A comparative study is performed to reveal the convergence characteristics and the robustness of three local neighborhoods in the particle swarm optimization algorithm (PSO): ring, Von Neumann and singly-linked ring. In the PSO algorithm, a neighborhood enables different communication paths among its members, and therefore, the way the swarm searches the landscape. Since the neighborhood structure changes the flying pattern of the swarm, convergence and diversity differ from structure to structure. A set of controled experiments is developed to observe the transmission behavior (convergency) of every structure. The comparison results illustrate similarities and differences in the three topologies. A brief discussion is provided to further reveal the reasons which may account for the difference of the three neighborhoods. © Springer-Verlag Berlin Heidelberg 2013.
CITATION STYLE
Muñoz Zavala, A. E. (2013). A comparison study of PSO neighborhoods. Advances in Intelligent Systems and Computing, 175 ADVANCES, 251–265. https://doi.org/10.1007/978-3-642-31519-0_16
Mendeley helps you to discover research relevant for your work.