基于SOM的无线通信话务量最优加权组合预测

针对单个预测模型难以准确刻画无线通信话务量的演变规律，并考虑数据自身的多样性，提出了基于自组织映射（Self-Organizing Maps，SOM）神经网络的无线通信话务量最优加权组合预测方法。该方法利用SOM神经网络对话务量数据进行自动聚类，并对聚类后的每类数据，分别确定相应最优加权组合预测的权重，进而获得相应的预测值。实验结果表明，所提出方法不仅能提高话务量预测的精度，还能增强预测系统的稳定性。

Combined prediction with optimal weight for wireless communication traffic based on SOM

In view of the limitation that a single prediction model cannot accurately characterize the evolving law of wire- less communication traffic,and considering its diversity,this paper presents a combined prediction with optimal weight for wireless communication traffic based on Self-Organizing Maps（SOM） neural network.This method firstly makes use of the SOM neural network to realize the automatic clustering of wireless communication traffic.Then for each class,the correspond- ing combined prediction with optimal weight is determined to provide the prediction values.The experimental results show that the proposed method not only can improve the prediction accuracy,but also enhance the prediction stability