A new multi-swarms competitive particle swarm optimization algorithm

Abstract

This paper presents the use of fuzzy C means clustering on swarms adaptive division, and proposes a multi-swarms competitive PSO(MSCPSO) algorithm based on fuzzy C means clustering. According to the scale of the swarms to select different optimal strategies, the swarm of large scale (can set the swarm scale threshold to estimate) uses the standard particle swarm algorithm to optimize, and the swarm of small scale randomly searches in the optimal solution neighborhood, increasing the probability of jumping out of the local optimization. Within every clustering, individuals communicate with each other, respectively finding the adaptive value of every clustering swarm by competitive learning and arranging the order according to the adaptive value of different clustering, and then the swarm of small adaptive value integrates with the neighboring swarm of large adaptive value, ensuring the particle swarms to search towards the optimal solution by the competition in the swarms, which increases the diversity of the swarms. This algorithm avoids getting into the local optimization and improves the global search capability. © 2012 Springer-Verlag.