基于监督学习的 RIS 辅助通信稀疏信道估计
信号处理
2022-02-25 v1
摘要
当直射路径受阻时（这在毫米波（mmWave）网络中很常见），可重构智能表面（RIS）可用于建立视距（LoS）通信。本文关注该网络的上行信道估计问题。我们通过离散化基站（BS）处的到达角（AoAs），将此问题建模为稀疏信号恢复问题。网格内与网格外 AoAs 被分别考虑。在网格内情形下，我们提出一种算法来估计直射与 RIS 信道。在网格外情形下，基于监督学习训练的神经网络用于估计残差角度，以及两种情形下的 AoAs。数值结果表明所提算法在两种情形下均具有性能增益。
引用
@article{arxiv.2202.11997,
title = {Supervised Learning based Sparse Channel Estimation for RIS aided Communications},
author = {Dilin Dampahalage and K. B. Shashika Manosha and Nandana Rajatheva and Matti Latva-aho},
journal= {arXiv preprint arXiv:2202.11997},
year = {2022}
}
备注
\c{opyright} 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works