Adaptive Multi-layer Particle Swarm Optimization with Neighborhood Search  

作　　者：TRAN Dang Cong WU Zhijian 

机构地区：[1]State Key Lab of Software Engineering,School of Computer,Wuhan University,Wuhan 430072,China [2]Vietnam Academy of Science and Technology,Hanoi,Vietnam

出　　处：《Chinese Journal of Electronics》2016年第6期1079-1088,共10页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61070008,No.61364025);the Foundation of State Key Laboratory of Software Engineering(No.SKLSE2014-10-04);Science and Technology Program of Nantong(No.BK2014057);Science and Technology Program of Hebei(No.12210319)

摘　　要：Particle swarm optimization(PSO) has shown a good performance on solving global optimization problems. Traditional PSO has two main drawbacks of premature convergence and low convergence speed, especially on complex problems. This paper presents a new approach called Adaptive multi-layer particle swarm optimization with neighborhood search(AMPSONS), where the traditional PSO is improved by employing an adaptive multi-layer search and neighborhood search strategy to achieve a trade-off between exploitation and exploration abilities. In order to evaluate the performance of the proposed AMPSONS algorithm, the performance of AMPSONS is compared with five other PSO family algorithms,namely, CLPSO, DNLPSO, DNSPSO, global MLPSO and local MLPSO on a set of benchmark functions. The comparison results show that AMPSONS has a promising performance on ma jority of the test functions.Particle swarm optimization（PSO） has shown a good performance on solving global optimization problems. Traditional PSO has two main drawbacks of premature convergence and low convergence speed, especially on complex problems. This paper presents a new approach called Adaptive multi-layer particle swarm optimization with neighborhood search（AMPSONS）, where the traditional PSO is improved by employing an adaptive multi-layer search and neighborhood search strategy to achieve a trade-off between exploitation and exploration abilities. In order to evaluate the performance of the proposed AMPSONS algorithm, the performance of AMPSONS is compared with five other PSO family algorithms,namely, CLPSO, DNLPSO, DNSPSO, global MLPSO and local MLPSO on a set of benchmark functions. The comparison results show that AMPSONS has a promising performance on ma jority of the test functions.

关 键 词：Particle swarm optimization Global optimization Neighborhood search Adaptive multi-layer search 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]