Evaluation of asynchronous multi-swarm particle optimization on several topologies

Particle swarm optimization is a population-based stochastic optimization technique that is easy to implement and has been successfully applied in many areas. However, its performance often deteriorates as the dimensionality of the problem increases. Recently, parallel strategies based on multiple swarms (multi-swarm) have been investigated as an alternative to overcome this problem. In this paper, we evaluate the impact of the topology on multi-swarm systems, considering that swarms are independent, and interact by means of particle migration. We focus on asynchronous communication, that is, only when an improvement occurs on the best particle that the solution migrates among swarms. The goal is to check how different communication strategies affect the parallel execution of the optimization tasks. Several different topologies and communication strategies have been evaluated, including broadcast and gossip on fully connected networks, unidirectional and bidirectional rings, hypercubes, and a dynamic topology.Extensive experimental results were obtained and are reported using several traditional benchmark functions. We evaluated the impact of the topologies in terms of the number of iterations and the communication overhead. With the results, a ranking of the different topologies is presented. The impact of the number of swarms on the optimization process is also evaluated. Copyright (c) 2012 John Wiley & Sons, Ltd.