-ting,2016,20(4):1389-1413.
[27]Nguyen T T,Vo D N. The application of one rank cuckoosearch algorithm for solving economic load dispatch prob-lems[J]. Applied Soft Computing,2015,37(C):763-773.
[28]Ma L B,Zhu Y L,Zhang D Y,et al. A hybrid approach toartificial bee colony algorithm[J]. Neural Computing&Applications,2016,27(2):387-409.
[29]Gao W F,Huang L L,Liu S Y,et al. Artificial bee colonyalgorithm based on information learning[J]. IEEE Trans-actions on Cybernetics,2015,45(12):2827-2939.
[30] Wu Z,Yu D. Application of improved bat algorithm forsolar PV maximum pow er point tracking under partiallyshaded condition[J]. Applied Soft Computing,2018,62(C):101-109.
[31] Li Y,Bai X,Jiao L,et al. Partitioned-cooperative quan-tum-behaved particle sw arm optimization based on multi-level thresholding applied to medical image segmentation[J]. Applied Soft Computing,2017,56(C):345-356.
[32]Singh S,Jagdish J,Bansal C,et al. Accelerating artificialbee colony algorithm w ith adaptive local search[J],M emetic Computing,2015,7(3):215-230.
[33]Portilla-Flores E A,Sánchez-Márquez A,Flores-Pulido L,et al. Enhancing the harmony search algorithm perform-ance on constrained numerical optimization[J]. IEEE Ac-cess,2017,(99):1-21.
[34]He L,Huang S. Modified firefly algorithm based multilev-el thresholding for color image segmentation[J]. Neuro-computing,2017,240:152-174.
[2]Basu M,Chowdhury A. Cuckoo search algorithm for eco-nomic dispatch[J]. Energy,2013,60(7):99-108.
[3]El-Maleh A H,Sait S M,Bala A. State assignment for areaminimization of sequential circuits based on cuckoo searchoptimization[J]. Computers&Electrical Engineering,2015,44(14):13-23.
[4]Zhu X,Wang N. Cuckoo search algorithm with membranecommunication mechanism for modeling overhead cranesystems using RBF neural netw orks[J]. Applied Soft Com-puting,2017,56:458-471.
[5]Xiao L,Shao W,Yu M,et al. Research and application of ahybrid w avelet neural netw ork model w ith the improvedcuckoo search algorithm for electrical pow er system fore-casting[J]. Applied Energy,2017,198:203-222.
[6]Sun W,Sun J. Daily PM2. 5 concentration prediction basedon principal component analysis and LSSVM optimized bycuckoo search algorithm[J]. Journal of Environmental Man-agement,2017,188(1):144-152.
[7]Aziz M A E. Source localization using TDOA and FDOAmeasurements based on modified cuckoo search algorithm[J]. Wireless Networks,2017,23(2):487-495.
[8] Radovan R. Bulatovic,Stevan R. Dordevic,Vladimir S.Dordevic. Cuckoo search algorithm:A metaheuristic ap-proach to solving the problem of optimum synthesis of asix-bar double dw ell linkage[J]. M echanism and M achineTheory,2013,61(1):1-13.
[9]Han W,Xu J,Zhou M,et al. Cuckoo search and particle fil-ter-based inversing approach to estimating defects via mag-netic flux leakage signals[J]. IEEE Transactions on M ag-netics,2016,52(4):1-11.
[10] Srivastav A,Agrawal S. Multi-objective optimization ofslow moving inventory system using cuckoo search[J].Intelligent Automation&Soft Computing,2017,3(6):1-7.
[11]Yamany W,El-Bendary N,Hassanien A E,et al. Multi-objective cuckoo search optimization for dimensionalityreduction[J]. Procedia Computer Science,2016,96(8):207-215.
[12]Wang Z,Li Y. Irreversibility analysis for optimization de-sign of plate fin heat exchangers using a multi-objectivecuckoo search algorithm[J]. Energy Conversion&M an-agement,2015,10(1):126-135.
[13] Piechocki J,Ambroziak D,Palkowski A,et al. Use ofmodified cuckoo search algorithm in the design process ofintegrated pow er systems for modern and energy self-suf-ficient farms[J]. Applied Energy,2014,114(114):901-908.
[14] Nadjemi O,Nacer T,Hamidat A,et al. Optimal hybridPV/w ind energy system sizing:Application of cuckoosearch algorithm foralgerian dairy farms[J]. Renew able&Sustainable Energy Review s,2017,70:1352-1365.
[15] Walton S,Hassan O,Morgan K,et al. Modified cuckoosearch:A new gradient free optimization algorithm[J].Chaos Solitons&Fractals,2011,44(9):710-718.
[16]Valian E,Tavakoli S,Mohanna S,et al. Improved cuckoosearch for reliability optimization problems[J]. Comput-ers&Industrial Engineering,2013,64(1):459-468.
[17]Li X T,Yin M H. Modified cuckoo search algorithm withself adaptive parameter method[J]. Information sciences,2015,298(12):80-97.
[18] Walton S,Hassan O,Morgan K,et al. Modified cuckoosearch:A new gradient free optimisation algorithm[J].Chaos Solitons&Fractals,2011,44(9):710-718.
[19]Fateen S E K,Bonilla-Petriciolet A. A note on effectivephase stability calculations using a Gradient-Based CuckooSearch algorithm[J]. Fluid Phase Equilibria,2014,375(6):360-366.
[20]Xiao L,Shao W,Yu M,et al. Research and application ofa hybrid w avelet neural netw ork model w ith the improvedcuckoo search algorithm for electrical pow er system fore-casting[J]. Applied Energy,2017,198:203-222.
[21]Cheung N J,Ding X M,Shen H B. A nonhomogeneouscuckoo search algorithm based on quantum mechanism forreal parameter optimization[J]. IEEE Transactions on Cy-bernetics,2017,47(2):391-402.
[22]Zhong Y,Liu X,Wang L,et al. Particle swarm optimisati-on algorithm w ith iterative improvement strategy formulti-dimensional function optimisation problems[J]. In-ternational Journal of Innovative Computing&Applica-tions,2012,4(3):223-232.
[23] Ren W J,Pan Q K,Liang J J. An improved harmonysearch algorithm for multi-dimensional function optimiza-tion problem[A]. IEEE Fifth International Conference onBio-Inspired Computing:Theories and Applications[C].IEEE,2010. 391-395.
[24]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):2687-2698.Wang L J,Yi Y L,Zhong Y W. Cuckoo search algorithmw ith dimension by dimension improvement[J]. Journal ofSoftw are,2013,24(11):2687-2698.(in Chinese)
[25]Valian E,Tavakoli S,Mohanna S,et al. Improved cuckoosearch for reliability optimization problems[J]. Comput-ers&Industrial Engineering,2013,64(1):459-468.
[26]Li X,Yin M. A particle swarm inspired cuckoo search al-gorithm for real parameter optimization[J]. Soft Compu-ting,2016,20(4):1389-1413.
[27]Nguyen T T,Vo D N. The application of one rank cuckoosearch algorithm for solving economic load dispatch prob-lems[J]. Applied Soft Computing,2015,37(C):763-773.
[28]Ma L B,Zhu Y L,Zhang D Y,et al. A hybrid approach toartificial bee colony algorithm[J]. Neural Computing&Applications,2016,27(2):387-409.
[29]Gao W F,Huang L L,Liu S Y,et al. Artificial bee colonyalgorithm based on information learning[J]. IEEE Trans-actions on Cybernetics,2015,45(12):2827-2939.
[30] Wu Z,Yu D. Application of improved bat algorithm forsolar PV maximum pow er point tracking under partiallyshaded condition[J]. Applied Soft Computing,2018,62(C):101-109.
[31] Li Y,Bai X,Jiao L,et al. Partitioned-cooperative quan-tum-behaved particle sw arm optimization based on multi-level thresholding applied to medical image segmentation[J]. Applied Soft Computing,2017,56(C):345-356.
[32]Singh S,Jagdish J,Bansal C,et al. Accelerating artificialbee colony algorithm w ith adaptive local search[J],M emetic Computing,2015,7(3):215-230.
[33]Portilla-Flores E A,Sánchez-Márquez A,Flores-Pulido L,et al. Enhancing the harmony search algorithm perform-ance on constrained numerical optimization[J]. IEEE Ac-cess,2017,(99):1-21.
[34]He L,Huang S. Modified firefly algorithm based multilev-el thresholding for color image segmentation[J]. Neuro-computing,2017,240:152-174.