Telecommunication traffic forecasting based on BP neural network trained by PSO
Telecommunication traffic forecasting based on BP <br> neural network which is optimized by particle swarm <br> optimization <br> (PSO) algorithm is presented. PSO is a novel random <br> optimization method based on swarm intelligence, <br> which has more powerful <br> ability of global optimization. Here, we use the <br> telecommunication traffic ranging fi”om 1989 to 2005 <br> in China as the sample to the <br> neural network, which has been trained by PSO, are <br> employed to illustrate the presented model. The <br> experimental results prove that <br> the proposed method optimized by PSO can quicken the <br> learning speed of the network and improve the <br> forecasting precision <br> compared with the conventional BP method and show <br> that the method is not only simple to calculate, but <br> also practical and effective.
BP neural network particle swarm optimization telecommunication traffic forecasting
DONG Xian XU Bing-ji
School of information Engineering, China University of Geosciences, Beijng 100083, China
国内会议
北京
英文
23-25
2011-08-06（万方平台首次上网日期，不代表论文的发表时间）