Convergence behavior of the fully informed particle swarm optimization algorithm

The fully informed particle swarm optimization algorithm (FIPS) is very sensitive to changes in the population topology. The velocity update rule used in FIPS considers all the neighbors of a particle to update its velocity instead of just the best one as it is done in most variants. It has been argued that this rule induces a random behavior of the particle swarm when a fully connected topology is used. This argument could explain the often observed poor performance of the algorithm under that circumstance. In this paper we study experimentally the convergence behavior of the particles in FIPS when using topologies with different levels of connectivity. We show that the particles tend to search a region whose size decreases as the connectivity of the population topology increases. We therefore put forward the idea that spatial convergence, and not a random behavior, is the cause of the poor performance of FIPS with a fully connected topology. The practical implications of this resul...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Marco Antonio Montes de Oca, Thomas Stützle
• Keywords: Connected Topology, GECCO 2008, Optimization, Particle Swarm, Population Topology