Robust heavy-traffic approximations for service systems facing overdispersed demand

Arrival processes to service systems are prevalently assumed non-homogeneous Poisson. Though mathematically convenient, arrival processes are often more volatile, a phenomenon that is referred to as overdispersion. Motivated by this, we analyze a class of stochastic models for which we develop performance approximations that are scalable in the system size, under a heavy-traffic condition. Subsequently, we show how this leads to novel capacity sizing rules that acknowledge the presence of overdispersion. This, in turn, leads to robust approximations for performance characteristics of systems that are of moderate size and/or may not operate in heavy traffic. To illustrate the value of our approach, we apply it to actual arrival data of an emergency department of a hospital.