Strategic Planning in Air Traffic Control as a Multi-objective Stochastic Optimization Problem

TL;DR

This paper introduces a multi-objective stochastic optimization approach using NSGA-II to create strategic air traffic control plans that balance sector congestion and regulatory compliance, accounting for trajectory uncertainties.

Contribution

It presents a novel decision support tool that models trajectory uncertainty and optimizes sector congestion and regulations simultaneously using a genetic algorithm.

Findings

Effective approximation of Pareto front for 24 aircraft and 11 sectors

Demonstrates the model's ability to balance congestion and regulation trade-offs

Provides a set of alternative strategic plans for air traffic controllers

Abstract

With the objective of handling the airspace sector congestion subject to continuously growing air traffic, we suggest to create a collaborative working plan during the strategic phase of air traffic control. The plan obtained via a new decision support tool presented in this article consists in a schedule for controllers, which specifies time of overflight on the different waypoints of the flight plans. In order to do it, we believe that the decision-support tool shall model directly the uncertainty at a trajectory level in order to propagate the uncertainty to the sector level. Then, the probability of congestion for any sector in the airspace can be computed. Since air traffic regulations and sector congestion are antagonist, we designed and implemented a multi-objective optimization algorithm for determining the best trade-off between these two criteria. The solution comes up as a set of alternatives for the multi-sector planner where the severity of the congestion cost is adjustable. In this paper, the Non-dominated Sorting Genetic Algorithm (NSGA-II) was used to solve an artificial benchmark problem involving 24 aircraft and 11 sectors, and is able to provide a good approximation of the Pareto front.