Reinforcement Learning-Based Multi-UAV Coverage Optimization

Sudden disasters such as earthquakes can lead to the destruction of communication infrastructure. As one of the key tools for rapid response, drone relay networks can provide basic communication capabilities to disaster-stricken areas. However, the limited energy and coverage range of UAVs constrain the network's operating time and communication performance. This paper proposes a deep reinforcement learning method based on Proximal Policy Optimization (PPO), which maximizes service provision to more users under the constraint of limited energy. Numerical simulation results demonstrate that the proposed algorithm significantly outperforms similar algorithms, showing strong practical application value.