Learning Deep Generative Models for Queuing Systems

Authors

  • Cesar Ojeda Berlin Center for Machine Learning TU Berlin
  • Kostadin Cvejoski Competence Center Machine Learning Rhine-Ruhr Fraunhofer Center for Machine Learning Fraunhofer IAIS
  • Bodgan Georgiev Competence Center Machine Learning Rhine-Ruhr Fraunhofer Center for Machine Learning Fraunhofer IAIS
  • Christian Bauckhage Competence Center Machine Learning Rhine-Ruhr Fraunhofer Center for Machine Learning Fraunhofer IAIS
  • Jannis Schuecker Bayer AG
  • Ramses J. Sanchez Competence Center Machine Learning Rhine-Ruhr B-IT University of Bonn

Keywords:

(Deep) Neural Network Algorithms

Abstract

Modern society is heavily dependent on large scale client-server systems with applications ranging from Internet and Communication Services to sophisticated logistics and deployment of goods. To maintain and improve such a system, a careful study of client and server dynamics is needed – e.g. response/service times, aver-age number of clients at given times, etc. To this end, one traditionally relies, within the queuing theory formalism,on parametric analysis and explicit distribution forms.However, parametric forms limit the model’s expressiveness and could struggle on extensively large datasets. We propose a novel data-driven approach towards queuing systems: the Deep Generative Service Times. Our methodology delivers a flexible and scalable model for service and response times. We leverage the representation capabilities of Recurrent Marked Point Processes for the temporal dynamics of clients, as well as Wasserstein Generative Adversarial Network techniques, to learn deep generative models which are able to represent complex conditional service time distributions. We provide extensive experimental analysis on both empirical and synthetic datasets, showing the effectiveness of the proposed models

Downloads

Published

2021-05-18

How to Cite

Ojeda, C., Cvejoski, K., Georgiev, B., Bauckhage, C., Schuecker, J., & Sanchez, R. J. (2021). Learning Deep Generative Models for Queuing Systems. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 9214-9222. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17112

Issue

Section

AAAI Technical Track on Machine Learning III