Hostname: page-component-84b7d79bbc-2l2gl Total loading time: 0 Render date: 2024-07-25T20:32:14.791Z Has data issue: false hasContentIssue false
  • English
  • Français

Applications of matrix-geometric solutions for queueing performance evaluation of a hybrid switching system

Published online by Cambridge University Press:  17 February 2009

Moshe Zukerman
Moshe Zukerman
Affiliation:
Telecom Australia Research Laboratories, Clayton, Victoria, Australia.
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

We consider a hybrid switch which provides integrated packet (asynchronous) and circuit (isochronous) switching. Queue size and delay distribution of the packet switched traffic in the steady state are derived by modelling the packet queue as a queue in a Markovian environment. The arrival process of the packets as well as of the circuit allocation requests are both modelled by a Poisson process. The analysis is performed for several circuit allocation policies, namely repacking, first-fit (involving static or dynamic renumbering) and best-fit. Both exact results and approximations are discussed. Numerical results are presented to demonstrate the effect of increase in packet and circuit loading on the packet delay for each of the policies.

Type
Research Article
Information
The ANZIAM Journal , Volume 31 , Issue 2 , October 1989 , pp. 219 - 239
Copyright
Copyright © Australian Mathematical Society 1989

References

[1]Budrikis, Z. L., Hullett, J. L., Newman, R. M., Economou, D., Fosdar, F. M. and Jeffery, R. D., “QPSX: A queued packet and synchronous circuit exchange”, Proc. ICCC, Munich (1986).Google Scholar
[2]Budrikis, Z. L., Evans, P. A. and Newman, R. M., “QPSX: a proposal from Australia for MAN standard”, IEEE 802 Committee Tutorial Presentation (1986).Google Scholar
[3]Budrikis, Z. L., Hullett, J. L., Neman, R. M., Economou, D., Fosdar, F. M. and Jeffery, J. D., “QPSX: A queued packet and synchronous exchange as a local or metropolitan area network”, Proc. Second Australian Computer Engineering Conference, Sydney (1986).Google Scholar
[4]Caves, K. and Flatman, A. V., “FDDI-II: a new standard for integrated services high speed LANs”, Proc. Wideband Communications, (1986) 81–91.Google Scholar
[5]coffman, E. G., Kadota, T. T. and Shepp, L. A., “A stochastic model of fragmentation in dynamic storage allocation”, SIAM J. Comput. 14 (1985).CrossRefGoogle Scholar
[6]Cooper, R. B., Introduction to queueing theory (North Holland, New York, 1981).Google Scholar
[7]Evans, P. A., Hayes, M. D. and Potter, P. G., “Metropolitan area networks”, Proc. IREE-CON'87, Sydney (1987).Google Scholar
[8]Feldmeier, D. C., Empirical analysis of a token ring network Tech. Memo. TM-254, MIT Lab. for Comp. Sci. (1984).Google Scholar
[9]Fischer, M. J. and Harris, T. C., “A model for evaluating the performance of an integrated circuite and packet-switched multiplex structure”, IEEE Trans. Comm. COM-24 (1976).CrossRefGoogle Scholar
[10]Gelenbe, E. and Rosenberg, C., Queues with slowly varying arrival and service process Report No. 059, Laboratoire I.S.E.M., Universite de Paris-Sud, France (1987).Google Scholar
[11]Heffes, H., “A class of data traffic processes-covariance function characterization and related queueing results”, Bell Syst. Tech. J. 59 (1980) 897–929.CrossRefGoogle Scholar
[12]Heffes, H. and Lucantoni, D. M., “A Markov modulated characterization of packetized voice and data traffic and related statistical multiplexer performance”, IEEE J-SAC. SAC-4 (1986) 856–868.Google Scholar
[13]Huber, M. N., Sauer, K. and Schodl, W., “QPSX and FDDI-II performance study of high speed LAN's”, EFOC/LAN Amsterdam (1988).Google Scholar
[14]Hullett, J. L. and Evans, P., “New proposal extends the reach of metro area nets”, Data Communications (1988).Google Scholar
[15]IEEE 802.6 Committee, Draft of proposed IEEE standard 802.6 distributed queue dual bus (DQDB) metropolitan area network (MAN)-Draft D6–88/I05, an internal working document of the IEEE 802.6 working group (1988).Google Scholar
[16]Knuth, D. E., The art of computer programming, volume 2: computer algorithms (Addison-Wesley, Massachusetts, 1973).Google Scholar
[17]Konheim, A. G. and Reiser, M., “The movable-boudnary multiplexor stability and decom-posability”, Teletraffic Analysis and Computer Performance Evaluation (North Holland, 1986).Google Scholar
[18]Leon-Garcia, A., Kwong, R. H. and Williams, G. F., “Performance evaluation methods for an integrated voice/data link”, IEEE Trans Comm. COM-30 (1982) 1848–1858.CrossRefGoogle Scholar
[19]Le, M. and Neitzel, L., “FDDI-II working paper”, ANSC Document No. X3T9.5 (1986).Google Scholar
[20]Manneld, D. R., “Transport delays in a hybrid switching system with polling”, Proc. IEEE ICC'85, Chicago, 1985.Google Scholar
[21]Meier-Hellstern, K. S., “A fitting algorithm for Markov-modulated Poisson process having two arrival rates”, European J. of Operational Research 29 (1987) 370–377.CrossRefGoogle Scholar
[22]Neuts, M. F., “The M/M/1 queue with randomly varying arrival and service rates”, Opsearch 15 (1978) 139–157.Google Scholar
[23]Neuts, M. F., “Further results on the M/M/l queue with randomly varying rates”, Opsearch 15 (1978) 158–168.Google Scholar
[24]Neuts, M. F., Matrix-Geometric solutions in stochastic models: an algorithmic approach (The John Hopkins University Press, Baltimore, 1981).Google Scholar
[25]Newman, R. M., Budrikis, Z. L. and Hullett, J. L., “The QPSX Man”, IEEE Communications Magazine 26 (1988) 20–28.CrossRefGoogle ScholarPubMed
[26]Newman, R. M. and Hullett, J. L., “Distributed queueing: a fast and efficient packet access protocol for QPSX”, Proc. ICCC'86, Munich, 1986.Google Scholar
[27]O'Reilly, P., “Performance analysis of data in burst switching”, IEEE Trans. on Commun. COM-43 (1986).Google Scholar
[28]Ramaswami, V. and Lucantoni, D. M., “Stationary waiting time distribution in queues with pase type service a in quasi birth and death processes”, Commun. Statist. Stochastic Models 1 (1985) 125–136.CrossRefGoogle Scholar
[29]Rossiter, M. H., “A switched Poisson model for data traffic”, Australian Telecommunication Research 21 (1987).Google Scholar
[30]Shoch, J. F. and Hupp, J. A., “Measured performance of an ethernet local network”, J. ACM 23 (1980) 711–721.CrossRefGoogle Scholar
[31]Sriram, K., Varshney, P. K. and Shanthikumar, J. G., “Discrete-time analysis of integrated voice/data multiplexers with and without speech activity detectors”, IEEE J-SAC. SAC-16 (1986) 1124–1132.Google Scholar
[32]Williams, G. F. and Leon-Garcia, A., “Performance analysis of integrated voice and data hybrid-switched links”, IEEE Trans. Comm. COM-32 (1984) 679–706.CrossRefGoogle Scholar
[33]Yechiali, U. and Naor, P., “Queueing problems with heterogeneous arrivals and service”, Opns. Res. 19 (1971) 722–734.CrossRefGoogle Scholar
[34]Zukerman, M., “On packet switching capacity in QPSX”, Proc. GLOBECOM, Tokyo (1987).Google Scholar
[35]Zukerman, M., “Circuit allocation and overload control in hybrid switching system”, Computer Networks and ISDN Systems 16 (1989) 281–298.CrossRefGoogle Scholar
[36]Zukerman, M., “Bandwidth allocation for bursty isochronous traffic in a hybrid switching system”, to appear in IEEE Trans. Commun.Google Scholar
[37]Zukerman, M., “Approximations for performance evaluation of the packet access queue in QPSX: the IEEE 802.6 evolving MAN standard”, A.T.R. 22 (1988) 53–62.Google Scholar
[38]Zukerman, M. and Kirton, P., “Applications of matrix-geometric solutions to the analysis of the bursty data queue in a B-ISDN switching system”, Proc. GLOBECOM '88 3 (1988) 1635–1639.Google Scholar