The Effect of Correlated Service and Inter-arrival Times on System Performance

Authors: Gang Uk Hwang

Abstract:

In communication networks where communication nodes are connected with finite capacity transmission links, the packet inter-arrival times are strongly correlated with the packet length and the link capacity (or the packet service time). Such correlation affects the system performance significantly, but little attention has been paid to this issue. In this paper, we propose a mathematical framework to study the impact of the correlation between the packet service times and the packet inter-arrival times on system performance. With our mathematical model, we analyze the system performance, e.g., the unfinished work of the system, and show that the correlation affects the system performance significantly. Some numerical examples are also provided.

Keywords: Performance analysis, Correlated queueing system, Unfinished work, PH-type distribution, Communicationsystem.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1078565

References:

[1] I. Cidon, R. Guerin, A. Khamisy, and M. Sidi, "Analysis of a Correlated Queue in a Communication System", IEEE Transactions on Information Theory, Vol. 39, No. 2, pp. 456-465, 1993.
[2] I. Cidon, R. Guerin, A. Khamisy, and M. Sidi, "On queues with interarrival times proportional to service times", Proceeding of INFOCOM -93.
[3] M. Kuczma, B. Choczewski and R. Ger., Iterative Functional Equations, Encyclopedia of Mathematics and its Applications, Cambridge University Press, Cambridge, 1990.
[4] D. Anick, D. Mitra, and M.M. Sondhi, "Stochastic theory of a datahandling system with multiple sources," Bell System Tech. J., Vol. 61, pp. 1871-1894, 1982.
[5] A.I. Elwalid, D. Mitra, and T.E. Stern, "Statistical multiplexing of Markov modulated sources: Theory and computational algorithms," Proc. 13th Int. Teletraffic Cong., Copenhagen, pp. 495-500, 1991.
[6] D. Mitra, "Stochastic theory of a fluid model of producers and consumers coupled by a buffer," Advances in Applied Probability, Vol. 20, pp. 646- 676, 1988.
[7] T.E. Stern and A.I. Elwalid, "Analysis of separable Markov-modulated models for information-handling systems," Advances in Applied Probability, Vol. 23, pp. 105-139, 1991.
[8] G.U. Hwang and K. Sohraby, "Modelling and Analysis of a Buffer in an ATM-based MPLS LER System," Proceeding of Globecom 2002, CQRS- 06-3, Taipei, Taiwan, 2002.
[9] G.U. Hwang and K. Sohraby, "Performance of Correlated Queues: The Impact of Correlated Service and Inter-arrival Times," Performance Evaluation, Vol. 55, No. 1-2, 129-145, 2004.
[10] M.F. Neuts, Matrix Geometric Solutions in Stochastic Models: An Algorithmic Approach, Johns Hopkins University Press, 1981.
[11] S. Asmussen, Applied Probability and Queues, John Wiley and Sons, 1987.
[12] H. Minc, Nonnegative Matrices, John Wiley & Sons, Inc., 1988.
[13] WAN packet Size Distribution, (Online), Available WWW: http://www.nlanr.net/NA/Learn/packetsizes.html.