Dynamic population size based particle swarm optimization

This paper is the first attempt to introduce a new concept of the birth and death of particles via time variant particle population size to improve the adaptation of Particle Swarm Optimization (PSO). Here a dynamic particle population based PSO algorithm (DPPSO) is proposed based on a time-variant particle population function which contains the attenuation item and undulate item. The attenuation item makes the population decrease gradually in order to reduce the computational cost because the particles have the tendency of convergence as time passes. The undulate item consists of periodical phases of ascending and descending,. In the ascending phase, new particles are randomly produced to avoid the particle swarm being trapped in the local optimal point, while in the descending phase, particles with lower ability gradually die so that the optimization efficiency is improved. The test on four benchmark functions shows that the proposed algorithm, effectively reduces the computational cost and greatly improves the global search ability.