Scaling Analysis of Wavelet Quantiles in Network Traffic
The study of network traffic by flow analysis has been the subject of intense and varied research. Wavelet transforms, which form the core of most traffic analysis tools, are known to be robust to linear trends in data measurements, but may suffer from the presence of occasional non-stationarities.
This paper considers how the information associated to quantiles of wavelet coefficients can be exploited to improve the understanding of traffic features. A tool based on these principles is introduced and results of its application to analysis of traffic traces are presented.
Unable to display preview. Download preview PDF.
- 2.Giorgi, G., Narduzzi, C.: A study of measurement-based traffic models for network diagnostics. In: Proc. IEEE Instrum. Meas. Tech. Conf. IMTC 2007, Warsaw, Poland, May 01-03 (2007)Google Scholar
- 3.Abry, P., Taqqu, M.S., Veitch, D.: Wavelets for the analysis, estimation and synthesis of scaling data. In: Park, K., Willinger, W. (eds.) Self Similar Traffic Analysis and Performance Evaluation. Wiley, Chichester (2000)Google Scholar
- 5.Leland, W., Taqqu, M., Willinger, W., Wilson, D.: On the self-similar nature of ethernet traffic (extended version). IEEE/ACM Trans. on Information Theory 2(1), 1–15 (1994)Google Scholar
- 7.National Laboratory for Applied Network Reasearch, U, http://mna.nlanr.net
- 9.Ivchenko, G., Medvedev, Y.: Mathematical Statistics. Mir, Moscow, Russia (1990)Google Scholar
- 10.Giorgi, G., Narduzzi, C.: Uncertainty of quantiles estimates in the measurement of self-similar processes. In: Proc. of inter. Workshop on Advanced Methods for Uncertainty Estimation in Measurement, AMUEM 2008, Sardagna, Trento, Italy, July 21-22 (2008)Google Scholar