Abstract
Internet traffic prediction plays a fundamental role in network design, management, control, and optimization. The self-similar and non-linear nature of network traffic makes highly accurate prediction difficult. In this paper, a boosting-based framework is proposed for self-similar and non-linear traffic prediction by considering it as a classical regression problem. The framework is based on Ada-Boost on the whole. It adopts Principle Component Analysis as an optional step to take advantage of self-similar nature of traffic while avoiding the disadvantage of self-similarity. Feed-forward neural network is used as the basic regressor to capture the non-linear relationship within the traffic. Experimental results on real network traffic validate the effectiveness of the proposed framework.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bone, R., Assaad, M., Crucianu, M.: Boosting Recurrent Neural Networks for Time Series Prediction. In: Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms (2003)
Brockwell, P., Davis, R.: Time Series: Theory and Methods, 2nd edn. Springer, New York (1991)
Gripenberg, G., Norros, I.: On the Prediction of Fractional Brownian Motion. Journal of Applied Probability, 400–410 (1996)
Hall, J., Mars, P.: The Limitations of Artificial Neural Networks for Traffic Prediction. In: IEE Proceedings on Communications, pp. 114–118 (2000)
Hansegawa, M., Wu, G., Mizuno, M.: Applications of Nonlinear Prediction Methods to the Internet Traffic. In: The 2001 IEEE International Symposium on Circuits and Systems, pp. 169–172 (2001)
Kegl, B.: Robust Regression by Boosting the Median. COLT/Kernel, 258–272 (2003)
Khotanzad, P., Sadek, N.: Multi-Scale High-Speed Network Traffic Prediction Using Combination of Neural Network. IJCNN, 1071–1075 (2003)
Leland, W.E., Taqqu, M.S., Willinger, W., Wilson, D.: On the Self-Similar Nature of Ethernet Traffic. IEEE/ACM Tran. on Networking, 1–15 (1994)
Lopez-Guerrero, M., Gallardo, J.R., Makrakis, D., Orozco-Barbosa, L.: Sensitivity of a Network Traffic Prediction Algorithm. In: PACRIM, pp. 615–618 (2001)
Muller, K.: Predicting Time Series with Support Vector Machines. In: Proceedings of the International Conference on Artificial Neural Network, pp. 999–1004 (1997)
Ostring, S., Sirisena, H.: The Influence of Long-rang Dependence on Traffic Prediction. IEEE ICC (2001), 1000–1005
Sang, B., Li, S.: A Predictability Analysis of Network Traffic. In: Proceeding of INFOCOM, pp. 343–351 (2000)
Schapire, R.E.: The Boosting Approach to Machine Learning: an Overview. In: MSRI Workshop on Nonliear Estimation and Classification (2002)
Shah, K., Bohacek, S., Jonckheere, E.: On the Predictability of Data Network Traffic. In: Proceedings of the 2003 American Control Conference, pp. 1619–1624 (2003)
Shu, Y., Jin, Z., Zhang, L., Wang, L.: Traffic Prediction Using FARIMA Models. IEEE ICC (1999), 891–895 (1999)
Small, M., Yu, D., Harrison, R.G.: Surrogate Test for Pseudoperiodic Time Series Data. Physical Review Letter (2001)
Wang, X., Shan, X.: A Wavelet-based Method to Predict Internet traffic. IEEE International Conference on Communications, Circuits and Systems and West Sino Expositions, 690–694 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tong, H., Li, C., He, J. (2004). A Boosting-Based Framework for Self-Similar and Non-linear Internet Traffic Prediction. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks - ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3174. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28648-6_148
Download citation
DOI: https://doi.org/10.1007/978-3-540-28648-6_148
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22843-1
Online ISBN: 978-3-540-28648-6
eBook Packages: Springer Book Archive