Self-Active Inertia Weight Strategy in Particle Swarm Optimization Algorithm

Inertia weight is one of the most important parameters of particle swarm optimization (PSO) algorithm. We introduce a self-active inertia weight strategy, in which the inertia weight is updated according to the convergence rate of the search process related to the optimized function. Four different functions were used to evaluate the effects of these strategies on the PSO performance. The experimental results show that self-active strategy is significantly faster convergence than LPSO