To boost the performance of wireless communication networks, unmanned aerial vehicles (UAVs) aided communications have drawn dramatically attention due to their flexibility in establishing the line of sight (LoS) communications. However, with the blockage in the complex urban environment, and due to the movement of UAVs and mobile users, the directional paths can be occasionally blocked by trees and high-rise buildings. Intelligent reflection surfaces (IRSs) that can reflect signals to generate virtual LoS paths are capable of providing stable communications and serving wider coverage. This is the first paper that exploits a three-dimensional geometry dynamic channel model in IRS- assisted UAV-enabled communication system. Moreover, we develop a novel deep learning based channel tracking algorithm consisting of two modules: channel pre-estimation and channel tracking. A deep neural network with off-line training is designed for denoising in the pre-estimation module. Moreover, for channel tracking, a stacked bi-directional long short term memory (Stacked Bi-LSTM) is developed based on a framework that can trace back historical time sequence together with bidirectional structure over multiple stacked layers. Simulations have shown that the proposed channel tracking algorithm requires fewer epochs to convergence compared to benchmark algorithms. It also demonstrates that the proposed algorithm is superior to different benchmarks with small pilot overheads and comparable computation complexity.

中文翻译：

---

IRS 辅助无人机通信系统中通道跟踪的深度学习


为了提高无线通信网络的性能，无人机（UAV）辅助通信因其在建立视距（LoS）通信方面的灵活性而引起了极大的关注。然而，随着复杂城市环境的堵塞，由于无人机和移动用户的移动，定向路径偶尔会被树木和高层建筑遮挡。智能反射面（IRS）可以反射信号并生成虚拟视距路径，能够提供稳定的通信并提供更广泛的覆盖范围。这是第一篇在 IRS 辅助无人机通信系统中利用三维几何动态信道模型的论文。此外，我们开发了一种新颖的基于深度学习的信道跟踪算法，由两个模块组成：信道预估计和信道跟踪。设计了具有离线训练的深度神经网络，用于预估计模块中的去噪。此外，对于通道跟踪，基于可以追溯历史时间序列的框架开发了堆叠式双向长短期记忆（Stacked Bi-LSTM）以及多个堆叠层上的双向结构。仿真表明，与基准算法相比，所提出的信道跟踪算法需要更少的收敛时间。它还表明，所提出的算法优于不同的基准，具有较小的导频开销和相当的计算复杂度。