Data-Driven Arrival Trajectory Optimization Model Based on Improved Genetic Algorithm

Trajectory optimization is essential for realizing trajectory-based operation and has become a hot topic in air traffic management research in recent years. Although existing optimization models have significantly succeeded in their applications, most still need controllers to intervene during rush hours. To further improve the trajectory optimization performance, this paper proposed a data-driven-based trajectory optimization model that learns human controllers’ experience from historical data and embeds this knowledge into the trajectory optimization model to enhance its performance. Case studies at Guangzhou Baiyun International Airport are conducted to validate the proposed model. Compared with a conventional genetic-algorithm-based trajectory optimization model, the proposed approach—by incorporating real historical trajectory data—demonstrates significantly improved performance in managing arrival flows during peak hours, increasing airspace capacity by approximately 30% under trajectory-based operation conditions. Besides, the optimized trajectories embedded with more actual operation experience are familiar to controllers and pilots; therefore, the airspace user training cost would be relatively low.