Migration Pool Technique for Parallel Particle Swarm Optimization Algorithm


ASLAN S. , Soysaldi M.

4th International Conference on Computer Science and Engineering (UBMK), Samsun, Turkey, 11 - 15 September 2019, pp.414-417 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/ubmk.2019.8907147
  • City: Samsun
  • Country: Turkey
  • Page Numbers: pp.414-417

Abstract

Particle swarm optimization algorithm (PSO) is used to solve optimization problems. In this algorithm, communication between particles is an important factor that enables us to find an optimum or near optimum solution. In parallel version of this algorithm, communication is ensured by the migration of particles between sub-population. In this study, we present a new migration pool technique when selecting the particle to migrate. According to the number of processors, we set three migration pool size. Then, we apply the proposed migration pool technique on 9 different test functions. The results show what the migration pool size should be for each function to reach the optimal solution.