Predecibilidad del tráfico en redes modernas de comunicaciones

  • Marco Aurelio Alzate Monroy Universidad Distrital Francisco José de Caldas
  • José Felix Vega Stavro Universidad Distrital Francisco José de Caldas
Keywords: Predicción óptima, predicción lineal, Tráfico autosimilar, Control de Congestión. (es_ES)

Abstract (es_ES)

En este artículo se presentan los resultados de algunos experimentos que permiten determinar la predecibilidad de una traza real de tráfico con características fractales. Se concluye que, sin necesidad de ajustar las observaciones a un modelo autosemejante particular, es posible utilizar estadísticas muestrales típicas para predecir con sorprendente exactitud la intensidad de tráfico en el futuro inmediato. Por último, se discute cómo podría explotarse esta característica para mejorar los mecanismos actuales de control de congestión en redes modernas de comunicaciones. Tanto el tratamiento del tema como la presentación de los experimentos se hacen de una manera tutorial. El apartado final presenta algunos resultados de investigación sobre protocolos de control de congestión basados en predecibilidad, obtenidos con el simulador de eventos discretos NS-2.

Abstract (en_US)

This paper presents the results of some experiments that allow determining the predictability in a real traffic trace with fractal behavior. The conclusion is that without fitting the trace to any particular self-similar model, is possible to use typical point statistical to predict, with high grade of precision, the traffic intensity in the near future. Finally we discuss about the use of this results for congestion control in modern telecommunications networks. The paper explains, in a tutorial manner, both the theory and the experiments. The final section presents some investigation results about congestion control protocols based on predictability, obtained with the discrete event simulator NS-2.

Downloads

Download data is not yet available.

References

R. Srikant. «Control of Communication Networks». In «Perspectives in Control Engineering», T. Samad, editor. IEEE Press, Piscataway, NJ, 2000.

] Sally Floyd and Van Jacobson. "Random Early Detection Gateways for Congestion Avoidance". IEEE/ACM Trans. On Networking, August 1993

S. Athuraliya, V. H. Li, S. H. Low and Q. Yin. "REM: Active Queue Management", IEEE Network, May 2001.

Wu-chang Feng, Dilip D. Kandlur, Debanjan Saha and Kang G. Shin. "BLUE: A New Class of Active Queue Management Algorithms", U. Michigan CSE-TR-387-99, April 1999.

M. Arlitt and C. Williamson. "Internet Web Servers: workload characterization and performance implications", IEEE/ACM Trans. On networking, Vol.5, N. 5, 1997

M. Crovella and A. Bestavros. "Self-similarity in WWW traffic: evidence and possible causes", IEEE/ACM Trans. On networking, Vol.5, N. 7, 1997

A. Feldmann, A. Gilbert, P. Huang and W. Willinger. "Dynamics of IP Traffic: A study of the role of variability and the impact of control". Proceedings ACM SIGCOMM, 1999.

M. Garret and W. Willinger. "Analysis, modeling and generation of self-similar VBR video traffic". Proceedings ACM SIGCOMM, 1994.

W. Leland, M. Taqqu, W. Willinger and D. Wilson. "On the selfsimilar nature of Ethernet traffic", IEEE/ACM Trans. On networking, Vol.2, N. 1, 1994

A. Feldmann. "Characteristic of TCP connection arrivals". In "Selfsimilar network traffic and performance evaluation", edited by K. Park and W. Willinger, John-Wiley and sons, 2000

Marco Alzate, "Tráfico Autosimilar en Redes de Comunicaciones", Revista INGENIERIA Universidad Distrital, Vol.7 N. 1, 2002.

M. Grossglauser and J. Bolot. «On the Relevance of long-rangedependence in network traffic», Proceedings ACM SIGCOMM, 1996.

T. Tuan and K. Park. "Congestion control for self-similar network traffic". In "Self-similar network traffic and performance evaluation", edited by K. Park and W. Willinger, John-Wiley and sons, 2000

G. He, Y. Gao J. Hou and K. Park. "A case for exploiting selfsimilarity of Internet traffic in TCP Congestion Control", Technical report, Department of Electrical Engineering, The Ohio State University, 2002

Yuan Gao, Guanghui He and Jennifer Hou. "On Exploiting Traffic Predictability in Active Queue Management", IEEE Infocom 2002, New York, June 2002

Yuan Gao, Guanghui He and Jennifer C. Hou. "On Leveraging Traffic Predictability in Active Queue Management", Technical report, Department of Electrical Engineering, The Ohio State University, 2002

T. Gyires, "Using Active Networks for Congestion Control in HighSpeed Networks with Self-Similar Traffic", IEEE Intl. Conf. On Systems, Man, and Cybernetics, 2000, Vol. 1

Lawrence Berkley National Laboratory, The Internet Traffic Archive, http://ita.ee.lbl.gov/html/ contrib/BC.html, April 29, 2000.

G.R.Grimmet and D.R. Stirzaker, "Probability and random processes", Oxford Science Publications, New York, 1992.

G. Gripenberg and I. Norros. "On the Prediction of Fractional Brownian Motion", 1994 <http://citeseer.nj.nec.com/ gripenberg94prediction.html>

Monson H. Hayes. "Statistical Digital Signal Processing and Modeling", John Wiley and Sons, New York, 1996.

Rene K. Boel, Iven M.Y. Mareels and Matthew R. James, "Performance Comparison Of Adaptive And Robust Predictors For Long Range Dependent Signals", 39th International Conference on Decision and Control, Sydney, Australia, December 2000

Fei Xue, "Modeling and Predicting LRD traffic with Farima Processes",

José Félix Vega Stavro, " Acerca de la Aplicación del Efecto de Memoria a Largo Plazo en el Control de Congestión en Redes de Conmutación de Paquetes", Universidad Distrital, Maestría en Teleinformática, por publicar Agosto 2003.

P Abry, D Veitch, Wavelet Analysis of LRD Traffic. IEE Transaction on Informatioin Theory, 1998.

How to Cite
Alzate Monroy, M. A., & Vega Stavro, J. F. (2001). Predecibilidad del tr&aacute;fico en redes modernas de comunicaciones. Ingeniería, 7(2), 21-30. https://doi.org/10.14483/23448393.2814
Published: 2001-11-30
Section
Ciencia, investigación, academia y desarrollo