Sub-swarm converging linear particle swarm optimization

In this paper, it is proposed to design constrained particle swarm optimization as sub-swarms. Our aim is to avoid drawbacks of linear particle swarm optimization (LPSO) and to reduce the variance between outputs of converging linear particle swarm optimization (CLPSO) outputs. For this purpose, instead of one and whole swarm started in LPSO and CLPSO equal sized sub-swarms are used and each sub-swarm converge to the solution independently. The performance of this approach is compared with the LPSO and CLPSO on different functions.