Deep Learning for Optimal Deployment of UAVs with Visible Light Communications

In this paper, the problem of optimizing the deployment of unmanned aerial vehicles (UAVs) equipped with visible light communication (VLC) capabilities is studied. In the studied model, the UAVs can predict the illumination distribution of a given service area and determine the user association with the UAVs to simultaneously provide communications and illumination. However, ambient illumination increases the interference over VLC links while reducing the illumination threshold of the UAVs. Therefore, it is necessary to consider the illumination distribution of the target area for UAV deployment optimization. This problem is formulated as an optimization problem, which jointly optimizes UAV deployment, user association, and power efficiency while meeting the illumination and communication requirements of users. To solve this problem, an algorithm that combines the machine learning framework of gated recurrent units (GRUs) with convolutional neural networks (CNNs) is proposed. Using GRUs and CNNs, the UAVs can model the long-term historical illumination distribution and predict the future illumination distribution. Based on the prediction of illumination distribution, the optimization problem becomes nonconvex and is then solved using a low-complexity, iterative physical relaxation algorithm. The proposed algorithm can find the optimal UAV deployment and user association to minimize the total transmit power. Simulation results using real data from the Earth observations group (EOG) at NOAA/NCEI show that the proposed approach can achieve up to 64.6% reduction in total transmit power compared to a conventional optimal UAV deployment that does not consider the illumination distribution and user association. The results also show that UAVs must hover at areas having strong illumination, thus providing useful guidelines on the deployment of VLC-enabled UAVs.