UAV assisted cellular network traffic offloading: Joint swarm, 3D deployment, and user allocation optimization based on a data-aware method

Unmanned Aerial Vehicles (UAVs) have become popular carriers of aerial Base Stations (BSs) to cover temporal hotspots and off-load the transmission requirements of mobile users. Although the UAV-BSs can ignore the terrestrial obstacles, using them to fast deploy for off-loading still faces the time-efficiency problem of jointly optimizing multi-objectives: such as the amount of UAV-BS swarm, 3D deployment locations, and allocating users. This work transforms the above joint optimization problem into a combinatorial problem and proposes data-driven heuristic solutions with both time efficiency and robustness. To alleviate the pressure of collecting data, this paper offers a generative neural network-based framework. Results show that the proposed data-aware method can well address the above problem with less computation iterations compared with benchmark methods.