zbMATH — the first resource for mathematics

Modeling teletraffic arrivals by a Poisson cluster process. (English) Zbl 1119.60075
The infinite source Poisson model for modeling teletraffic arrivals is considered. This model is also referred to as Poisson cluster process or branching Poisson process. We recall that the Poisson cluster process is obtained by marking the Poisson point \(\Gamma_{j}\) by the pair (\(K_{j}, (X_{ji}, i \geq 1\))). The covariance structure of the increment process of \(N\) is derived. The asymptotic behaviour of the Poisson cluster process is studied. The conditions on the distribution of \(K_{j}\) and \(X_{ji}\) under which the random sums \(\sum_{i=1}^{K_{j}} X_{ji}\) have a regularly varying tail are formulated. Using the form of the distribution of the interarrival times of the process \(N\) under the Palm measure, the authors also conduct an exploratory statistical analysis of internet packet arrivals to a server.
In contrast to other modeling techniques, such as the commonly used ON/OFF or the infinite source Poisson models, the used Poisson cluster process model is more realistic and has significantly higher precision and lower computation overhead.

60K25 Queueing theory (aspects of probability theory)
68M20 Performance evaluation, queueing, and scheduling in the context of computer systems
90B20 Traffic problems in operations research
90B15 Stochastic network models in operations research
Full Text: DOI
[1] G. ALSMEYER, On generalized renewal measures and certain first passage times, Ann. Probab. 20 (1992) 1229–1247. · Zbl 0759.60088 · doi:10.1214/aop/1176989690
[2] F. BACCELLI AND P. BRÉMAUD, Elements of Queueing Theory. Palm Martingale Calculus and Stochastic Recurrences, 2nd edition (Springer, New York, 2003). · Zbl 1021.60001
[3] J.M. Bardet, G. Lang, E. Moulines, and P. Soulier, Wavelet estimator of long-range dependent processes. Stat. Inference Stoch. Process. 3 (2000) 85–99. 19th ”Rencontres Franco-Belges de Statisticiens” (Marseille, 1998). · Zbl 1054.62579
[4] M.S. BARTLETT, The spectral analysis of point processes es. J. Roy. Statist. Soc., Series B 25 (1963) 264–296. · Zbl 0124.08504
[5] P. BILLINGSLEY, Convergence of Probability Measures. (Wiley, New York, 1968). · Zbl 0172.21201
[6] N.H. BINGHAM, C.M. GOLDIE, AND J.L. TEUGELS, Regular Variation (Cambridge University Press, Cambridge (UK), 1987).
[7] P.J. BROCKWELL AND R.A. DAVIS, Time Series: Theory and Methods, (2nd edition) (Springer, New York, 1991).
[8] D.B.H. CLINE AND T. HSING, Large deviation probabilities for sums of random variables with heavy or subexponential tails. Technical Report, Texas A& M University (1998).
[9] M. CROVELLA AND A. BESTAVROS, Self-similarity in world wide web traffic: evidence and possible causes. In Proceedings of the 1996 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (1996) vol. 24, pp. 160–169.
[10] M. CROVELLA, A. BESTAVROS, AND M.S. TAQQU, Heavy-tailed probability distributions in the world wide web. A Practical Guide to Heavy Tails: Statistical Techniques for Analysing Heavy Tailed Distributions, R., Adler, R. Feldman, and M.S., Taqqu (eds.) (Birkhäuser, Boston, 1998) pp. 3–26. · Zbl 0945.62130
[11] D. DALEY, Asymptotic properties of stationary point processes es with generalized clusters. Z. Wahrscheinlichkeitstheorie verw. Geb. 21 (1972) 65–76. · Zbl 0213.19803 · doi:10.1007/BF00535107
[12] D. DALEY AND R. VESILO, Long range dependence of point processes, with queueing examples. Stochastic Processes and Their Applications 70 (1997) 265–282. · Zbl 0911.60077 · doi:10.1016/S0304-4149(97)00045-8
[13] D. DALEY AND D. VERE-JONES, An Introduction to the Theory of Point Processes (Springer, New York, 1988). · Zbl 0657.60069
[14] P. EMBRECHTS, C. KLÜppelberg, and T. Mikosch, Modelling Extremal Events for Insurance and Finance (Springer, Berlin, 1997). · Zbl 0873.62116
[15] P. EMBRECHTS AND E. OMEY, On subordinated distribution s and random record processes. Proc. Camb. Phil. Soc. 93 (1983) 339–353. · Zbl 0513.60029 · doi:10.1017/S0305004100060643
[16] G. Faÿ, F. Roueff, and P. Soulier, Estimation of the memory parameter of the infinite source Poisson process. Preprint (2005). Available at http://arxiv.org/abs/math/0509371 . · Zbl 1127.62070
[17] A. GUT, Stopped Random Walks (Springer, New York, 1988). · Zbl 0634.60061
[18] N.R. Hansen, Markov Controlled Excursions, Local Alignment and Structure. PhD thesis, Institute of Mathematics, University of Copenhagen (2003) .
[19] D. HEATH, S. RESNICK, AND G. SAMORODNITSKY, Heavy tails and long range dependence in ON/OFF processes and associated fluid models. Math. Oper. Res. 23 (1998) 145–165. · Zbl 0981.60092
[20] N. Hohn and D. Veitch, Inverting sampled traffic. ACM/SIGCOMM Internet Measurement Conference, (Miami, USA, 2003) pp. 222–233.
[21] N. Hohn, D. Veitch, and P. Abry, Cluster processes: a natural language for network traffic. IEEE Trans. Signal Process. 51 (2003), 2229–2244.
[22] O. Kallenberg, Foundations of Modern Probability, 2nd edition (Springer, New York, 2001). · Zbl 0892.60001
[23] W.E. LELAND, M.S. TAQQU, W. WILLINGER, AND D.V. WILSON, On the self-similar nature of Ethernet traffic. ACM/SIGCOMM Computer Communications Review (1993) 183–193.
[24] P.A.W. LEWIS, A branching Poisson process model for the analysis of computer failure patterns. J. Roy. Statist. Soc., Series B 26 (1964) 398–456. · Zbl 0132.39204
[25] T. MIKOSCH AND G. SAMORODNITSKY, The supremum of a negative drift random walk with dependent heavy-tailed steps. Ann. Appl. Probab. 10 (2000) 1025–1064. · Zbl 1083.60506 · doi:10.1214/aoap/1019487517
[26] T. MIKOSCH AND G. SAMORODNITSKY, Scaling limits for cumulative input processes. Math. Oper. Research (2006) To appear. · Zbl 1279.90033
[27] T. MIKOSCH, S. RESNICK, H. ROOTZÉN, AND A. STEGEMAN, Is network traffic approximated by stable Lévy motion or fractional Brownian motion? Ann. Appl. Probab. 12 (2002) 23–68. · Zbl 1021.60076
[28] E. Moulines, F. Roueff, and M. Taqqu, A wavelet Whittle estimator of the memory parameter of a non-stationary Gaussian time series. Preprint (2005). Available at http://arxiv.org/abs/math.ST/0601070 . · Zbl 1142.62062
[29] A.V. NAGAEV, Limit theorems for large deviations where Cramér’s conditions are violated (in Russian). Izv. Akad. Nauk UzSSR, Ser. Fiz.–Mat. Nauk 6 (1969a) 17–22.
[30] A.V. NAGAEV, Integral limit theorems for large deviations when Cramér’s condition is not fulfilled I,II. Theory Probab. Appl. 14 (1969b) 51–64, 193–208. · Zbl 0196.21002
[31] S.V. NAGAEV, Large deviations of sums of independent random variables. Ann. Probab. 7 (1979) 745–789. · Zbl 0418.60033 · doi:10.1214/aop/1176994938
[32] V.V. PETROV, Limit Theorems of Probability Theory (Oxford University Press, Oxford, 1995). · Zbl 0826.60001
[33] S.I. RESNICK, Point processes, regular variation and weak convergence . Adv. Appl. Probab. 18 (1986) 66–138. · Zbl 0597.60048 · doi:10.2307/1427239
[34] S.I. RESNICK, Extreme Values, Regular Variation, and Point Processes. (Sprin-ger, New York, 1987). · Zbl 0633.60001
[35] G. SAMORODNITSKY AND M.S. TAQQU, Stable Non-Gaussian Random Processes. Stochastic Models with Infinite Variance (Chapman & Hall, New York, 1994). · Zbl 0925.60027
[36] A.J. STAM, Regular variation of the tail of a subordinated probability distribution . Adv. Appl. Probab. 5 (1973) 287–307. · Zbl 0264.60029 · doi:10.2307/1426038
[37] M. WESTCOTT, On existence and mixing results for cluster point processes. J. Royal Stat. Soc. Series B 33 (1971) 290–300. · Zbl 0226.60123
[38] W. WILLINGER, M.S. TAQQU, R. SHERMAN, AND D. WILSON, Self-similarity through high variability: statistical analysis of ethernet LAN traffic at the source level. Proceedings of the ACM/SIGCOMM’95, Cambridge, MA. Computer Communications Review 25 (1995) 100–113.
[39] G.W. Wornell and A.V. Oppenheim, Estimation of fractal signals from noisy measurements using wavelets. IEEE Transactions on Signal Processing 40 (1992) 611–623. · doi:10.1109/78.120804
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.