Key points are not available for this paper at this time.
In recent trend, unmanned aerial vehicles (UAVs) have become irreplaceable performer in enhancing mobile networks performance. Its flexibility and mobility features reinforce its existence in modern wireless communication networks as a dynamic base station (BS) to provide good wireless connectivity for mobile networks. Noting that, positioning of UAV plays an important role in achieving optimal performance for wireless communication networks. In this paper, we consider implementing a system model consisting of unmanned aerial vehicle (UAV) as a dynamic base station aided (NOMA) communication system to maximize the proposed system achievable sum rate. To optimize the position of UAV, we introduced a reinforcement learning (RL) based settle by modeling the UAV position optimization problem as a multi-armed bandit (MAB) problem. The interference and power limitations are constraints considered in the proposed formulated problem. The proposed simulation results show the effectiveness of the proposed MAB algorithm in solving the proposed UAV position optimization problem.
Elsayed et al. (Tue,) studied this question.