基于复合模型的智能化移动通信话务预测

移动通信话务量作为一种时间序列,具有较强的非线性和随机性,而且易受节假日、旅游等客户行为及天气等其它因素的影响。尤其是话务量长期的发展变化,很难用传统的预测方法进行预测。根据移动通信话务量自身特点,采用复合模型,将话务量分为平稳期趋势分量、平稳期周期分量、节假日话务量,用综合评判的分段一元线性回归及模板匹配算法分别对趋势分量、周期分量和节假日话务进行建模。最后,开发了基于复合模型的智能化预测系统,在广东省某市试运行的结果表明：基于复合模型的预测方法比传统预测方法精度高。

Intellectualized traffic forecasting of mobile telephone based on complex models

As a kind of time sequence,mobile telephone traffic has strong nonlinearity and randomicity,and is easily affected by the festival,travel,weather and other factors.Especially for long development of traffic,it is hardly forecasted by the traditional methods.This paper proposes a new approach based on complex models to forecast mobile telephone traffic.The traffic is divided into three parts: trend heft of common traffic,periodic heft of common traffic and festival traffic,and modeled by the integrated judgments liner regression and template match.The system designed by this method has testing run in a city of south China.The test results show that this method is more effective than the traditional forecasting methods.