Optimizing Dynamic Deployment of UAV Base Stations: A Digital Twin Approach

Unmanned aerial vehicle base station (UAV-BS) communication networks are considered as a promising solution for temporarily recovering urban telecommunication services interrupted by natural disasters. However, the deployment of UAV-BSs remains a challenge in disaster scenarios where terrestrial base stations may be unavailable, and users' locations (mobility in 3D, both on the ground and in the building) and requirements are constantly changing over time. In this paper, we propose a new digital twin (DT) framework to dynamically optimize UAV-BSs deployment in terms of both quantity and location while ensuring guaranteed network quality of service (QoS) and satisfied user requirements. It leverages a graph neural network (GNN) with new random walk for network modeling, a convolutional neural network (CNN) with online learning for QoS prediction, and deep reinforcement learning (DRL) models for optimizing UAV-BSs quantity and location. These three computing paradigms work collaboratively to respond to the evolving disaster context in an adaptive manner, improving UAV-BSs deployment subject to dynamic user requirements and mobility. Simulation results confirm the DT framework's effectiveness in optimizing UAV-BSs deployment in disaster scenarios.