A multi-fidelity modelling approach for airline disruption management using simulation

Disruption is a serious and common problem for the airline industry. High utilisation of aircraft airport resources mean that disruptive events can have large knock-on effects rest schedule. The must rearrange their schedule to reduce impact. focus in this paper on Aircraft Recovery Problem. complexity uncertainty involved industry makes difficult solve. Many deterministic modelling approaches been proposed, but these struggle handle inherent variability problem. This proposes multi-fidelity framework, enabling uncertain elements environment be included within decision making process. We combine integer program find initial solutions novel simulation optimisation procedure improve solutions. allows evaluated whilst accounting empirical evaluation suggests combination consistently finds good rescheduling options.