Time Series Model Based Traffic Forecasting in QoS

• 作 者: JIANGXiang-rong[1]TANGLu-xian[2]CUIYing-ying[1]
• 机 构: Scientific Decision-making Lab of SDAS, Shandong Institute for Development Strategy of Science &Tech
• 出 处: 中国管理科学与工程学会2013年年会暨第十一届中国管理科学与工程论坛
• 发表日期: 2013年期

　　We propose a procedure to forecast data traffic.It is a modification of method developed for forecasting series with stable seasonal patterns.The new method is motivated by the observations that data traffic shows strong seasonal patterns,which may be evolving over time and remain relative stability.The new method is proved more effective than traditional time series models.The method can be applied to forecast individual observations as well as the end-of-season totals.Empirical study will be conducted with data from China Mobile to evaluate the performance of the proposed method.