Title: A study on the effect of v_max in particle swarm optimisation with high dimension

Authors: Xingjuan Cai, Ying Tan

Addresses: Division of System Simulation and Computer Application, Taiyuan University of Science and Technology, Shanxi, 030024, China. ' Division of System Simulation and Computer Application, Taiyuan University of Science and Technology, Shanxi, 030024, China

Abstract: Velocity threshold v_max is an important parameter of particle swarm optimisation. Different from other parameters, it affects the algorithm performance by restricting the moving size and direction of each particle. However, the current results are all with small dimensions no larger than 30. Because of the scientific development, many optimisation tasks are complex, high dimensional multi-modal functions. Therefore, in this paper, the authors investigate the selection principle of v_max with high dimension on numerical optimisation problems. To make a deep insight, the test suit consists of three different type benchmarks: unimodel, multi-modal functions with a few local optima and multi-modal functions with many local optima. Simulation results show the 10% of the upper bound of the domain may generally obtain the satisfied solution within the allowed iterations.

Keywords: particle swarm optimisation; PSO; velocity threshold; high dimensional benchmarks; numerical optimisation; bio-inspired computation.

DOI: 10.1504/IJBIC.2009.023816

International Journal of Bio-Inspired Computation, 2009 Vol.1 No.3, pp.210 - 216

Published online: 12 Mar 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article