Air Holding Problem Module to Decision Support in Air Traffic Flow Management

摘要

Air Traffic Management (ATM) has the objective to guarantee that the aircraft operators meet the scheduled time of departure and arrival to maintain optimal flight profiles with minimum constraints. This paper describes a solution of Air Holding Problem (AHP) of ATM in Brazil using Multiagent System to improve Reinforcement Learning in collaboration with the flight controllers to support the decision process. The results obtained in the case study are promising, the behavior of the prototypes demonstrated that the Q-learning algorithm converged in a satisfying way. The prototypes generated actions that contributed effectively to the reduction of saturation in the air traffic scenarios under test.