Multi-objective optimization approach for air traffic flow management

Overview & Synopsis

Air traffic has long been a generally high growth sector and all forecasts indicate that this trend will continue at a similar pace for the next twenty years. The regular traffic demand growth has led to congestion at airports and in space. In this paper, we will create in first a probabilistic model which describes the uncertainty of the aircraft's tra-jectory, and its presence in a sector during a time interval. We define as result, a multi-objective optimization problem whose objective functions are the expected cost of delay and the expected cost of congestion. Then we use the Non-dominated Sorting Genetic Algorithm (NSGA-II) to solve an instance included 21 flights and 1 sector, and is able to provide a good approximation of the Pareto front. The decision-making stage was then performed with the aid of data clustering techniques to reduce the size of the Pareto-optimal set and obtain a smaller representation of the multi-objective design space, thereby making it easier for the decision-maker to find satisfactory and meaningful trade-offs, and to select a preferred final design solution.