Simplified particle swarm optimization algorithm based on particles classification

When basic particle swarm optimization algorithm (PSO) is used to resolve some complex problems, its global optimal model usually falls into local optimal value and its local model has slowest convergence velocity in the later stage of evolution. So, a simplified particle swarm optimization algorithm is proposed. Firstly, all particles in whole swarm are divided into three categories, denoted as the better particles, the ordinary particles and the worse particles according to their fitness. After the velocity equation of PSO is analyzed, the velocity part of PSO´s iteration equations is removed rationally. Then, these three types of particles evolve dynamically according to three corresponding kinds of simplified algorithm models. Then, PSO, other two improved PSOs with good optimization performance at present and simplified PSO proposed by this paper all are used to resolve the optimization problems of four widely used test functions, and the results show that simplified PSO has better optimization performance than others.