Binary particle swarm optimization with multiple evolutionary strategies  

作　　者：ZHAO Jing HAN ChongZhao WEI Bin 

机构地区：[1]Ministry of Education Key Lab For Intelligent Networks and Network Security, State Key LaboratoTny for Manufacturing Systems Engineering, Institute of Integrated Automation, School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China [2]Institute of System Engineering, School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China

出　　处：《Science China(Information Sciences)》2012年第11期2485-2494,共10页中国科学（信息科学）（英文版）

基　　金：supported by the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (Grant No. 60921003);National Basic Research Program of China (Grant No. 2007CB311006);National Natural Science Foundation of China (Grant No. 61074176)

摘　　要：This paper introduces a novel variation of binary particle swarm optimization （BPSO） algorithm and a further extension to improve its performance. Firstly, mimicking the behaviors of some creatures group, multiple evolutionary strategies BPSO （MBPSO） is introduced which takes different evolutionary strategies for various particles according to their performances. Then, on the basis of MBPSO, a new strategy is discussed to improve the performance of the MBPSO （M2BPSO） which adopts the concept of the mutation operator aiming to overcome the premature convergence and slow convergent speed during the later stages of the optimization. The proposed two Mgorithms are tested on seven benchmark functions and their results are compared with those obtained by other methods. Experimental results show that our methods outperform the other algorithms.This paper introduces a novel variation of binary particle swarm optimization （BPSO） algorithm and a further extension to improve its performance. Firstly, mimicking the behaviors of some creatures group, multiple evolutionary strategies BPSO （MBPSO） is introduced which takes different evolutionary strategies for various particles according to their performances. Then, on the basis of MBPSO, a new strategy is discussed to improve the performance of the MBPSO （M2BPSO） which adopts the concept of the mutation operator aiming to overcome the premature convergence and slow convergent speed during the later stages of the optimization. The proposed two Mgorithms are tested on seven benchmark functions and their results are compared with those obtained by other methods. Experimental results show that our methods outperform the other algorithms.

关 键 词：binary particle swarm optimizer evolutionary strategies swarm intelligence 

分 类 号：O224[理学—运筹学与控制论] TP301.6[理学—数学]