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 clients’ and servers’ dynamics is needed — e.g. response/service times, average 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 queueing systems: the Recurrent Adversarial 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 the rich distributional forms of adversarial neural networks. We provide extensive experimental analysis on both empirical and synthetic datasets, showing the effectiveness of the proposed models.