A smart airspace sectorization approach based on spectral clustering and NSGA-II

Airspace sectorization is one of the most important issues in air traffic management, which can directly affect the ability of the air traffic system. Current airspace sectorization cannot meet the increasing demand of air traffic. To facilitate utilizing the airspace more efficiently, the method to design sectors of airspace needs to be updated. This paper proposes a smart sectorization approach which is based on spectral clustering and NSGA-II. The sectorization problem is a typical constrained multi-objective optimization problem with several constraints which can be hardly molded by mathematical formulas. With the method embedded in the constrained NSGA-II, all of the critical constraints such as sector convexity and minimum flight time in one sector can be easily handled. To facilitate the convergence of the evolving computation in NSGA-II, an initial sectorization method based on spectral clustering is proposed to generate the first generation of NSGA-II. We test our method on the high-altitude airspace controlled by Beijing Area Control Center. The results show that our method can obtain better solutions with less number of sectors, no constraint violation and more reasonable workload allocation.