Loading...
Improving Multi-Swarm by Slightly Mutation Particle and GBEST of Stuck Swarm Along with Randomly Selecting GBEST of Other Swarm
Author(s)
Chengkhuntod, Kanokporn
Kruatrachue, Boontee
Siriboon, Kritawan
Date Issued
August 21, 2018
Type
Conference Paper
Abstract
This paper proposed another approach in handling trapping in local optimum problem of Particle Swarm Optimization (PSO) using multi-swarm. Since each swarm might trap in different local optimum, the trapped swarm restart with slightly mutation (15% of each particle attributes) along with swaying swarm by randomly use of other swarm GBEST position. In the case of all swarm trapping in the same location, the trap GBEST is also slightly mutate in the same way as particle position. This proposed technique is tested on a set of twenty-four benchmark test functions. The experimental results show that the proposed method is better than other comparing methods.
Citation
Icsec 2017 21st International Computer Science and Engineering Conference 2017 Proceeding, 49-52, 2018