Neural-Guided Adaptive Clustering for UAV-Based User Grouping in 5G/6G Post-Disaster Networks

In post-disaster scenarios, Unmanned Aerial Vehicles (UAVs) acting as Mobile Aerial Base Stations (MABSs) offer a flexible means of restoring communication for isolated user equipment (UE) when conventional infrastructure is unavailable. Clustering of UEs is central to UAV path planning, yet static algorithms such as Affinity Propagation Clustering (APC) often fail to generalise across diverse disaster environments and user densities. This study introduces a hybrid clustering framework that dynamically selects between APC and density-based clustering (DBSCAN), guided by a neural classifier trained on spatial UE distribution features. The chosen centroids then seed a Genetic Algorithm (GA) that evolves UAV trajectories under multiple performance indicators, including coverage, capacity, and path efficiency. Simulation results demonstrate that the hybrid clustering approach improves the adaptability and effectiveness of UAV deployments by learning context-aware clustering strategies. Compared with fixed APC-based planning, the proposed method achieves higher service ratios and more efficient UAV paths across heterogeneous disaster scenarios, validating intelligent clustering selection as a key enabler for real-time UAV-assisted communication restoration.