The canonical PSO algorithm is a robust stochastic evolutionary computation technique based on the information exchange between the particles. The Potential and Dynamics-based PSO algorithm is inspired by the canonical PSO and it is based on the motion dynamics.
This thesis proposes a novel PSO algorithm, based on the potential field and the motion dynamics model. It is assumed that particles form potential fields and each particle has its own mass. The potential filed and mass are modeled by the particles’ fitness value. By using these fitness based models, the proposed algorithm performs well, in particular, in avoiding the local minima compare to the original PSO.
Although the PDPSO algorithm is designed to have more exploration capability compare to the canonical algorithm. The algorithm shows more exploration power, but the exploitation capability was weakened. To solve the problem, an updated version of PDPSO which have more exploitation capability is proposed while the exploration power is kept in the updated algorithm.
In addition, the relationship between swarm divergence and parameters of PDPSO is discussed.