Analysis And Research On The Topology Structure Of The Particle Swarm Algorithm

As a newly developed swarm intelligence paradigm, particle swarm algorithm is a very promising optimization tool, with many advantages in high-dimensional problems or engineering design field. The main idea of this algorithm originated from Social Psychology and Artificial Life as a simuluation of socion-cognitive process. Because of its high convergence rate and excellent generalization, particle swarm algorithm has attracted much attention since it was first proposed in 1995.In some literatures, most researchers have focused their effrots on how to promote the convergence rate and avoid the premature convergence problem. Introducing new mechanisms to ensure the diversity of swarm population or escape from local minima may be useful on reliveving premature convergence of the algorithm. As to improving convergence rate, much work focus on tuning strategy patameters, or modifying the original framework with ideas inspired from other meta-heuristics. As most researchers of this field are with pure scientific computing or engineering applications background, they care more about the results other than probe into the real cause, not to mention consider social psychology origins of the algorithm.We attach importcance to both theroetical analysis and experimental demonstration in the research. The paper made a detailed analysis and summary, which focuses on the impact of the topological structure. This paper attempts to make on the basis of some breakthrough or improvement for the topology structure of particle swarm optimization algorithm. More importantly, relevant literatures have been proved that the topological structure had a great influence on performance of the algorithm about particle swarm.This paper focuses on studying a dynamics topology structure based on random particle swarm optimization, which uses of K means clustering algorithm to optimize to improve it.Firstly, this paper intruoduces some theories and basic knowledge on particle swarm optimization algorithm, and research achievements of PSO algorithm are summarized;Secondly, the dynamic topology strategy is presented, on the basis of existing PSO algorithm, and the process of individual adaptive strategy, global update strategy and the neighborhood searching strategy and so on which are in the topology of the algorithm is given in detail. In addition, the theoretical advantages of this algorithm and its convergence are analyzed and demonstrated by using theorem which is discrete time system equation convergence theorem;Finally, in order to solve the optimal solution of a variety of multi-dimensional functions, the algorithm compares with the WMPSO and immune PSO algorithm from experiment, the experiments have proved the feasibility and effectiveness of the algorithm.