To overcome the problem of premature convergence frequently appeared in standard particle swarm
optimization(PSO) algorithm, an improved PSO algorithm based on periodic evolution strategy(PSO-PES) is proposed. Thus,
the problem of premature convergence of the PSO algorithm is prevented. The local search ability and global search ability
are enhanced by an adaptive function based on the information of velocities of the particles. Simulations results for several
typical test functions show that PSO-PES possesses more powerful global search capabilities, better convergence rate and
better performance of optimization.