基于变因子加权学习与邻代维度交叉策略的改进CSA算法
|
摘要
针对乌鸦搜索算法(CSA)优化高维问题时存在寻优精度低、局部极值逃逸能力弱等问题,提出一种耦合多个体变因子加权学习机制与最优个体邻代维度交叉策略的改进乌鸦搜索算法(ICSA).该算法随迭代进程动态修正模型控制参数(感知概率和飞行长度),利用多个体的变因子加权学习机制保证子代个体同时继承跟随乌鸦与上代最优个体的位置信息以避免单个体继承的过快种群同化并减小陷入局部极值的风险;同时构建历史最优个体的邻代维度交叉策略,并按维度绝对差异大的优先替换原则更新最优个体位置,以保留历代最优维度信息并提高算法的局部极值逃逸能力.数值实验结果分别验证了模型参数对CSA算法性能的一定影响,加权学习因子不同递变形式对ICSA算法性能改善的有效性与差异性以及改进算法的优越寻优性能.
Considering that crow search algorithm( CSA) has low optimization accuracy and weak local-optimum escape ability in optimizing high-dimensional problems, an improved crow search algorithm( ICSA) is proposed by coupling the variable-factors' weighted learning mechanism of multiple individuals( Mi-VWL) and the adjacent-generations dimension crossover strategy of the best individual( Bi-ADC). In the proposed algorithm, the model parameters,i. e. awareness probability and flight length, are firstly modified dynamically with increasing number of iterations. Meanwhile, the Mi-VWL is introduced to guarantee that offspring individuals of crow population can inherit position information from the followed crow and the best individual of the last generation simultaneously,which is advantageous to avoid the over-rapid population intensification of single-individual learning and reduce the algorithm's risk on dropping into local optimum. Furthermore,BiADC is constructed and the priority replacement principle of larger absolute value difference of dimensions between two-generations is adopted to update position of the best individual,which is beneficial to retain the optimal dimension information of historical best crows and enhance the local extreme escape ability of algorithms. Experimental results verify the influence of modal parameters on CSA's performance, the effectiveness and differences of different-type weighted learning factor on improving ICSA's capability and the superior optimization ability of the proposed algorithm, respectively.
Considering that crow search algorithm( CSA) has low optimization accuracy and weak local-optimum escape ability in optimizing high-dimensional problems, an improved crow search algorithm( ICSA) is proposed by coupling the variable-factors' weighted learning mechanism of multiple individuals( Mi-VWL) and the adjacent-generations dimension crossover strategy of the best individual( Bi-ADC). In the proposed algorithm, the model parameters,i. e. awareness probability and flight length, are firstly modified dynamically with increasing number of iterations. Meanwhile, the Mi-VWL is introduced to guarantee that offspring individuals of crow population can inherit position information from the followed crow and the best individual of the last generation simultaneously,which is advantageous to avoid the over-rapid population intensification of single-individual learning and reduce the algorithm's risk on dropping into local optimum. Furthermore,BiADC is constructed and the priority replacement principle of larger absolute value difference of dimensions between two-generations is adopted to update position of the best individual,which is beneficial to retain the optimal dimension information of historical best crows and enhance the local extreme escape ability of algorithms. Experimental results verify the influence of modal parameters on CSA's performance, the effectiveness and differences of different-type weighted learning factor on improving ICSA's capability and the superior optimization ability of the proposed algorithm, respectively.
引文
[1]ZHANG Y,LIU S,ZHANG X. An optimized supply chain netw ork model based on modified genetic algorithm[J].Chinese Journal of Electronics,2017,26(3):468-476.
[2] XUAN H,ZHANG R,SHI S. An efficient cuckoo search algorithm for system-level fault diagnosis[J]. Chinese Journal of Electronics,2016,25(6):999-1004.
[3]ZHANG L,LIU M,HAO J,et al. Scheduling semiconductor w afer fabrication using a new harmony search algorithm based on receipt priority interval[J]. Chinese Journal of Electronics,2016,25(5):866-872.
[4]HOLLAND J. Genetic algorithms[J]. Scientific American,1992,267:66-72.
[5] FOGEL D. Artificial intelligence through simulated evolution[A]. Proceedings of National Conference on Emerging Trends&Applications in Computer Science[C]. USA:Wiley-IEEE Press,1966. 227-296.
[6]KENNEDY J,EBERHART R. Particle swarm optimization[A]. Proceedings of IEEE International Conference on Neural Netw orks(Vol. 4)[C]. USA:IEEE,1995. 1942-1948.
[7]DORIGO M. Ant Colony Optimization for Vehicle Routing Problem[D]. Ph D thesis,Politecnico di M ilano,M ilan,Italy,1992.
[8]KIRKPATRICK S,GELATT C D,VECCHI M P. Optimization by simmulated annealing[J]. Science,1983,220(4598):671-680.
[9] MIRJALILI S,MIRJALILI S M,HATAMLOU A. Multiverse optimizer:A nature-inspired algorithm for global optimization[J]. Neural Computing and Applications,2016,27(2):495-513.
[10]GONCALVES M S,LOPEZ R H,MIGUEL L F F. Search group algorithm:a new metaheuristic method for the optimization of truss structures[J]. Computers&Structures,2015,153:165-184.
[11] MIRJALILI S. The ant lion optimizer[J]. Advances in Engineering Softw are,2015,83:80-98.
[12]ASKRZAADEH A. A novel metaheuristic method for solving constrained engineering optimization problems:Crow search algorithm[J]. Computers&Structures,2016,169:1-12.
[13]LIU D,LIU C,FU Q,et al. ELM evaluation model of regional groundw ater quality based on the crow search algorithm[J]. Ecological Indicators,2017,81:302-314.
[14]OLIVA D,HINOJOSA S,CUEVAS E,et al. Cross entropy based thresholding for magnetic resonance brain images using crow search algorithm[J]. Expert Systems w ith Applications,2017,79:164-180.
[2] XUAN H,ZHANG R,SHI S. An efficient cuckoo search algorithm for system-level fault diagnosis[J]. Chinese Journal of Electronics,2016,25(6):999-1004.
[3]ZHANG L,LIU M,HAO J,et al. Scheduling semiconductor w afer fabrication using a new harmony search algorithm based on receipt priority interval[J]. Chinese Journal of Electronics,2016,25(5):866-872.
[4]HOLLAND J. Genetic algorithms[J]. Scientific American,1992,267:66-72.
[5] FOGEL D. Artificial intelligence through simulated evolution[A]. Proceedings of National Conference on Emerging Trends&Applications in Computer Science[C]. USA:Wiley-IEEE Press,1966. 227-296.
[6]KENNEDY J,EBERHART R. Particle swarm optimization[A]. Proceedings of IEEE International Conference on Neural Netw orks(Vol. 4)[C]. USA:IEEE,1995. 1942-1948.
[7]DORIGO M. Ant Colony Optimization for Vehicle Routing Problem[D]. Ph D thesis,Politecnico di M ilano,M ilan,Italy,1992.
[8]KIRKPATRICK S,GELATT C D,VECCHI M P. Optimization by simmulated annealing[J]. Science,1983,220(4598):671-680.
[9] MIRJALILI S,MIRJALILI S M,HATAMLOU A. Multiverse optimizer:A nature-inspired algorithm for global optimization[J]. Neural Computing and Applications,2016,27(2):495-513.
[10]GONCALVES M S,LOPEZ R H,MIGUEL L F F. Search group algorithm:a new metaheuristic method for the optimization of truss structures[J]. Computers&Structures,2015,153:165-184.
[11] MIRJALILI S. The ant lion optimizer[J]. Advances in Engineering Softw are,2015,83:80-98.
[12]ASKRZAADEH A. A novel metaheuristic method for solving constrained engineering optimization problems:Crow search algorithm[J]. Computers&Structures,2016,169:1-12.
[13]LIU D,LIU C,FU Q,et al. ELM evaluation model of regional groundw ater quality based on the crow search algorithm[J]. Ecological Indicators,2017,81:302-314.
[14]OLIVA D,HINOJOSA S,CUEVAS E,et al. Cross entropy based thresholding for magnetic resonance brain images using crow search algorithm[J]. Expert Systems w ith Applications,2017,79:164-180.