Recurrent Adversarial Service Times
This work addresses the problem of modeling service system dynamics more flexibly for researchers and practitioners in fields like internet services and mobility, though it appears incremental as it adapts existing neural network techniques to a specific domain.
The paper tackled the limitations of parametric assumptions in queuing theory by proposing a deep neural network solution that combines a recurrent neural network for arrival processes with a recurrent generative adversarial network for service time distributions, evaluated on empirical datasets including Blockchain, GitHub, Stackoverflow, and New York taxi cab systems.
Service system dynamics occur at the interplay between customer behaviour and a service provider's response. This kind of dynamics can effectively be modeled within the framework of queuing theory where customers' arrivals are described by point process models. However, these approaches are limited by parametric assumptions as to, for example, inter-event time distributions. In this paper, we address these limitations and propose a novel, deep neural network solution to the queuing problem. Our solution combines a recurrent neural network that models the arrival process with a recurrent generative adversarial network which models the service time distribution. We evaluate our methodology on various empirical datasets ranging from internet services (Blockchain, GitHub, Stackoverflow) to mobility service systems (New York taxi cab).