Particle Swarm Optimization with Grey Neighborhood Operator

With the help of grey relational analysis, this study attempts to propose a grey neighborhood operator to determine the local best position for particle swarm optimization algorithm. Such a grey-based local best particle swarm optimization is denoted as Glbest particle swarm optimization in this study. The grey neighborhood operator is proposed to not only avoid premature convergence but also improve the search performance. In addition, Glbest particle swarm optimization is applied to solve the optimization problems of six benchmark functions for illustration. Simulation results show that the proposed Glbest particle swarm optimization could outperform several particle swarm optimization variants on most of the test functions.