A hybrid particle swarm optimization for function optimization

A novel hybrid particle swarm optimization algorithm named HDPSO is proposed in this paper in order to produce faster and more accurate convergence compared with the Particle Swarm Optimization (PSO). The HDPSO algorithm combines PSO with Differential Evolution (DE) operators in which an individual of the new generation is not only created by PSO but also by DE operators. Additionally, in order to preserve the diversity of the swarm and reserve good particles Hypothesis Test (HT) is used in HDPSO. The hybrid algorithm was then tested by several widely used functions of different difficulties under noisy and non-noisy conditions. The results were compared with several other popular algorithms and the comparison results demonstrate the effectiveness and robustness of the proposed algorithm compared with the other algorithms.