Particle Swarm is a relatively novel approach for global stochastic optimization. In this paper some variations over the basic algorithm are proposed, with the aim of a more efficient search over the solution space obtained with a negligible overhead in both complexity and speed. The presented algorithms are then applied to a mathematical test function and to a microwave microstrip filter to show their superior capabilities with respect to the conventional version.
|Number of pages
|Journal of Intelligent and Fuzzy Systems
|Published - 2008
- Genetic algorithm
- Particle swarm