Optimizing Urban UAV Delivery Networks with Improved K-Means: Insights from Shiyan City

This study addresses the logistical challenges of urban unmanned aerial vehicle (UAV) delivery systems by proposing an enhanced K-Means clustering algorithm tailored for delivery area division. Integrating UAV-specific constraints, such as battery life, payload limits, and dynamic delivery demands, the algorithm optimizes flight distance, energy efficiency, and cluster workload balance. Comprehensive simulations using data from Shiyan City validate the algorithm ’ s effectiveness, demonstrating significant improvements over traditional methods. The findings offer a scalable framework for integrating UAVs into urban logistics networks and provide actionable insights for optimizing UAV operations under real-world conditions. This research also highlights future directions, including incorporating real-time data streams and advanced UAV technologies to enhance logistics adaptability and efficiency.