Markovian modelling of internet traffic

ABSTRACT

This tutorial discusses the suitability of Markovian models to describe IP network traffic that exhibits peculiar scale invariance properties, such as selfsimilarity and long range dependence. Three Markov Modulated Poisson Processes (MMPP), and their associated parameter fitting procedures, are proposed to describe the packet arrival process by incorporating these peculiar behaviors in their mathematical structure and parameter inference procedures. Since an accurate modeling of certain types of IP traffic requires matching closely not only the packet arrival process but also the packet size distribution, we also discuss a discrete-time batch Markovian arrival process that jointly characterizes the packet arrival process and the packet size distribution. The accuracy of the fitting procedures is evaluated by comparing the long range dependence properties, the probability mass function at each time scale and the queuing behavior corresponding to measured and synthetic traces generated from the inferred models.

References

1. Leland, W., Taqqu, M., Willinger, W., Wilson, D.: On the self-similar nature of Ethernet traffic (extended version). IEEE/ACM Transactions on Networking 2(1), 1-15 (1994)
2. Beran, J., Sherman, R., Taqqu, M., Willinger, W.: Long-range dependence in variable-bit rate video traffic. IEEE Transactions on Communications 43(2/3/4), 1566-1579 (1995)
3. Crovella, M., Bestavros, A.: Self-similarity in World Wide Web traffic: Evidence and possible causes. IEEE/ACMTransactions on Networking 5(6), 835-846 (1997)
4. Paxson, V., Floyd, S.: Wide-area traffic: The failure of Poisson modeling. IEEE/ACM Transactions on Networking 3(3), 226-244 (1995)
5. Ryu, B., Elwalid, A.: The importance of long-range dependence of VBR video traffic in ATM traffic engineering: Myths and realities. ACM Computer Communication Review 26, 3-14 (1996)
6. Grossglauser, M., Bolot, J.C.: On the relevance of long-range dependence in network traffic. IEEE/ACMTransactions on Networking 7(5), 629-640 (1999)
7. Nogueira, A., Valadas, R.: Analyzing the relevant time scales in a network of queues. In: Proceedings of SPIE's International Symposium ITCOM 2001 (August 2001)
8. Heyman, D., Lakshman, T.: What are the implications of long range dependence for VBR video traffic engineering? IEEE/ACM Transactions on Networking 4(3), 301-317 (1996)
9. Neidhardt, A., Wang, J.: The concept of relevant time scales and its application to queuing analysis of self-similar traffic. In: Proceedings of SIGMETRICS 1998/PERFORMANCE 1998, pp. 222-232 (1998)
10. Yoshihara, T., Kasahara, S., Takahashi, Y.: Practical time-scale fitting of self-similar traffic with Markov-modulated Poisson process. Telecommunication Systems 17(1-2), 185-211 (2001)
11. Salvador, P., Valadas, R.: Framework based on markov modulated poisson processes for modeling traffic with long-range dependence. In: van der Mei, R.D., de Bucs, F.H.S. (eds.) Internet Performance and Control of Network Systems II, August 2001. Proceedings SPIE, vol. 4523, pp. 221-232 (2001)
12. Salvador, P., Valadas, R.: A fitting procedure for Markov modulated Poisson processes with an adaptive number of states. In: Proceedings of the 9th IFIP Working Conference on Performance Modelling and Evaluation of ATM & IP Networks (June 2001)
13. Andersen, A., Nielsen, B.: A Markovian approach for modeling packet traffic with longrange dependence. IEEE Journal on Selected Areas in Communications 16(5), 719-732 (1998)
14. Hajek, B., He, L.: On variations of queue response for inputs with the same mean and autocorrelation function. IEEE/ACM Transactions on Networking 6(5), 588-598 (1998)
15. Feldmann, A., Gilbert, A., Willinger, W.: Data networks as cascades: Investigating the multifractal nature of internetWAN traffic. In: Proceedings of SIGCOMM, pp. 42-55 (1998)
16. Feldmann, A., Gilbert, A.C., Huang, P., Willinger, W.: Dynamics of IP traffic: A study of the role of variability and the impact of control. In: SIGCOMM, pp. 301-313 (1999)
17. Riedi, R., Véhel, J.: Multifractal properties of TCP traffic: a numerical study. Technical Report No 3129, INRIA Rocquencourt, France (February 1997), www.dsp.rice.edu/~riedi
18. Salvador, P., Valadas, R., Pacheco, A.: Multiscale fitting procedure using Markov modulated Poisson processes. Telecommunications Systems 23(1-2), 123-148 (2003)
19. Nogueira, A., Salvador, P., Valadas, R., Pacheco, A.: Fitting self-similar traffic by a superposition of mmpps modeling the distribution at multiple time scales. IEICE Transactions on Communications E84-B(8), 2134-2141 (2003)
20. Nogueira, A., Salvador, P., Valadas, R., Pacheco, A.: Modeling self-similar traffic through markov modulated poisson processes over multiple time scales. In: Proceedings of the 6th IEEE International Conference on High Speed Networks and Multimedia Communications (July 2003)
21. Nogueira, A., Salvador, P., Valadas, R., Pacheco, A.: Hierarchical approach based on mmpps for modeling self-similar traffic over multiple time scales. In: Proceedings of the First International Working Conference on Performance Modeling and Evaluation of Heterogeneuous Networks (HET-NETs 2003) (July 2003)
22. Klemm, A., Lindemann, C., Lohmann, M.: Traffic modeling of IP networks using the batch Markovian arrival process. Performance Evaluation 54(2), 149-173 (2003)
23. Gao, J., Rubin, I.: Multifractal analysis and modeling of long-range-dependent traffic. In: Proceedings of International Conference on Communications ICC 1999, June 1999, pp. 382- 386 (1999)
24. Lucantoni, D.M.: New results on the single server queue with a batch Markovian arrival process. Stochastic Models 7(1), 1-46 (1991)
25. Lucantoni, D.M.: The BMAP/G/1 queue: A tutorial. In: Donatiello, L., Nelson, R. (eds.) Models and Techniques for Performance Evaluation of Computer and Communication Systems, pp. 330-358. Springer, Heidelberg (1993)
26. Pacheco, A., Prabhu, N.U.: Markov-additive processes of arrivals. In: Dshalalow, J.H. (ed.) Advances in Queueing: Theory and Methods, ch. 6, pp. 167-194. CRC, Boca Raton (1995)
27. Veitch, D., Abry, P.: A wavelet based joint estimator for the parameters of LRD. IEEE Transactions on Information Theory 45(3) (April 1999)
28. Feldmann, A., Whitt, W.: Fittingmixtures of exponentials to long-tail distributions to analyze network performance models. Performance Evaluation 31(3-4), 245-279 (1997)
29. Osborne, M., Smyth, G.: A modified prony algorithm for fitting sums of exponential functions. SIAM J. Sci. Statist. Comput. 16, 119-138 (1995)
30. Salvador, P., Pacheco, A., Valadas, R.: Modeling IP traffic: Joint characterization of packet arrivals and packet sizes using BMAPs. Computer Networks Journal 44, 335-352 (2004).

Index Terms

• Computing methodologies

  • Modeling and simulation

    • Model development and analysis

      • Modeling methodologies