Loading...
Combine multi particle swarm in supporting trapping in local optima
Author(s)
Poempool, Lukkana
Kruatrachue, Boontee
Siriboon, Kritawan
Date Issued
August 13, 2018
Type
Conference Paper
Abstract
This paper proposed using multi swarm to lessen trapping in local optima problem of Particle Swarm Optimization (PSO). The use of multiple swarms can increase wider global search at the cost of decrease narrower local search. Hence, the use of multiple swarms alone can't solve the trapping problem. This paper extends the use of multi swarm by merging all the swarm into single group to enhanced local search when needed. This can increase the local search ability of multi swarm and increase the chance of the trapped swarm to move to other nearby local optima. The proposed method is compared to similarly comparable modified PSO and other similarly multi particle swarm without merging using 26 benchmark functions.
Citation
Iceast 2018 4th International Conference on Engineering Applied Sciences and Technology Exploring Innovative Solutions for Smart Society, 2018