Neighborhood topologies in fully informed and best-of-neighborhood particle swarms

被引:234
作者
Kennedy, James [1 ]
Mendes, Rui
机构
[1] US Bur Labor Stat, Washington, DC 20212 USA
[2] Univ Minho, Dept Informat, P-4704553 Braga, Portugal
来源
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS | 2006年 / 36卷 / 04期
关键词
algorithms; optimization; particle swarm;
D O I
10.1109/TSMCC.2006.875410
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this study, we vary the way an individual in the particle swarm interacts with its neighbors. The performance of an indiviual depends on population topology as well as algorithm version. It appears that a fully informed particle swarm is more susceptible to alterations in the topology, but with a good topology, it can outperform the canonical version.
引用
收藏
页码:515 / 519
页数:5
相关论文
共 9 条