Clan particle swarm optimization

Particle swarm optimization (PSO) has been used to solve many different types of optimization problems. In spite of this, the original version of PSO is not capable to find reasonable solutions for some types of problems. Therefore, novel approaches to deal with more sophisticated problems are required. Many variations of the basic PSO form have been explored, targeting the velocity update equation. Other approaches attempt to change the communication topology inside the swarm. The purpose of this paper is to propose a topology based on the concept of clans.

First of all, this paper presents a detailed description of its proposal. After that, it shows a graphical convergence analysis for the Rosenbrock benchmark function. In the sequence, a convergence analysis for clan PSO with different parameters is performed. A comparison with star, ring, focal, von Neumann and four clusters topologies is also performed.

The paper's simulation results have shown that the proposal obtained better results than the other topologies for the benchmark functions selected for this paper.

The proposed topology for PSO based on clans provides a novel form for information distribution inside the swarm. In this approach, the topology is determined dynamically during the search process, according to the success rate inside each clan.