Queueing Systems

, Volume 79, Issue 3–4, pp 365–390 | Cite as

Optimal design of measurements on queueing systems

  • Ben M. ParkerEmail author
  • Steven Gilmour
  • John Schormans
  • Hugo Maruri-Aguilar


We examine the optimal design of measurements on queues with particular reference to the M/M/1 queue. Using the statistical theory of design of experiments, we calculate numerically the Fisher information matrix for an estimator of the arrival rate and the service rate to find optimal times to measure the queue when the number of measurements is limited for both interfering and non-interfering measurements. We prove that in the non-interfering case, the optimal design is equally spaced. For the interfering case, optimal designs are not necessarily equally spaced. We compute optimal designs for a variety of queuing situations and give results obtained under the \(D\)- and \(D_s\)-optimality criteria.


Design of experiments Maximum likelihood estimation  M/M/1 queue Active measurements 

Mathematics Subject Classification

62K05 60K99 68M20 



The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work.


  1. 1.
    Abate, J., Whitt, W.: Asymptotics for M/G/1 low-priority waiting-time tail probabilities. Queueing Syst. 25(1), 173–233 (1997)CrossRefGoogle Scholar
  2. 2.
    Acharya, S.: On normal approximation for maximum likelihood estimation from single server queues. Queueing Syst. 40(3), 313 (1999)Google Scholar
  3. 3.
    Aigner, D.: Parameter estimation from cross-sectional observations on an elementary queuing system. Oper. Res. 22(2), 422–428 (1974)CrossRefGoogle Scholar
  4. 4.
    Atkinson, A., Donev, A., Tobias, R.: Optimum Experimental Designs, with SAS. Oxford University Press, Oxford (2007)Google Scholar
  5. 5.
    Baccelli, F., Machiraju, S., Veitch, D., Bolot, J.: The role of PASTA in network measurement. ACM SIGCOMM Comput. Commun. Rev. 36(4), 231–242 (2006)CrossRefGoogle Scholar
  6. 6.
    Baccelli, F., Machiraju, S., Veitch, D., Bolot, J.: On optimal probing for delay and loss measurement. In: Proceedings of the 7th ACM SIGCOMM conference on Internet measurement, pp. 291–302. ACM (2007)Google Scholar
  7. 7.
    Baccelli, F., Machiraju, S., Veitch, D., Bolot, J.: Probing for loss: the case against probe trains. Commun. Lett. IEEE 15(5), 590–592 (2011)CrossRefGoogle Scholar
  8. 8.
    Basawa, I., Bhat, U., Lund, R.: Maximum likelihood estimation for single server queues from waiting time data. Queueing Syst. 24, 155–167 (1997)CrossRefGoogle Scholar
  9. 9.
    Basawa, I., Bhat, U., Zhou, J.: Parameter Estimation in Queueing Systems using Partial Information. Technical Report. Ohio State University, Columbus (2006)Google Scholar
  10. 10.
    Basawa, I., Prabhu, N.: Estimation in single server queues. Nav. Res. Logist. Q. 28(3), 475–487 (1981)CrossRefGoogle Scholar
  11. 11.
    Basawa, I., Prabhu, N.: Large sample inference from single server queues. Queueing Syst. Theory Appl. 3(4), 289–304 (1988)CrossRefGoogle Scholar
  12. 12.
    Billingsley, P.: Statistical Inference for Markov Processes. The University of Chicago Press, Chicago (1962)Google Scholar
  13. 13.
    Bodas, S., Shah, D., Wischik, D.: Congestion control meets medium access: throughput, delay, and complexity. In: Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems, pp. 399–400 (2012)Google Scholar
  14. 14.
    Chaloner, K., Verdinelli, I.: Bayesian experimental design: a review. Stat. Sci. 10(3), 273–304 (1995)CrossRefGoogle Scholar
  15. 15.
    Chen, T.: Parameter estimation for partially observed queues. IEEE Trans. Commun. 42(9), 2730–2739 (1994)CrossRefGoogle Scholar
  16. 16.
    Chernoff, H.: Locally optimal designs for estimating parameters. Ann. Math. Stat. 24(4), 586–602 (1953)CrossRefGoogle Scholar
  17. 17.
    Clarke, A.: Maximum likelihood estimates in a simple queue. Ann. Math. Stat. 28(4), 1036–1040 (Dec 1957)Google Scholar
  18. 18.
    Coffman, E., Robert, P., Simatos, F., Tarumi, S., Zussman, G.: A performance analysis of channel fragmentation in dynamic spectrum access systems. Queueing Syst. 71(3), 293–320 (2012)Google Scholar
  19. 19.
    Grossglauser, M., Tse, D.N.: A time-scale decomposition approach to measurement-based admission control. IEEE/ACM Trans. Netw. 11(4), 550–563 (2003)CrossRefGoogle Scholar
  20. 20.
    Jenkins, J.: The relative efficiency of direct and maximum likelihood estimates of mean waiting time in the simple queue M/M/l. J. Appl. Prob. 9(2), 396–403 (1972)CrossRefGoogle Scholar
  21. 21.
    Khisti, A., Huitema, C., Dube, A.: Controlling admission of data streams onto a network based on end-to-end measurements. US Patent 7,239,611, 3 July 2007Google Scholar
  22. 22.
    Kleinrock, L.: Queueing Systems: Theory, vol. 1. John Wiley & Sons Inc, New York (1975)Google Scholar
  23. 23.
    Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the Nelder–Mead simplex method in low dimensions. SIAM J. Optim. 9, 112–147 (1998)CrossRefGoogle Scholar
  24. 24.
    Leland, W.E., Taqqu, M.S., Willinger, W., Wilson, D.V.: On the self-similar nature of ethernet traffic (extended version). IEEE/ACM Trans. Netw. 2(1), 1–15 (1994)CrossRefGoogle Scholar
  25. 25.
    Love, S., Pollock, G.S., Goldsack, P., Kirshenbaum, E.R.: System and method for monitoring communication networks using data stream characterization. US Patent 6,904,020, 7 June 2005Google Scholar
  26. 26.
    Morse, P.M.: Stochastic properties of waiting lines. J. Oper. Res. Soc. Am. 3(3), 255–261 (1955). (Copyright 1955 INFORMS)Google Scholar
  27. 27.
    Nilsson, M.: Measuring available path capacity using short probe trains. In IEEE Network Operations and Management Symposium (NOMS), pp. 910–913 (2010)Google Scholar
  28. 28.
    Norros, I.: A storage model with self-similar input. Queueing Syst. 16(3), 387–396 (1994)CrossRefGoogle Scholar
  29. 29.
    Pagendam, D., Pollett, P.: Optimal sampling and problematic likelihood functions in a simple population model. Environ. Model. Assess. 14(6), 759–767 (2009)CrossRefGoogle Scholar
  30. 30.
    Pagendam, D., Pollett, P.: Robust optimal observation of a metapopulation. Ecol. Model. 221(21), 2521–2525 (2010)CrossRefGoogle Scholar
  31. 31.
    Parker, B., Gilmour, S., Schormans, J.: Measurement of packet loss probability by optimal design of packet probing experiments. IET Commun. 3(6), 979 (2009)CrossRefGoogle Scholar
  32. 32.
    Parker, B.M., Gilmour, S.G., Schormans, J.A.: Design of experiments for categorical repeated measurements in packet communication networks. Technometrics 53(4), 339–352 (2011)CrossRefGoogle Scholar
  33. 33.
    Raiciu, C., Barre, S., Pluntke, C., Greenhalgh, A., Wischik, D., Handley, M.: Improving datacenter performance and robustness with multipath TCP. ACM SIGCOMM Comput. Commun. Rev. 41, 266–277 (2011)CrossRefGoogle Scholar
  34. 34.
    Reynolds, J.: The covariance structure of queues and related processes: a survey of recent work. Adv. Appl. Prob. 7(2), 383–415 (1975)CrossRefGoogle Scholar
  35. 35.
    Ross, J., Pagendam, D., Pollett, P.: On parameter estimation in population models II: multi-dimensional processes and transient dynamics. Theor. Popul. Biol. 75(2–3), 123–132 (2009)CrossRefGoogle Scholar
  36. 36.
    Roughan, M.: Fundamental bounds on the accuracy of network performance measurements. In: Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems, pp. 253–264 (2005)Google Scholar
  37. 37.
    Roughan, M.: A comparison of poisson and uniform sampling for active measurements. IEEE J. Sel. Areas Commun. 24(12), 2299–2312 (2006)CrossRefGoogle Scholar
  38. 38.
    Shah, D., Wischik, D.: Fluid models of congestion collapse in overloaded switched networks. Queueing Syst. 69(2), 121–143 (2011)CrossRefGoogle Scholar
  39. 39.
    Shah, D., Wischik, D.: Log-weight scheduling in switched networks. Queueing Syst. 71(1–2), 97–136 (2012)Google Scholar
  40. 40.
    Spall, J.: Introduction to Stochastic Search and Optimization: Estimation, Simulation and Control. John Wiley & Sons Inc, New Jersey (2003)CrossRefGoogle Scholar
  41. 41.
    The ISP Column. The QoS emperor’s wardrobe. (2012). Accessed 26 Sept 2014
  42. 42.
    Wolff, R.: Poisson arrivals see time averages. Oper. Res. 30(2), 223–231 (1982)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Ben M. Parker
    • 1
    Email author
  • Steven Gilmour
    • 1
  • John Schormans
    • 2
  • Hugo Maruri-Aguilar
    • 3
  1. 1.Southampton Statistical Sciences Research InstituteUniversity of SouthamptonSouthamptonUK
  2. 2.School of Electronic Engineering and Computer ScienceQueen Mary University of LondonLondonUK
  3. 3.School of Mathematical SciencesQueen Mary University of LondonLondonUK

Personalised recommendations