A Dynamic Multi-Swarm Particle Swarm Optimization With Global Detection Mechanism

To overcome the shortcomings of standard particle swarm optimization algorithm (PSO), such as premature convergence and low precision, a dynamic multi-swarm PSO with global detection mechanism (DMS-PSO-GD) is proposed. In DMS-PSO-GD, whole population divided into two kinds sub-swarms: several same-sized sub-swarms sub-swarm. The achieve information interaction sharing among themselves through randomly regrouping strategy. sub-swarm evolves independently learns from optimal individuals dominant characteristics. During evolution process population, variances average fitness values are used for measuring distribution particles, by which one individual can be detected easily. comparison results DMS-PSO-GD other 5 well-known algorithms suggest that it demonstrates superior performance solving different types functions.