基于距离扩散的粒子群算法

Particle Swarm Optimization Algorithm Based on Distance

粒子群算法是一种进化计算技术。文章提到的基于距离扩散的粒子群算法(JLSPSO)是在随机粒子群算法的进化过程中,嵌入确定性搜索方法以避免出现停止微粒,并且被每个微粒所共享的社会信息是随距离扩散,以便对微粒产生不同影响。经过这样改进后,JLSPSO既可以加快收敛速度,又可以保持群体多样性。通过对两个多峰的测试函数进行仿真,其结果表明:JLSPSO算法不仅具有较快的收敛速度,而且能够更有效地进行全局搜索。

Particle swarm optimization algorithm is an evolution of computing technology. JLSPSO is presented in this paper. During the evolution of stochastic particle swarm optimization algorithm, the certain search method is imbedded so that the particle don＇t stop, the social information that is shared by every particle proliferate with distance in order to have different effect to every particle. Thus, the convergence is speed up and the population diversity is kept. Through the experiments of two multimodal test functions, the result of simulation proves that the JLSPSO can not only significantly speed up the convergence, but also effectively solve the premature convergence problem.