Data-Driven Planning for Ground Delay Programs

This paper provides a model-based approach to planning ground delay programs. Previous research on automated planning of ground delay programs has involved the use of mathematical programming techniques. This paper proposes a data-driven method that models the problem of choosing a traffic management initiative by using the framework of the multiarmed bandit decision problem. This approach makes greater use of the available data, and suggestions made by this procedure can be shown along with data that informed the decision. This combination of tools allows decision makers to more easily evaluate suggested decisions. The paper also provides simulations of the procedure on the basis of data from Newark (New Jersey) International Airport to evaluate its effectiveness.