Deep Reinforcement Learning-Based Full-Duplex Communication UAV Base Station Trajectory Optimization in Disaster Environments

Unmanned aerial vehicles (UAVs) are widely used in various fields due to their fast mobility and flexible deployment capabilities. While previous research focused on using UAVs as relays, recent studies have explored the use of UAVs as base stations (UAV-BS) to overcome the limitations of ground-base stations. Particularly, in disaster environments where traditional ground-base stations are unavailable, the utilization of UAV-BS has gained significant attention for overcoming critical communication challenges. Moreover, research on full-duplex (FD) communication, which enhances frequency efficiency to serve a larger number of nodes in disaster environments, has been actively pursued. However, the availability of FD communication between node pairs can vary depending on the position of the UAV-BS when it is used. In this paper, we propose a deep reinforcement learning (DRL)-based approach to optimize the trajectory of UAV-BS for efficient FD communication in disaster environments. Our experimental results demonstrate that the proposed algorithm outperforms other existing algorithms, achieving more efficient FD communication within the given time constraints.