Soft adaptive particle swarm algorithm for large scale optimization

In this paper we investigate a novel optimization strategy to reinforce the basic particle swarm optimization algorithm. The proposed algorithm operates at three evolution levels where an adaptive inertia weight is presented. The most important features presented are both the safety distance introduced to move the particle through its current position, and the proximity index. In order to balance from local to global search and to improve the algorithm performance, we propose an acceleration feature to update the position rule at the next time.