独立局部搜索与多区域渐近收敛的新型PSO算法
|
摘要
针对标准粒子群算法(PSO)全局与局部搜索能力相互制约的缺点,提出一种带有独立局部搜索机制、多区域搜索策略和渐近收敛能力的新型PSO算法(ILS-PSO).设计新的简化参数的全局搜索公式、非劣解邻域局部搜索公式和当前最优解邻域深度搜索公式,使算法具备独立的全局与局部搜索能力.通过参数ξ和λ协调算法的全局与局部搜索能力,以实现算法的多区域搜索和渐近式收敛.典型函数及其偏移函数的对比测试结果表明,ILSPSO算法具有良好的优化性能,其综合性能优于其他对比算法.
Global and local search abilities restrict each other in the standard particle swarm optimization(PSO) algorithm.A new improved PSO algorithm with the independent local search(PSO-ILS) mechanism, multi-area search strategy and asymptotic convergence ability is proposed. Firstly, a new global search formula with simplified parameters, a local one for neighborhood of non-inferior solutions and a depth one for neighborhood of current optimal solution, are designed.Therefore, the proposed algorithm possesses independent both global and local search abilities. Then, for realizing the multi-area search strategy and asymptotic convergence abilities, the parameters ξ and λ are defined to coordinate the abilities of both global and local searches. The comparative experimental result of typical and their shifted functions demonstrates that the PSO-ILS algorithm is of better performance than other algorithms.
Global and local search abilities restrict each other in the standard particle swarm optimization(PSO) algorithm.A new improved PSO algorithm with the independent local search(PSO-ILS) mechanism, multi-area search strategy and asymptotic convergence ability is proposed. Firstly, a new global search formula with simplified parameters, a local one for neighborhood of non-inferior solutions and a depth one for neighborhood of current optimal solution, are designed.Therefore, the proposed algorithm possesses independent both global and local search abilities. Then, for realizing the multi-area search strategy and asymptotic convergence abilities, the parameters ξ and λ are defined to coordinate the abilities of both global and local searches. The comparative experimental result of typical and their shifted functions demonstrates that the PSO-ILS algorithm is of better performance than other algorithms.
引文
[1]Chan C L,Chen C L.A cautious PSO with conditional random[J].Expert Systems with Applications an Int J,2015,42(8):4120-4125.
[2]Agrawal S,Silakari S.Flotcher-reeves based particle swarm optimization for multimodal[J].Soft Computing,2014,18(11):2227-2243.
[3]申元霞,陈健,曾传华.层次学习骨干粒子群优化算法[J].控制与决策,2016,31(12):2183-2188.(Shen Y X,Chen J,Zeng C H.Hierarchical learning bare-bones particle swarm optimization algorithm[J].Control and Decision,2016,31(12):2183-2188.)
[4]Qin Q,Cheng S,Zhang Q,et al.Particle swarm optimization with interswarm interactive learning strategy[J].IEEE Trans on Cybernetics,2016,46(10):2238-2251.
[5]Jordehi A R.Enhanced leader PSO(ELPSO):A new PSO variant for solving global optimisation problems[J].Applied Soft Computing,2015,26(26):401-417.
[6]Sun C,Jin Y,Cheng R,et al.Surrogate-assisted cooperative swarm optimization of high-dimensional expensive problems[J].IEEE Trans on Evolutionary Computation,2017,21(4):644-660.
[7]夏学文,王博建,金畅,等.一种自适应多种群的PSO算法[J].系统仿真学报,2016,28(12):2887-2895.(Xia X W,Wang B J,Jing C,et al.Self-adaptive multi-swarm particle swarm optimization[J].J of System Simulation,2016,28(12):2887-2895.)
[8]Shabbir F,Omenzetter P.Particle swarm optimization with sequential niche technique for dynamic finite element model updating[J].Computer-Aided Civil and Infrastructure Engineering,2015,30(5):359-375.
[9]吴涛,严余松,陈曦.基于随机评价机制的交互式双子群QPSO算法[J].控制与决策,2015,30(3):526-530.(Wu T,Yan Y S,Chen X.Improved dual-group interaction QPSO algorithm based on random evaluation[J].Control and Decision,2015,30(3):526-530.)
[10]Garg H.A hybrid PSO-GA algorithm for constrained optimization problems[J].Applied Mathematics&Computation,2016,274(11):292-305.
[11]Wang S,Zhang Y,Dong Z,et al.Feed-forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection[J].Int J of Imaging Systems&Technology,2015,25(2):153-164.
[12]Kaveh A,Mahdavi V R.A hybrid CBO-PSO algorithm for optimal design of truss structures with dynamic constraints[J].Applied Soft Computing,2015,34(5):260-273.
[13]Mistry K,Zhang L,Neoh S C,et al.A micro-GA embedded PSO feature selection approach to intelligent facial emotion recognition[J].IEEE Trans on Cybernetics,2016,99:1-14.
[14]Zhao F,Liu Y,Zhang C,et al.A self-adaptive harmony PSO search algorithm and its performance analysis[J].Expert Systems with Applications,2015,42(21):7436-7455.
[15]Cesare N D,Chamoret D,Domaszewski M.A new hybrid PSO algorithm based on a stochastic Markov chain model[J].Advances in Engineering Software,2015,90(C):127-137.
[16]Li C,Nguyen T T,Yang M,et al.An adaptive multipopulation framework for locating and tracking multiple optima[J].IEEE Trans on Evolutionary Computation,2016,20(4):590-605.
[17]Sheng W,Chen S,Sheng M,et al.Adaptive multisubpopulation competition and multiniche crowding-based memetic algorithm for automatic data clustering[J].IEEE Trans on Evolutionary Computation,2016,20(6):838-858.
[18]田一明,陈雪波,孙秋柏.行为安全管理系统中员工不安全行为涌现性抑制的研究[J].安全与环境学报,2016,16(2):174-178.(Tian Y M,Chen X B,Sun Q B.Study on the inhibitive tendency of the unsafe behavior inclination of the em-ployees in the BBS management and con-trol system[J].J of Safety and Environment,2016,16(2):174-178.)
[19]Bai J,Liu H.Multi-objective artificial bee algorithm based on decomposition by PBI method[J].Applied Intelligence,2016,45(4):1-16.
[2]Agrawal S,Silakari S.Flotcher-reeves based particle swarm optimization for multimodal[J].Soft Computing,2014,18(11):2227-2243.
[3]申元霞,陈健,曾传华.层次学习骨干粒子群优化算法[J].控制与决策,2016,31(12):2183-2188.(Shen Y X,Chen J,Zeng C H.Hierarchical learning bare-bones particle swarm optimization algorithm[J].Control and Decision,2016,31(12):2183-2188.)
[4]Qin Q,Cheng S,Zhang Q,et al.Particle swarm optimization with interswarm interactive learning strategy[J].IEEE Trans on Cybernetics,2016,46(10):2238-2251.
[5]Jordehi A R.Enhanced leader PSO(ELPSO):A new PSO variant for solving global optimisation problems[J].Applied Soft Computing,2015,26(26):401-417.
[6]Sun C,Jin Y,Cheng R,et al.Surrogate-assisted cooperative swarm optimization of high-dimensional expensive problems[J].IEEE Trans on Evolutionary Computation,2017,21(4):644-660.
[7]夏学文,王博建,金畅,等.一种自适应多种群的PSO算法[J].系统仿真学报,2016,28(12):2887-2895.(Xia X W,Wang B J,Jing C,et al.Self-adaptive multi-swarm particle swarm optimization[J].J of System Simulation,2016,28(12):2887-2895.)
[8]Shabbir F,Omenzetter P.Particle swarm optimization with sequential niche technique for dynamic finite element model updating[J].Computer-Aided Civil and Infrastructure Engineering,2015,30(5):359-375.
[9]吴涛,严余松,陈曦.基于随机评价机制的交互式双子群QPSO算法[J].控制与决策,2015,30(3):526-530.(Wu T,Yan Y S,Chen X.Improved dual-group interaction QPSO algorithm based on random evaluation[J].Control and Decision,2015,30(3):526-530.)
[10]Garg H.A hybrid PSO-GA algorithm for constrained optimization problems[J].Applied Mathematics&Computation,2016,274(11):292-305.
[11]Wang S,Zhang Y,Dong Z,et al.Feed-forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection[J].Int J of Imaging Systems&Technology,2015,25(2):153-164.
[12]Kaveh A,Mahdavi V R.A hybrid CBO-PSO algorithm for optimal design of truss structures with dynamic constraints[J].Applied Soft Computing,2015,34(5):260-273.
[13]Mistry K,Zhang L,Neoh S C,et al.A micro-GA embedded PSO feature selection approach to intelligent facial emotion recognition[J].IEEE Trans on Cybernetics,2016,99:1-14.
[14]Zhao F,Liu Y,Zhang C,et al.A self-adaptive harmony PSO search algorithm and its performance analysis[J].Expert Systems with Applications,2015,42(21):7436-7455.
[15]Cesare N D,Chamoret D,Domaszewski M.A new hybrid PSO algorithm based on a stochastic Markov chain model[J].Advances in Engineering Software,2015,90(C):127-137.
[16]Li C,Nguyen T T,Yang M,et al.An adaptive multipopulation framework for locating and tracking multiple optima[J].IEEE Trans on Evolutionary Computation,2016,20(4):590-605.
[17]Sheng W,Chen S,Sheng M,et al.Adaptive multisubpopulation competition and multiniche crowding-based memetic algorithm for automatic data clustering[J].IEEE Trans on Evolutionary Computation,2016,20(6):838-858.
[18]田一明,陈雪波,孙秋柏.行为安全管理系统中员工不安全行为涌现性抑制的研究[J].安全与环境学报,2016,16(2):174-178.(Tian Y M,Chen X B,Sun Q B.Study on the inhibitive tendency of the unsafe behavior inclination of the em-ployees in the BBS management and con-trol system[J].J of Safety and Environment,2016,16(2):174-178.)
[19]Bai J,Liu H.Multi-objective artificial bee algorithm based on decomposition by PBI method[J].Applied Intelligence,2016,45(4):1-16.