A Distributionally Robust Optimization Framework for Ambulance Location and Dispatching under Travel Time Uncertainty
Efficient Emergency Medical Services management involves complex decision-making problems. We propose a Distributionally Robust Optimization framework for the integrated ambulance location and dispatching problem, explicitly accounting for uncertainty in ambulance travel times, a key factor that is often neglected in the EMS optimization literature. The approach models ambiguity sets, providing protection against worst-case scenarios while avoiding the excessive conservatism of traditional robust optimization. Several variants are developed and evaluated through in-sample and out-of-sample experiments using historical data from the Basque Country. In addition, a Discrete Event Simulation model is used to assess the operational performance under realistic spatio-temporal demand patterns. The results show that DRO-based solutions offer a well-balanced trade-off between robustness and efficiency, highlighting their methodological and practical value for healthcare operations management.
Palabras clave: OR in health services Stochastic programming Robust optimization Distributionally robust optimization Location