A dynamic search space Particle Swarm Optimization algorithm based on population entropy

In the traditional improved Particle Swarm Optimization algorithms, the search spaces of the particles are always fixed. In this paper, based on the standard particle swarm optimization (PSO) algorithm, a dynamic search space particle swarm optimization algorithm (DSPPSO) based on population entropy is proposed. The population entropy is introduced to describe the particles´ location confusion degree, and it will be reduced while all the particles fly to the best objective point. During the evolution progress, the search space is determined by the previous average location and population entropy. DSPPSO reduces the waste of search space in PSO, and it improves the searching speed and accuracy of convergence. In DSPPSO, only a few parameters need to be set, and the algorithm has a simple structure which can be used conveniently. Simulation results validate the feasibility and validity of this improved particle swarm optimization algorithm.