CONSTRAINED RANKING AND SELECTION FOR OPERATIONS OF AN EMERGENCY DEPARTMENT

We consider a problem of finding the optimal number of medical staffs for an emergency department through stochastic simulation. Specifically, the objective is to maximize the expected net profit per period of the emergency department while confining the maximum duration of expected waiting times of critical and noncritical patients. This is formulated as a simulation optimisation problem with two stochastic constraints on waiting times. To find the optimal solution of the problem under statistical guarantees, we introduce a two-step fully sequential ranking and selection framework: we first determine a set of strictly feasible solutions and then select the best solution among them. We implement the proposed framework via Simio and apply it to an emergency department of a university hospital.