Research on A Machine-Learning Based Scheduling Algorithm for Air Traffic Controllers

Abstract

Workload of air traffic controllers has increased over the years owing to the rapid development of civil aviation. To enhance the security control of air traffic, a more reasonable scheduling method needs to be put in place to ensure enough rest break for air traffic controllers. This paper has first reviewed previous worldwide studies on linkages between scheduling method and controller workload. It then discusses scheduling methods used in current air traffic facilities and their potential drawbacks. As a potential response to these drawbacks, a machine-learning based scheduling algorithm is proposed by the paper, along with a comparative verification to prove its feasibility and practicality.