Hybrid Approach for Airspace Sectorization Based on K-Means Clustering and Genetic Algorithm Optimization

This paper presents a genetic optimization approach for airspace sectorization that combines K-means clustering and a genetic algorithm (GA). The algorithm minimizes the operating costs related to airspace complexities, unbalanced workloads, and inter-sector coordination requirements while respecting geometric constraints such as minimum distance, convexity, and connectivity. The algorithm initiates sectorization solutions using K-means clustering and then iteratively refines them using GA operations. A comparative analysis was conducted on ten tests, assigning various weights to cost components. The hybrid approach was tested using air traffic data over a one-hour period. The study evaluated the optimal, worst, and average fitness scores by adjusting the weights' importance orders and comparing the results to the current state-of-the-art method. The results demonstrate that GA with a smaller weighting yields optimum operating costs, highlighting the efficiency of the hybrid approach in resolving the airspace sectorization problem while adhering to geometric constraints.