Performance Analysis of Internet Traffic Forecasting Model

인터넷 트래픽 예측 모형 성능 분석 연구

  • Received : 20110100
  • Accepted : 20110200
  • Published : 2011.04.30


In this paper, we compare performance of three models. The Holt-Winters, FARIMA and ARGARCH models, are used in predicting internet traffic data for analysis of traffic characteristics. We first introduce the time series models and apply them to real traffic data to forecast. Finally, we examine which model is the most suitable for explaining the long memory, the characteristics of the traffic material, and compare the respective prediction performance of the models.


Traffic;long memory;Holt-Winters;FARIMA;AR-GARCH


  1. Basu, A., Mukherjee, A. and Klivansky, S. (1996). Time series models for internet traffic, InProceedings IEEE Infocom 96, Fifteenth Annual Conference of the IEEE Computer Societies, 4, 24–28.
  2. Dingde, J. and Guangmin, H. (2009). GARCH model-based large-scale IP traffic matrix estimation, Communications Letters, IEEE, 13, 52–54.
  3. Engle, R. F. (1982). Autoregressive conditional heteroskedasticity with estimates of the variance of U. K. inflation, Econometrica, 50, 987–1008.
  4. Kim, S. (2007). Time series models for performance evaluation of network traffic forecasting, The Korea, Jiurnal of Applied Statistics, 20, 219–227.
  5. Liu, J., Shu, Y., Zhang, L. and Xue, F. (1999). Traffic modeling based on FARIMA models, IEEE Canadian Conference on Electrical and Computer Engineering, 162–167.
  6. Shu, Y., Yu, M., Yang, O., Liu, J. and Feng, H. (2005). Wireless traffic modeling and prediction using seasonal ARIMA models, IEICE-Transactions on Comminications, 10, 3992–3999.
  7. Tikunov, D. and Nishimura, T. (2007). Traffic prediction for mobile network using Holt-Winter’s exponential smoothing, Telecommunications and Computer Networks, 15th International Conference, 1–5.
  8. Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages, Management Science, 6, 324–342.


Supported by : 한국연구재단