Particle swarm optimization based on adaptive mutation and diminishing inerita weights

Adaptive mutation is introduced into improved particle swarm optimization to increase the performance of particle swarm optimization algorithms. The mutation probability is adjusted according to the variance of the population´s fitness. Nonlinear decreasing strategy is used to adjust the inertia weight and enhance searching ability that can abandon the local optimal solution and find the global one. Simulation results show the algorithm proposed in this paper has better convergence accuracy and higher evolution velocity compared with the conventional particle swarm optimization algorithms. The performance of improved PSO outperformed the traditional PSO.