Abstract
We employ Mixture Density Networks (MDNs) as a general approach for estimation of customer waiting times in queueing systems based on system states that customers observe upon their arrival. We generate a large amount of data by using discrete-event simulation. Part of the generated dataset is used to train the model, and we utilize the whole dataset for the evaluation of the model. Finally, we illustrate this application in a real-world dataset.
Supported by JSPS KAKENHI Grant Number 18K18006 and 21K11765.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Deep learning for siri’s voice: on-device deep mixture density networks for hybrid unit selection synthesis. https://machinelearning.apple.com/research/siri-voices. Accessed 25 Aug 2021
Bishop, C.M.: Mixture density networks. Department of Computer Science and Applied Mathematics, Aston University, UK, Technical report (1994)
Bishop, S.A., Okagbue, H.I., Oguntunde, P.E., Opanuga, A.A., Odetunmibi, O.A.: Survey dataset on analysis of queues in some selected banks in Ogun state, Nigeria. Data Brief 19, 835–841 (2018)
Demir, E., Demir, V.B.: Predicting flight delays with artificial neural networks: case study of an airport. In: 2017 25th Signal Processing and Communications Applications Conference (SIU), pp. 1–4 (2017)
Edelson, N.M., Hildebrand, K.: Congestion tolls for Poisson queueing processes. Econometrica 43(1), 81–92 (1975)
Gneiting, T., Raftery, A.E.: Strictly proper scoring rules, prediction, and estimation. J. Am. Stat. Assoc. 102(477), 359–378 (2007)
Gomes, D., Nabil, R.H., Nur, K.: Banking queue waiting time prediction based on predicted service time using support vector regression. In: 2020 International Conference on Computation, Automation and Knowledge Management (ICCAKM), pp. 145–149 (2020)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)
Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. arXiv preprint arXiv:1809.01999 (2018)
Ibrahim, R., Whitt, W.: Real-time delay estimation based on delay history. Manuf. Serv. Oper. Manag. 1(3), 397–415 (2009)
Ibrahim, R., Whitt, W.: Wait-time predictors for customer service systems with time-varying demand and capacity 59(5), 1106–1118 (2011)
Jouini, O., Dallery, Y., Akşin, Z.: Queueing models for full-flexible multi-class call centers with real-time anticipated delays. Int. J. Prod. Econ. 120(2), 389–399 (2009). Special Issue on Introduction to Design and Analysis of Production Systems
Maister, D.: The psychology of waiting lines. In: Czepiel, J., Solomon, M.R., Surprenant, C.F. (eds.) The Service encounter: managing employee/customer interaction in service businesses. D. C. Heath and Company, Lexington Books, Lexington (1985)
Makansi, O., Ilg, E., Cicek, O., Brox, T.: Overcoming limitations of mixture density networks: a sampling and fitting framework for multimodal future prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7144–7153 (2019)
Morozov, E.V., Rogozin, S.S., Nguyen, H.Q., Phung-Duc, T.: Modified erlang loss system for cognitive wireless networks (2021). https://arxiv.org/abs/2103.03222, to appear in Journal of Mathematical Sciences
Naor, P.: The regulation of queue size by levying tolls. Econometrica 37(1), 15–24 (1969)
Raeis, M., Tizghadam, A., Leon-Garcia, A.: Predicting distributions of waiting times in customer service systems using mixture density networks. In: 2019 15th International Conference on Network and Service Management (CNSM), pp. 1–6 (2019)
Senderovich, A., Weidlich, M., Gal, A., Mandelbaum, A., et al.: Queue mining – predicting delays in service processes. In: Jarke, M. (ed.) CAiSE 2014. LNCS, vol. 8484, pp. 42–57. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07881-6_4
Whitt, W.: Predicting queueing delays. Manag. Sci. 45(6), 870–888 (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, H.Q., Phung-Duc, T. (2021). Mixture Density Networks as a General Framework for Estimation and Prediction of Waiting Time Distributions in Queueing Systems. In: Ballarini, P., Castel, H., Dimitriou, I., Iacono, M., Phung-Duc, T., Walraevens, J. (eds) Performance Engineering and Stochastic Modeling. EPEW ASMTA 2021 2021. Lecture Notes in Computer Science(), vol 13104. Springer, Cham. https://doi.org/10.1007/978-3-030-91825-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-91825-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91824-8
Online ISBN: 978-3-030-91825-5
eBook Packages: Computer ScienceComputer Science (R0)