Fuzzy logic for dynamic adaptation in PSO with multiple topologies

Particle Swarm Optimization (PSO) combines the ideas of two algorithms, namely global best PSO (or gbest PSO) and local best PSO (or lbest PSO). The social networks employed in this paper by the gbest PSO and lbest PSO algorithms are star, ring, Von Neumann and random topologies. Each topology is used in a core of a quad-core system. The multi-topologies system mixes the best particles of each core (topology). A fuzzy system is implemented to dynamically adapt some parameters of the particle swarm optimization algorithm in each topology. The objective is to find a better optimal solution without getting trapped in local minimums. Benchmark functions were used to show the performance of the proposed system.