Comparing Metaheuristic Optimization Algorithms for Ambulance Allocation: An Experimental Simulation Study

Conference paper at GECCO ‘23: Genetic and Evolutionary Computation Conference


The optimization of Emergency Medical Services is a central issue in modern healthcare systems. With this in focus, we study a data set containing medical emergencies for the years 2015–2019 from Oslo and Akershus, Norway. By developing a discrete trace-based simulation model based on the data set, we compute average response times that are used to optimize ambulance allocations to stations in the region. We study several metaheuristics, specifically genetic, stochastic local search, and memetic algorithms. These metaheuristics are tested using the simulation to optimize ambulance allocations, considering response times. The algorithms are compared against each other and a set of baseline allocation models over different time periods. The main results of our experimental simulation study are that: (i) the metaheuristics generally outperform the simpler baselines, (ii) the best-performing metaheuristic is the genetic algorithm, and (iii) the performance difference between the metaheuristics and the simpler baselines increases in situations with high demand on ambulances. Finally, we present suggestions for future work that may help to further improve upon the current state-of-the-art.

GECCO ‘23: Proceedings of the Genetic and Evolutionary Computation ConferenceJuly 2023. pp. 1454–1463
Xavier F. C. Sánchez Díaz
Xavier F. C. Sánchez Díaz
PhD candidate in Artificial Intelligence

PhD candidate in Artificial Intelligence at the Department of Computer Science (IDI) of the Norwegian University of Science and Technology