Adaptive Parameter Control for Quantum-behaved Particle Swarm Optimization on Individual Level

Abstract

Particle swarm optimization (PSO) is a population-based evolutionary search technique, which has comparable performance with genetic algorithm. The existing PSOs, however, are not global-convergence-guaranteed algorithms. In the previous work, we proposed quantum-behaved particle swarm optimization (QPSO) algorithm that outperforms traditional PSOs in search ability as well as having less parameter to control. This paper focuses on discussing two adaptive parameter control methods for QPSO. After the ideology of QPSO is formulated, the experiment results of stochastic simulation are given to show how to select the parameter value to guarantee the convergence of the particle in QPSO. Finally, two adaptive parameter control methods are presented and experiment results on benchmark functions testify their efficiency.