On Some Non-linear Decreasing Inertia Weight Strategies in Particle Swarm Optimization

Inspired by analyzing principle of PSO, some non-linear strategies for decreasing inertia weight (DIW) are proposed based on the existing linear DIW (LDIW), in this paper. Then a power function is designed to unify them. Four benchmark functions are used to evaluate these strategies on the PSO performance and select the best one. The experimental results show that for most continuous optimization problems, the best one gains an advantage over the linear strategy and others. It has more varieties of the swarm at the early stages so can escape from local minimum more easily, and also can speed up the convergence of particles at the later stages to improve the performance of PSO.