Reinforcement Learning based Sum Rate Maximization for UAV-Assisted NOMA System

Unmanned aerial vehicles (UAVs) have emerged as indispensable assets in modern mobile networks. Their ability to provide flexible and dynamic wireless connectivity has opened up new possibilities for various applications, including disaster management, surveillance, and remote sensing. However, the positioning of UAVs in such systems plays a critical role in achieving optimal performance. In this paper, we propose a reinforcement learning (RL) approach to optimize the position of the UAV in order to maximize the sum rate of a non-orthogonal multiple access (NOMA) system using real-time measurements. The formulated problem considers various constraints such as interference and power limitations. Simulation results show the effectiveness of the proposed algorithm.