Multiple Choice Strategy For PSO Algorithm – Performance Analysis On Shifted Test Functions
Michal Pluháček, Roman Šenkeřík, Ivan Zelinka, Donald David Davendra · 2013
A new promising strategy for the PSO (Particle swarm optimization) algorithm is proposed and described in this paper. This new strategy presents alternative way of assigning new velocity to each individual in particle swarm (population). This new multiple choice particle swarm optimization (MC-PSO) algorithm is tested on two different shifted test functions to show the performance on problems that are not constant in time. The promising results of this alternative strategy are compared with the not modified PSO version.