Self-adaptive particle swarm optimization algorithm for global optimization

Particle swarm optimization (PSO) algorithm is a simple yet powerful population-based stochastic search technique for solving optimization problems in the continuous search domain. However, the canonical PSO is more likely to get stuck at a local optimum and thereby leads to premature convergence when solving practical problems. To overcome such inconvenience, a novel PSO algorithm is reported which entitled self-adaptive particle swarm optimization (SaPSO) in this paper. Sufficiently analyzing the particles state and dynamically allocating different particles with moderate properties without increasing the population size, the core idea of the schema, maintain the diversity of the population to cope with the deception multiple local optima and reduce the computational complexity. Self-adaptive adjust the inertia weight of the velocity update rule based on the empirical values and negative feedback technique which relieve the burden of specifying the parameters values. The new method is tested on a set of well-known benchmark test functions. The simulation results suggest that it outperforms to other state-of-the-art techniques referred to in this paper in terms of the quality of the final solutions.