复杂函数优化中的一种扩展微粒群算法

Extended Particle Swarm Optimization Algorithm for Optimizing Complicated Functions

为了提高标准微粒群算法处理复杂函数时的优化性能,引入了一种扩展形式的新微粒群算法。该算法充分利用了微粒群算法中两个量的优点:群体最优位置利于引导个体快速进化、个体最优位置的中心利于增强群体的多样性。新算法是标准微粒群算法的扩展形式,同时保持了迭代公式的简洁形式。通过复杂函数优化的数值模拟表明,扩展的微粒群算法较标准微粒群算法在寻优能力上有明显的提高。

In ordor to improve the performance of the standard particle swarm optimization algorithm （PSO） optimizing the complicated functions, a new extended particle swarm optimization algorithm （EPSO） was advanced. EPSO took full advantage of two variables in PSO, the global best place （pg） availing guiding individual evolution quickly, and the center of all individual best places （pmean） availing increasing the colonial diversity. The new algorithm was the extension of PSO, at the same time the concise iterative formulation was kept. The simulations of complicated functions optimizatuon show that the EPSO has better ability to find the global optimum solution than the standard particle swarm optimization algorithm.