Federated Deep Reinforcement Learning for Joint Coverage and Connectivity in Cooperative UAV Networks for Emergency Communications

In disaster-affected areas where conventional communication infrastructure is severely damaged, unmanned aerial vehicles (UAVs) can serve as critical aerial platforms for providing emergency coverage to ground points of interest (PoIs). However, cooperative UAV deployment for area coverage poses several challenges, including energy-constrained trajectory planning, maintenance of reliable communication connectivity for data relaying, prevention of inter-UAV collisions, and maximization of coverage efficiency. In this paper, we propose FedJCC, a federated deep reinforcement learning framework for joint coverage and connectivity optimization in cooperative UAV networks for emergency communications. The problem is formulated as a constrained Markov decision process (MDP), and a hierarchical UAV architecture is adopted, in which cluster heads maintain communication relaying while cluster members provide ground coverage. To enable collision-free navigation, a virtual forcebased collision avoidance mechanism derived from the improved adaptive artificial potential field (IAAPF) method is incorporated into the framework. FedJCC is built on a dueling double deep Q-network (D3QN) with prioritized experience replay, where each UAV is trained locally and model parameters are periodically aggregated through federated averaging. In addition, a dynamic deployment adjustment mechanism is introduced to reduce the number of active UAVs while preserving coverage performance. Simulation results show that FedJCC achieves a coverage ratio of 98.8%, substantially outperforming state-of-the-art combinatorial optimization baselines. The results further demonstrate that FedJCC surpasses existing baseline algorithms in terms of packet delivery ratio and average end-to-end delay across different scenarios. Finally, the coverage-connectivity tradeoff analysis confirms that FedJCC operates closest to the ideal region in which both objectives are jointly maximized, thereby validating the effectiveness of the proposed framework for disaster response applications.