Transparent flying relay stations (FlyRSs), represented by transparent relays mounted on unmanned aerial vehicles (UAVs), have the potential to improve cellular network’s capacity and coverage at little extra complexity and energy cost, especially when compared with non-transparent relays. As the transparent relays do not transmit reference signals, they do not lend themselves easily to channel estimation. This makes solving the problems of user association and positioning of transparent FlyRSs much harder. We propose a solution enabling an efficient association of users to the FlyRSs and determining suitable positions of the FlyRSs. Surprisingly, this can be done knowing neither the qualities of the channels linking the FlyRSs and the users nor the users’ location information. Our approach involves the users being grouped into clusters based on the channels to nearby static base stations via agglomerative hierarchical clustering. Then, 3D positions of one FlyRS per cluster are determined by deep neural networks. The proposal improves the users’ sum capacity with respect to existing solutions that rely on the knowledge of users’ positions.

中文翻译：

---

透明飞行中继站定位与关联规则

以安装在无人驾驶飞行器 (UAV) 上的透明中继为代表的透明飞行中继站 (FlyRS) 具有提高蜂窝网络的容量和覆盖范围的潜力，而不会增加额外的复杂性和能源成本，尤其是与非透明中继相比时。由于透明中继不传输参考信号，因此它们不容易用于信道估计。这使得解决透明 FlyRS 的用户关联和定位问题变得更加困难。我们提出了一种解决方案，能够将用户与 FlyRS 有效关联并确定 FlyRS 的合适位置。令人惊讶的是，这可以在既不知道连接 FlyRS 和用户的信道质量也不知道用户位置信息的情况下完成。我们的方法涉及通过凝聚层次聚类基于到附近静态基站的信道将用户分组到集群中。然后，每个集群一个 FlyRS 的 3D 位置由深度神经网络确定。相对于依赖于用户位置知识的现有解决方案，该提议提高了用户的总和能力。