Diversity-guided quantum-behaved particle swarm optimization algorithm based on clustering coefficient and characteristic distance

Aiming at the drawback of being easily trapped into the local optima and premature convergence in quantum-behaved particle swarm optimization algorithm, clustering coefficient and characteristic distance is proposed to measure diversity of the population by which quantum-behaved particle swarm optimization algorithm is guided. The population is divergent to increase population diversity and enhance exploration if clustering coefficient is large and characteristic distance is small; the population is convergent to reduce population diversity and enhance exploitation if clustering coefficient is small and characteristic distance is large. The simulation results of testing four benchmark functions show that diversity-guided quantum-behaved particle swarm optimization algorithm based on clustering coefficient and characteristic distance has better optimization performance than other algorithms, the validity and feasibility of the method is verified.