Two-phase Particle Swarm Optimization with Scale-free Network Model

Enlightened by the properties of scale-free network model, BA model is extended and introduced into particle swarm optimization, and a novel two-phase particle swarm optimization with scale-free network model (TPSO-SNM) is proposed. At the early stages of the algorithm, particles are randomly distributed in a ring, new particles are continuously added into the structure based on the node degree and the distance between nodes. At the same time, the global optimum in evolution equation is substituted with the average optimal location in neighborhood. Simulation results show that the new method has better ability to find the global optimum solution.