Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Statistical Methods
Control, Design, and Uncertainty Quantification
Conclusion
References
All Topics
Mathematics
Applied Mathematics

A survey of parameter and state estimation in queues

Profile image of Azam AsanjaraniAzam Asanjarani

2021, Queueing Systems

https://doi.org/10.1007/S11134-021-09688-W
visibility

…

description

36 pages

link

1 file

Abstract

We present a broad literature survey of parameter and state estimation for queueing systems. Our approach is based on various inference activities, queueing models, observations schemes, and statistical methods. We categorize these into branches of research that we call estimation paradigms. These include: the classical sampling approach, inverse problems, inference for noninteracting systems, inference with discrete sampling, inference with queueing fundamentals, queue inference engine problems, Bayesian approaches, online prediction, implicit models, and control, design, and uncertainty quantification. For each of these estimation paradigms, we outline the principles and ideas, while surveying key references. We also present various simple numerical experiments. In addition to some key references mentioned here, a periodically-updated comprehensive list of references dealing with parameter and state estimation of queues will be kept in an accompanying annotated bibliography.

Related papers

Likelihood-Free Parameter Estimation for Dynamic Queueing Networks
Antonietta Mira

arXiv (Cornell University), 2018

Dynamic queueing networks (DQN) model queueing systems where demand varies strongly with time, such as airport terminals. With rapidly rising global air passenger traffic placing increasing pressure on airport terminals, efficient allocation of resources is more important than ever. Parameter inference and quantification of uncertainty are key challenges for developing decision support tools. The DQN likelihood function is, in general, intractable and current approaches to simulation make likelihood-free parameter inference methods, such as approximate Bayesian computation (ABC), infeasible since simulating from these models is computationally expensive. By leveraging a recent advance in computationally efficient queueing simulation, we develop the first parameter inference approach for DQNs. We demonstrate our approach with data of passenger flows in a real airport terminal, and we show that our model accurately recreates the behaviour of the system and is useful for decision support. Special care must be taken in developing the distance for ABC since any useful output must vary with time. We use maximum mean discrepancy, a metric on probability measures, as the distance function for ABC. Prediction intervals of performance measures for decision support tools are easily constructed using draws from posterior samples, which we demonstrate with a scenario of a delayed flight.

View PDFchevron_right
Statistical inference for G/M/1 queueing system
sudha jain

Operations Research Letters, 1988

In this paper, maximum likelihood estimates of the parameters are derived for the G/M/1 queueing model with variable arrival rate. A simulated numerical example is used to illustrate its application for estimating the parameter when the interarrival time distribution is exponential. Problems of hypothesis testing are also investigated.

View PDFchevron_right
Parameter inference of queueing models for IT systems using end-to-end measurements
Laura Wynter

Performance Evaluation, 2006

Performance modeling has become increasingly important in the design, engineering and optimization of information technology (IT) infrastructures and applications. However, modeling work itself is time consuming and requires a good knowledge not only of the system, but also of modeling techniques. One of the biggest challenges in modeling complex IT systems consists in the calibration of model parameters, such as the service requirements of various job classes. We present an approach for solving this problem in the queueing network framework using inference techniques. This is done through a mathematical programming formulation, for which we propose an efficient and robust solution method. The necessary input data are end-to-end measurements which are usually easy to obtain. The robustness of our method means that the inferred model performs well in the presence of noisy data and further, is able to detect and remove outlying data sets. We present numerical experiments using data from real IT practice to demonstrate the promise of our framework and algorithm.

View PDFchevron_right
Simulation methods for queues: An overview
Peter Glynn

Queueing Systems, 1988

This paper gives an overview of those aspects of simulation methodology that are (to some extent) peculiar to the simulation of queueing systems. A generalized semi-Markov process framework for describing queueing systems is used through much of the paper. The main topics covered are: output analysis for simulation of transient and steady-state quantities, variance reduction methods that exploit queueing structure, and gradient estimation methods for performance parameters associated with queueing networks.

View PDFchevron_right
Bayesian control of the number of servers in a queueing system
Rosa Lillo

Journal of Statistical Planning and Inference, 2007

In this paper we consider the problem of designing a GI/M/c queueing system. Given arrival and service data, our objective is to choose the optimal number of servers so as to minimize an expected cost function which depends on quantities, such as the number of customers in the queue. A semiparametric approach based on Erlang mixture distributions is used to model the general interarrival time distribution. Given the sample data, Bayesian Markov chain Monte Carlo methods are used to estimate the system parameters and the predictive distributions of the usual performance measures. We can then use these estimates to minimize the steady-state expected total cost rate as a function of the control parameter c.

View PDFchevron_right
Bayesian analysis of an M|M|1|∞ queueing model
Naveen Bansal

Pakistan Journal of Statistics and Operation Research, 2022

In this paper, by considering an M|M|1|∞ queueing model, Bayes estimators of traffic intensity and measures of system performance are worked out under squared error loss function (SELF) based on observed data on the independent interarrival and service times. Further, minimum posterior risk associated with Bayes estimators of traffic intensity and system performance measures are obtained under SELF. Numerical illustration of the performance of the estimates is given through simulation study. It is shown that Bayes estimators perform better than the maximum likelihood estimators under the influence of prior information.

View PDFchevron_right
Bayes, Neyman and Neyman-Bayes Inference for Queueing Systems
Daniel Ciuiu

2007

In this paper we will use the Bayesian inference for the parameters that appear in the queueing systems. We will estimate these parameters and we will build confidence intervals and significance tests for them, considering the parameters of the exponential Poisson and geometric distribution. We will also use the Neyman and the Neyman-Bayes inference for the exponential and Poisson distribution.

View PDFchevron_right
BAYESIAN ANALYSIS IN AN M/G/S QUEUE WITH OPTIONAL SECOND SERVICE.
IJAR Indexing

The paper proposes Bayesian framework in an M/G/s queuing system with optional second service.The semi-parametric model based on a finite mixture of Gamma distributions is considered to approximate both the general service and re-service times densities in this queuing system. A Bayesian procedure based on birth-death MCMC methodology is proposed to estimate system parameters, predictive densities and some performance measures related to this queuing system such as stationary system size and waiting time. The approach is illustrated with several numerical examples based on various simulation studies.

View PDFchevron_right
Estimation of linear stochastic systems over a queueing network
Eduardo Souto

Proceedings - 2005 Systems Communications: ICW 2005, Wireless - ICHSN 2005, High Speed Networks - ICMCS 2005, Multimedia Communications Systems - SENET 2005, Sensor Networks, 2005

View PDFchevron_right
Some Pitfalls of Black Box Queue Inference: The Case of State-Dependent Server Queues
J. George Shanthikumar

Probability in the Engineering and Informational Sciences, 1993

In several queueing systems the service rate of a server is affected by the work load present in the system. For example, a teller at a bank or a checker at a check-out counter in a supermarket may change the service rate depending on the number of customers present in the system. But the service rate as a function of the number in the system can rarely be measured. Consequently, in a typical model of such a system it is assumed that the service rate is constant. Hence, such systems with a single stage are often modeled by GI/GI/c queueing systems with mutually independent arrival and service processes. Then the observed service times are used to find a sample distribution that will represent the distribution of the assumed i.i.d. service times. The purpose of this paper is to explore the effect of this black box queue inference (BBQI) in its ability to predict the performance of the actual system. In this regard, we have shown that when the arrival process is Poisson, if the server...

View PDFchevron_right

References (131)

  1. Alouf, S., Nain, P., and Towsley, D. Inferring network characteristics via moment-based estimators. In INFOCOM 2001. Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings. IEEE (2001), vol. 2, IEEE, pp. 1045-1054.
  2. Antunes, N., Jacinto, G., and Pacheco, A. Probing a M/G/1 queue with general input and service times. ACM SIGMETRICS Performance Evaluation Review 41, 3 (2014), 34-36.
  3. Antunes, N., Jacinto, G., Pacheco, A., and Wichelhaus, C. Estimation of the traffic in- tensity in a piecewise-stationary M t /G t /1 queue with probing. ACM SIGMETRICS Performance Evaluation Review 44, 2 (2016), 3-5.
  4. Armero, C. Bayesian analysis of M/M/1/∞/FIFO queues. Bayesian statistics 2 (1985), 613- 618.
  5. Armero, C. Bayesian inference in Markovian queues. Queueing Systems 15, 1 (1994), 419-426.
  6. Armero, C., and Bayarri, M. Bayesian prediction in M/M/1 queues. Queueing Systems 15, 1 (1994), 401-417.
  7. Armero, C., and Bayarri, M. Prior assessments for prediction in queues. The Statistician 43, 1 (1994), 139-153.
  8. Armony, M., and Plambeck, E. The impact of duplicate orders on demand estimation and capacity investment. Management science 51, 10 (2005), 1505-1518.
  9. Asanjarani, A., and Nazarathy, Y. Parameter and state estimation in queues and related stochastic models: A bibliography. arXiv preprint arXiv:1701.08338 (2020).
  10. Asanjarani, A., and Nazarathy, Y. The Role of Information in System Stability with Partially Observable Servers. Methodology and Computing in Applied Probability 22 (2020), 949-968.
  11. Asanjarani, A., Nazarathy, Y., and Taylor, G. Queueing Estimation Survey. https://github.com/yoninazarathy/QueueingEstimationSurvey, 2020.
  12. Asmussen, S. Applied probability and queues (stochastic modeling and applied probability series, vol. 51). Springer Science & Business Media, 2010.
  13. Asmussen, S., Nerman, O., and Olsson, M. Fitting phase-type distributions via the EM algorithm. Scandinavian Journal of Statistics 23, 4 (1996), 419-441.
  14. Au, L., Byrnes, G., Bain, C., Fackrell, M., Brand, C., Campbell, D., and Taylor, P. Predicting overflow in an emergency department. IMA Journal of Management Mathematics 20, 1 (2009), 39-49.
  15. Ausín, M., Wiper, M., and Lillo, R. Bayesian estimation for the M/G/1 queue using a phase-type approximation. Journal of Statistical Planning and Inference 118, 1-2 (2004), 83- 101.
  16. Baccelli, F., Kauffmann, B., and Veitch, D. Inverse problems in queueing theory and internet probing. Queueing Systems 63, 1 (2009), 59-107.
  17. Bandi, C., Bertsimas, D., and Youssef, N. Robust queueing theory. Operations Research 63, 3 (2015), 676-700.
  18. Basawa, I., Bhat, U., and Lund, R. Maximum likelihood estimation for single server queues from waiting time data. Queueing Systems 24, 1 (1996), 155-167.
  19. Basawa, I., Bhat, U., and Zhou, J. Parameter estimation using partial information with applications to queueing and related models. Statistics & Probability Letters 78, 12 (2008), 1375-1383.
  20. Basawa, I., and Prabhu, N. Large sample inference from single server queues. Queueing Systems 3, 4 (1988), 289-304.
  21. Bertsimas, D., and Servi, L. Deducing queueing from transactional data: the queue inference engine, revisited. Operations Research 40 (1992), S217-S228.
  22. Bhat, U., Miller, G., and Rao, S. Statistical analysis of queueing systems. Chapter in: Frontiers in queueing (ed. J.H. Dshalalow) (1997), 351-394.
  23. Bhat, U., and Rao, S. Statistical analysis of queueing systems. Queueing Systems 1, 3 (1987), 217-247.
  24. Bingham, N., and Pitts, S. Non-parametric estimation for the M/G/∞ queue. Annals of the Institute of Statistical Mathematics 51, 1 (1999), 71-97.
  25. Bingham, N., and Pitts, S. Nonparametric inference from M/G/l busy periods. Stochastic Models 15, 2 (1999), 247-272.
  26. Bladt, M., and Sørensen, M. Statistical inference for discretely observed Markov jump processes. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 67, 3 (2005), 395-410.
  27. Blanghaps, N., Nov, Y., and Weiss, G. Sojourn time estimation in an M/G/∞ queue with partial information. Journal of Applied Probability 50, 4 (2013), 1044-1056.
  28. Bolstad, W., and Curran, J. Introduction to Bayesian statistics. John Wiley & Sons, 2016.
  29. Boxma, O., and Vlasiou, M. On queues with service and interarrival times depending on waiting times. Queueing Systems 56, 3-4 (2007), 121-132.
  30. Bramson, M. Stability of queueing networks. Springer, 2008.
  31. Brillinger, D. Cross-spectral analysis of processes with stationary increments including the stationary G/G/∞ queue. The Annals of Probability 2, 5 (1974), 815-827.
  32. Brockwell, P., Davis, R., and Fienberg, S. Time series: theory and methods: theory and methods. Springer Science & Business Media, 1991.
  33. Brown, M. An M/G/∞ estimation problem. The Annals of Mathematical Statistics 41, 2 (1970), 651-654.
  34. Carson, J., and Law, A. Conservation equations and variance reduction in queueing simula- tions. Operations Research 28, 3-part-i (1980), 535-546.
  35. Chen, H., and Yao, D. Fundamentals of queueing networks: Performance, asymptotics, and optimization ( stochastic modelling and applied probability series, vol. 46), vol. 46. Springer Science & Business Media, 2013.
  36. Chen, T., Walrand, J., and Messerschmitt, D. Parameter estimation for partially ob- served queues. Communications, IEEE Transactions on 42, 9 (1994), 2730-2739.
  37. Clarke, A. Maximum likelihood estimates in a simple queue. The Annals of Mathematical Statistics 28, 4 (1957), 1036-1040.
  38. Cohen, J. The single server queue (applied. Mathematics and mechanics, vol. 8). North-Holland Amsterdam, 1982.
  39. Comert, G., and Cetin, M. Queue length estimation from probe vehicle location and the impacts of sample size. European Journal of Operational Research 197, 1 (2009), 196-202.
  40. Conti, P. Large sample Bayesian analysis for Geo/G/1 discrete-time queueing models. The Annals of Statistics 27, 6 (1999), 1785-1807.
  41. Cox, D. Some problems of statistical analysis connected via congestion. In Proc. Symp. on Congestion Theory (1965), pp. 289-316.
  42. Daley, D., and Servi, L. Exploiting Markov chains to infer queue length from transactional data. Journal of Applied Probability 29, 3 (1992), 713-732.
  43. Daley, D., and Servi, L. A two-point Markov chain boundary-value problem. Advances in Applied Probability 25, 3 (1993), 607-630.
  44. Daley, D., and Servi, L. Estimating waiting times from transactional data. INFORMS Journal on Computing 9, 2 (1997), 224-229.
  45. Daley, D., and Servi, L. Moment estimation of customer loss rates from transactional data. Journal of Applied Mathematics and Stochastic Analysis 11, 3 (1998), 301-310.
  46. den Boer, A., and Mandjes, M. Convergence rates of Laplace-transform based estimators. Bernoulli 23, 4A (2017), 2533-2557.
  47. Dimitrijevic, D. Inferring most likely queue length from transactional data. Operations Re- search Letters 19, 4 (1996), 191-199.
  48. Dinh, T., Andrew, L., and Nazarathy, Y. Architecture and robustness tradeoffs in speed- scaled queues with application to energy management. International Journal of Systems Science 45, 8 (2014), 1728-1739.
  49. Dong, J., and Whitt, W. Stochastic grey-box modeling of queueing systems: fitting birth- and-death processes to data. Queueing Systems 79, 3-4 (2015), 391-426.
  50. Dong, J., and Whitt, W. Using a birth-and-death process to estimate the steady-state distribution of a periodic queue. Naval Research Logistics (NRL) 62, 8 (2015), 664-685.
  51. Duffie, D., and Glynn, P. Estimation of continuous-time Markov processes sampled at random time intervals. Econometrica 72, 6 (2004), 1773-1808.
  52. Duffy, K., and Meyn, S. Estimating Loynes' exponent. Queueing Systems 68, 3-4 (2011), 285-293.
  53. Edelmann, D., and Wichelhaus, C. Nonparametric inference for queueing networks of Geom X /G/∞ queues in discrete time. Advances in Applied Probability 46, 3 (2014), 790-811.
  54. Fearnhead, P. Filtering recursions for calculating likelihoods for queues based on inter- departure time data. Statistics and Computing 14, 3 (2004), 261-266.
  55. Foss, S., and Konstantopoulos, T. An overview of some stochastic stability methods (special issue: network design, control and optimization). Journal of the Operations Research Society of Japan 47, 4 (2004), 275-303.
  56. Frey, J., and Kaplan, E. Queue inference from periodic reporting data. Operations Research Letters 38, 5 (2010), 420-426.
  57. Glynn, P., Melamed, B., and Whitt, W. Estimating customer and time averages. Opera- tions research 41, 2 (1993), 400-408.
  58. Glynn, P., and Torres, M. Parametric estimation of tail probabilities for the single-server queue. Chapter in Frontiers in Queueing: Models and Applications in Science and Engineering (ed. J.H. Dshalalow) (1997), 449-462.
  59. Glynn, P., and Whitt, W. A central-limit-theorem version of L= λW. Queueing Systems 1, 2 (1986), 191-215.
  60. Glynn, P., and Whitt, W. Indirect estimation via L = λW . Operations Research 37, 1 (1989), 82-103.
  61. Glynn, P., and Zeevi, A. Estimating tail probabilities in queues via extremal statistics. analysis of communication networks: Call centres, traffic and performance, 135-158. Fields Inst. Commun 28 .
  62. Goldenschluger, A. Nonparametric estimation of the service time distribution in the M/G/∞ queue. Advances in Applied Probability 48, 4 (2016), 1117-1138.
  63. Goldenshluger, A. The M/G/∞ estimation problem revisited. Bernoulli 24, 4A (2018), 2531-2568.
  64. Goldenshluger, A., and Koops, D. T. Nonparametric estimation of service time character- istics in infinite-server queues with nonstationary Poisson input. Stochastic Systems 9, 3 (2019), 183-207.
  65. Grübel, R. Stochastic models as functionals: some remarks on the renewal case. Journal of Applied Probability 26, 2 (1989), 296-303.
  66. Grübel, R., and Pitts, S. A functional approach to the stationary waiting time and idle period distributions of the GI/G/1 queue. The Annals of Probability 20, 4 (1992), 1754-1778.
  67. Grübel, R., and Wegener, H. Matchmaking and testing for exponentiality in the M/G/∞ queue. Journal of Applied Probability 48, 1 (2011), 131-144.
  68. Hall, P., and Park, J. Nonparametric inference about service time distribution from indirect measurements. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 66, 4 (2004), 861-875.
  69. Hansen, M., and Pitts, S. Nonparametric inference from the M/G/1 workload. Bernoulli 12, 4 (2006), 737-759.
  70. Heckmuller, S., and Wolfinger, B. Reconstructing arrival processes to G/D/1 queueing systems and tandem networks. In Performance Evaluation of Computer & Telecommunication Systems, 2009. SPECTS 2009. International Symposium on (2009), vol. 41, IEEE, pp. 361-368.
  71. Heckmüller, S., and Wolfinger, B. Reconstructing arrival processes to discrete queueing systems by inverse load transformation. Simulation 87, 12 (2011), 1033-1047.
  72. Hei, X., Bensaou, B., and Tsang, D. A light-weight available bandwidth inference method- ology in a queueing analysis approach. In Communications, 2005. ICC 2005. 2005 IEEE Inter- national Conference on (2005), vol. 1, IEEE, pp. 120-124.
  73. Hei, X., Bensaou, B., and Tsang, D. Model-based end-to-end available bandwidth inference using queueing analysis. Computer Networks 50, 12 (2006), 1916-1937.
  74. Hernandez-Lerma, O., and Marcus, S. Adaptive control of service in queueing systems. Systems & Control Letters 3, 5 (1983), 283-289.
  75. Ibrahim, R., and Whitt, W. Wait-time predictors for customer service systems with time- varying demand and capacity. Operations Research-Baltimore 59, 5 (2011), 1106-1118.
  76. Insua, D., Wiper, M., and Ruggeri, F. Bayesian analysis of M/Er/1 and M/H k /1 queues. Queueing Systems 30, 3 (1998), 289-308.
  77. Jones, L. Inferring balking behavior from transactional data. Operations Research 47, 5 (1999), 778-784.
  78. Jones, L. Remarks on queue inference from departure data alone and the importance of the queue inference engine. Operations Research Letters 40, 6 (2012), 503-505.
  79. Jones, L., and Larson, R. Efficient computation of probabilities of events described by order statistics and applications to queue inference. ORSA Journal on Computing 7, 1 (1995), 89-100.
  80. Kauffmann, B. Inverse problems in bandwidth sharing networks. In Proceedings of the 24th International Teletraffic Congress (2012), International Teletraffic Congress, p. 6.
  81. Ke, J., and Chu, Y. Comparison on five estimation approaches of intensity for a queueing system with short run. Computational Statistics 24, 4 (2009), 567-582.
  82. Kelly, F. Reversibility and stochastic networks. Cambridge University Press, 2011.
  83. Kiessler, P., and Lund, R. Technical note: Traffic intensity estimation. Naval Research Logistics (NRL) 56, 4 (2009), 385-387.
  84. Kim, S., and Whitt, W. Estimating waiting times with the time-varying Little's law. Proba- bility in the Engineering and Informational Sciences 27, 4 (2013), 471-506.
  85. Kim, S., and Whitt, W. Statistical analysis with Little's law. Operations Research 61, 4 (2013), 1030-1045.
  86. Kim, S., Whitt, W., and Cha, W. A data-driven model of an appointment-generated arrival process at an outpatient clinic. INFORMS Journal on Computing 30, 1 (2018), 181-199.
  87. Krishnasamy, S., Arapostathis, A., Johari, R., and Shakkottai, S. On learning the cµ rule in single and parallel server networks. In 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton) (2018), IEEE, pp. 153-154.
  88. Larson, R. The queue inference engine: deducing queue statistics from transactional data. Management Science 36, 5 (1990), 586-601.
  89. Latouche, G., Ramaswami, V., Sethuraman, J., Sigman, K., Squillante, M., and Yao, D. Matrix-Analytic Methods in Stochastic Models (Springer proceedings in mathematics & statistics, vol. 27). Springer Science & Business Media, 2012.
  90. Mandelbaum, A., and Zeltyn, S. Estimating characteristics of queueing networks using transactional data. Queueing Systems 29, 1 (1998), 75-127.
  91. Mandjes, M., Patch, B., and Walton, N. Detecting Markov chain instability: a Monte Carlo approach. Stochastic Systems 7, 2 (2017), 289-314.
  92. Mandjes, M., and Ravner, L. Hypothesis testing for a Lévy-driven storage system by Poisson sampling. Stochastic Processes and their Applications 133 (2020), 41-73.
  93. Mcgrath, M., Gross, D., and Singpurwalla, N. A subjective Bayesian approach to the theory of queues I-Modeling. Queueing Systems 1, 4 (1987), 317-333.
  94. McGrath, M., and Singpurwalla, N. A subjective Bayesian approach to the theory of queues II-Inference and information in M/M/1 queues. Queueing Systems 1, 4 (1987), 335-353.
  95. McVinish, R., and Pollett, P. Constructing estimating equations from queue length data. preprint.
  96. Nam, S., Kim, S., and Sung, D. Estimation of available bandwidth for an M/G/1 queueing system. Applied Mathematical Modelling 33, 8 (2009), 3299-3308.
  97. Neal, R. Slice sampling. Annals of statistics 31, 3 (2003), 705-741.
  98. Novak, A., and Watson, R. Determining an adequate probe separation for estimating the arrival rate in an M/D/1 queue using single-packet probing. Queueing Systems 61, 4 (2009), 255-272.
  99. Nozari, A., and Whitt, W. Estimating average production intervals using inventory mea- surements: Little's law for partially observable processes. Operations research 36, 2 (1988), 308-323.
  100. Pagurek, B., Stanford, D. A., and Woodside, C. M. Optimal prediction of times and queue lengths in the M/G/1 queue. Journal of the Operational Research Society 39, 6 (1988), 585-593.
  101. Park, J., Kim, Y. B., and Willemain, T. Analysis of an unobservable queue using arrival and departure times. Computers & Industrial Engineering 61, 3 (2011), 842-847.
  102. Pickands III, J., and Stine, R. Estimation for an M/G/∞ queue with incomplete informa- tion. Biometrika 84, 2 (1997), 295-308.
  103. Pin, F., Veitch, D., and Kauffmann, B. Statistical estimation of delays in a multicast tree using accelerated EM. Queueing Systems 66, 4 (2010), 369-412.
  104. Pitts, S. Nonparametric estimation of the stationary waiting time distribution function for the GI/G/1 queue. The Annals of Statistics 22, 3 (1994), 1428-1446.
  105. Ramirez-Cobo, P., Lillo, R., Wilson, S., and Wiper, M. Bayesian inference for double Pareto lognormal queues. The Annals of Applied Statistics 4, 3 (2010), 1533-1557.
  106. Ravner, L., Boxma, O., and Mandjes, M. Estimating the input of a Lévy-driven queue by Poisson sampling of the workload process. Bernoulli 25, 4B (2019), 3734-3761.
  107. Reynolds, J. The covariance structure of queues and related processes-a survey of recent work. Advances in Applied Probability 7, 2 (1975), 383-415.
  108. Rodrigo, A., and Vazquez, M. Large sample inference in retrial queues. Mathematical and Computer Modelling 30, 3-4 (1999), 197-206.
  109. Ross, J., Taimre, T., and Pollett, P. Estimation for queues from queue length data. Queueing Systems 55, 2 (2007), 131-138.
  110. Schruben, L., and Kulkarni, R. Some consequences of estimating parameters for the M/M/1 queue. Operations Research Letters 1, 2 (1982), 75-78.
  111. Schweer, S., and Wichelhaus, C. Nonparametric estimation of the service time distribution in the discrete-time GI/G/∞ queue with partial information. Stochastic Processes and their Applications 125, 1 (2015), 233-253.
  112. Schweer, S., and Wichelhaus, C. Nonparametric estimation of the service time distribution in discrete-time queueing networks. Stochastic Processes and their Applications 130, 8 (2020), 4643 -4666.
  113. Senderovich, A., Leemans, S., Harel, S., Gal, A., Mandelbaum, A., and van der Aalst, W. Discovering queues from event logs with varying levels of information. In Interna- tional Conference on Business Process Management (2016), Springer, pp. 154-166.
  114. Senderovich, A., Weidlich, M., Gal, A., and Mandelbaum, A. Queue mining-predicting delays in service processes. In International Conference on Advanced Information Systems En- gineering (2014), Springer, pp. 42-57.
  115. Senderovich, A., Weidlich, M., Gal, A., and Mandelbaum, A. Queue mining for delay prediction in multi-class service processes. Information Systems 53 (2015), 278-295.
  116. Senderovich, A., Weidlich, M., Gal, A., Mandelbaum, A., Kadish, S., and Bun- nell, C. Discovery and validation of queueing networks in scheduled processes. In Advanced Information Systems Engineering (2015), Springer, pp. 417-433.
  117. Sharma, V., and Mazumdar, R. Estimating traffic parameters in queueing systems with local information. Performance Evaluation 32, 3 (1998), 217-230.
  118. Stanford, D., Pagurek, B., and Woodside, C. Optimal prediction of times and queue lengths in the GI/M/1 queue. Operations Research 31, 2 (1983), 322-337.
  119. Sutton, C., and Jordan, M. Bayesian inference for queueing networks and modeling of internet services. The Annals of Applied Statistics 5, 1 (2011), 254-282.
  120. Thiongane, M., Chan, W., and l'Ecuyer, P. New history-based delay predictors for service systems. In 2016 Winter Simulation Conference (WSC) (2016), IEEE, pp. 425-436.
  121. Thiruvaiyaru, D., and Basawa, I. Empirical Bayes estimation for queueing systems and networks. Queueing Systems 11, 3 (1992), 179-202.
  122. Thiruvaiyaru, D., Basawa, I., and Bhat, U. Estimation for a class of simple queueing networks. Queueing Systems 9, 3 (1991), 301-312.
  123. Van der Aalst, W., Weijters, T., and Maruster, L. Workflow mining: Discovering process models from event logs. IEEE transactions on knowledge and data engineering 16, 9 (2004), 1128-1142.
  124. Wang, W., and Casale, G. Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue Length Data. ACM SIGMETRICS Performance Evaluation Review 43, 2 (2015), 45-47.
  125. Wang, W., Casale, G., Kattepur, A., and Nambiar, M. Maximum likelihood estima- tion of closed queueing network demands from queue length data. In Proceedings of the 7th ACM/SPEC on International Conference on Performance Engineering (2016), pp. 3-14.
  126. Whitt, W. Predicting queueing delays. Management Science 45, 6 (1999), 870-888.
  127. Whitt, W. Stochastic-process limits: an introduction to stochastic-process limits and their application to queues. Springer Science & Business Media, 2002.
  128. Whitt, W. Fitting birth-and-death queueing models to data. Statistics and Probability Letters 82 (2012), 998-1004.
  129. Woodside, C., Stanford, D., and Pagurek, B. Optimal prediction of queue lengths and delays in G i /M/M multiserver queues. Operations research 32, 4 (1984), 809-817.
  130. Zhang, L., Xia, C., Squillante, M., and Mills, W. Workload service requirements analysis: A queueing network optimization approach. In Modeling, Analysis and Simulation of Computer and Telecommunications Systems, 2002. MASCOTS 2002. Proceedings. 10th IEEE International Symposium on (2002), IEEE, pp. 23-32.
  131. Zheng, S., and Seila, A. Some well-behaved estimators for the M/M/1 queue. Operations Research Letters 26, 5 (2000), 231-235.

Related papers

Parameter and State Estimation in Queues and Related
Azam Asanjarani

This is an annotated bibliography on estimation and inference results for queues and related stochastic models. The purpose of this document is to collect and categorise works in the field, allowing for researchers and practitioners to explore the various types of results that exist. This bibliography attempts to include all known works that satisfy both of these requirements: • Works that deal with queueing models. • Works that contain contributions related to methodology of parameter estimation, state estimation, hypothesis testing, confidence interval and/or actual data-sets of application areas. It also includes reference to selected additional related material in Section 8. There are additional works not mentioned in this bibliography that are mildly related. This includes methods for parameter estimation of point processes, methods for parameter estimation of stochastic matrix analytic models as well as inference, estimation and tomography of communication networks not directly modelled as queueing networks. Our attempt is to make this bibliography exhaustive, yet there are possibly some papers that we have missed. As it is updated continuously, additions and comments are welcomed. The sections below categorise the works based on several categories. A single paper may appear in several categories simultaneously. The final section lists all works in chronological order along with short descriptions of the contributions.

View PDFchevron_right
Parameter identification for queueing systems by means of the maximum likelihood method
Roman Safreider

This diploma thesis considers the problem of parameter estimation for time-continuous Markov processes on discrete state spaces. A Markov process is a mathematical model for the random evolution of a system of events over the time axis. The stochastic process has the Markov property, i.e. the likelihood of a given future state only depends on the present state and not on the past evolution of the process. Therefore, a Markov process is also called a memoryless process. These processes are very important for descriptions of natural phenomena in physics, the sciences and economics. If we consider the board game Monopoly, we can simulate the movement of a player's pawn using a Markov process. The discrete state space is the board consisting of forty spaces. The pawn's moves are determined entirely by dice rolls and by its starting points. It does not depend on how the pawn has reached the current state or even the previous moves. Therefore the movement process has the Markov property. Of course we exclude some of the 'community chest' states, which have a direct in uence on the pawn's movement, e.g. the card 'Go directly to jail, ...'. Furthermore, Markov processes are used in economics to model a great variety of di erent phenomena, as for example asset prices or market crashes. Another typical example is a random walk on the number line which starts at zero and transitions occur one step upward or downward with the same probability at each step. The position of the process in the following transitions only depends on the present position and not on the way the process has walked before it reached its present state. For example zero-sum games can be modeled with this process. Thereby it moves up at each win and down at each loose. Therefore, the present state represents the di erence of both wins and looses. Another extensive eld of applications is the queueing theory. Considering the length of a queue on a discrete state space, a Markov process allows us to model the stochastic behavior of a queue. The Markov property is immediately ensured since the next state of the queue length only depends on the present one. In contrast to the Monopoly example, this case is modeled by a continuous-time Markov process since events do not occur as before at each dice roll, but rather new customers could arrive at every single moment. This leads us to many other di erent examples: such as Birth-and-Death processes where the number of citizens is counted or customer lines in a supermarket. Furthermore, we could consider a queue of customers in a telephone system waiting for connection. Hereby, the telephone company is interested in lowering its running costs as well as in satisfying its customers. If the capacity is not big enough, it can happen in peak times that someone has to wait very long for a free line before getting connected. The queueing theory is able to give us an answer about over ows of the system as well as about the necessary number of connection lines to prevent such over ows. Another 7 8 Chapter 1. Introduction applied example is when the owner of a supermarket gets an instrument to identify the needed number of open cash desks to minimize waiting times for customers. In summary, queueing theory is mainly used to optimize the problems connected any sort of waiting lines. Now the question arises how these kinds of queueing systems can be modeled. Normally, we do not have exact information about the system and its parameters. Because of this, the classical queueing system has Poisson arrival processes with exponentially distributed inter arrival times as well as exponentially distributed service times, for instance with parameter  for the arrival process and for the service times. The size of the waiting room is variable but usually assumed to be countable and in nite. This kind of queueing system can be written in Kendall's notation as M=M=1=1 system where the rst and second M=Markovian stands for the mentioned arrival and service process, the 1 represents the number of service stations and the in nity symbol stands for the size of the waiting room. Since the parameters  and are unknown they must be estimated based on observation of the process, clearly, best results are obtained by continuous observation of the process. This would imply staying next to a supermarket's cash desk the whole time and recording all waiting line changes, including event times points. We would thereby not lose track of any events and would gain accurate information from the very beginning. This leads us to the question about how to use the information then: the maximum likelihood estimation of the parameters, which is simple and well-known, is normally used, see e.g. [2]Billingsley from 1961. Many others have investigated this kind of estimation since then and the main idea of the likelihood estimation has remained the same. Given an observation over a period of time we take those possible values for the parameters which would maximize the probability to get exactly that observation. Consequently, we need the transition probability functions. Since we assume the queue to t to a wellknown parametric model, for example the M=M=1=1 model, the distribution of both, the arrival and service processes, are known whereas only its corresponding parameters are to be estimated. Therefore, the theory of Markov processes and especially the queueing system theory give us the transition probabilities between the di erent states with respect to the parameters. With some stationarity conditions on the process and with knowledge of the right parameters, we could say for example how great the probability is for a special length of a queue at a random point of time. Maximum likelihood estimation of the parameters of the mentioned Birth-and-Death processes was rst studied by [10] Keiding in 1975. He showed how to estimate the birth and death intensities, if a continuous observation over a xed time interval of the process is available. Realistically speaking, however, a non-stop observation of a waiting line is rarely possible. In their work [7]Dehay & Yao considered the likelihood estimation for discretely observed Markov processes. This means that an observer comes back after a speci c period of time to count the length of the queue. They de ne this period of time to be xed and the process is therefore called equidistantly observed. The occurring observations are then called to be an observation chain. However, if a Markov process is only observed at discrete equidistant time points, the situation is 9 more complex. Whereas in the continuous observation case noted previously, we had accurate information without having missed any events, here, the case is di erent. It could happen that more customers arrive between two observation points and meanwhile the same amount of customers is being served at the front of the queue. Since we do not di erentiate between them in the queue, but only count the amount of the customers, we do not record any change of queueing length in that case. Nevertheless it is possible for Dehay and Yao to de ne a likelihood estimation function and to show some asymptotic properties for the maximum likelihood estimator in that case. The requirements for their theory are very clear. The process has to be a Markov process on a countable state space. Note: in this situation, it is possible to use an in nite state space. In addition the process is not allowed to have an in nite expected sojourn time at any state of queue. The intensity matrix Q must be conservative; this means that a process should have the same intensity to jump in and out of any state. Furthermore,

View PDFchevron_right
Parameter estimation for partially observed queues
Jean Walrand

IEEE Transactions on Communications, 1994

View PDFchevron_right
Estimating probability distributions of dynamic queues
Benjamin Heydecker

Transportation Planning and Technology, 2014

Queues are often associated with uncertainty or unreliability, which can arise from chance or climatic events, phase changes in system behaviour, or inherent randomness. Knowing the probability distribution of the number of customers in a queue is important for estimating the risk of stress or disruption to routine services and upstream blocking, potentially leading to exceeding critical limits, gridlock or incidents. The present paper focuses on time-varying queues produced by transient oversaturation during demand peaks where there is randomness in arrivals and service. The objective is to present practical methods for estimating a probability distribution from knowledge of the mean, variance and utilisation (degree of saturation) of a queue available from computationally efficient, if approximate, time-dependent calculation. This is made possible by a novel expression for time-dependent queue variance. The queue processes considered are those commonly used to represent isolated priority (M/M/1) and signal-like (M/D/1) systems, plus some statistical variations within the common Pollaczek-Khinchin framework. Results are verified by comparison with Markov simulation based on recurrence relations.

View PDFchevron_right
Probabilistic models for queues at fixed control signals
Francesco Viti

Transportation Research Part B: Methodological, 2010

The estimation of queues at signalized intersections is a classical problem in transportation engineering and operations research. Nevertheless, a general theory able to explain how queues form and cause delays to the drivers is still missing. Typically, queue dynamics are modelled as deterministic, causal phenomena, and under rather limiting assumptions; however, especially in urban networks, these are far from being deterministic or certain. This paper presents a new probabilistic queuing model that can explain the dynamic and stochastic behaviour of queues at fixed controlled signals. The probabilistic approach allows one to capture the temporal behaviour of queues, and to measure the uncertainty of a queue state prediction by computing the evolution of its probability in time, assumed any temporal distribution of the arrivals. This can be fundamental information in, e.g., travel time estimation, network reliability, design and planning of urban areas, and to estimate complex effects that can be observed in congested networks such as spillback or gridlock. Comparison with microscopic simulation shows very good consistency both under the assumption of stationary and non-stationary arrival distributions.

View PDFchevron_right

Related topics

  • Mathematics
  • Applied Mathematics
  • Computer Science
  • Statistics
  • Queueing theory
  • Numerical Analysis and Computati...

    • Cited by

    A survey of parameter and state estimation in queues
    Azam Asanjarani

    Queueing Systems, 2021

    We present a broad literature survey of parameter and state estimation for queueing systems. Our approach is based on various inference activities, queueing models, observations schemes, and statistical methods. We categorize these into branches of research that we call estimation paradigms. These include: the classical sampling approach, inverse problems, inference for noninteracting systems, inference with discrete sampling, inference with queueing fundamentals, queue inference engine problems, Bayesian approaches, online prediction, implicit models, and control, design, and uncertainty quantification. For each of these estimation paradigms, we outline the principles and ideas, while surveying key references. We also present various simple numerical experiments. In addition to some key references mentioned here, a periodically-updated comprehensive list of references dealing with parameter and state estimation of queues will be kept in an accompanying annotated bibliography.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved