论文标题
非常大规模阵列通信的近场渠道估计：一种基于模型的深度学习方法
Near-Field Channel Estimation for Extremely Large-Scale Array Communications: A model-based deep learning approach
论文作者
论文摘要
非常大规模的大规模MIMO（XL-MIMO）已被审查为未来无线通信的有前途的技术。 XL-MIMO的部署，尤其是在高频乐队中，导致用户位于近场区域而不是传统的远场。这封信提出了有效的基于模型的深度学习算法，用于估计XL-MIMO通信的近场无线通道。特别是，我们首先使用基于空间网格的稀疏字典来将XL-MIMO近场通道估计任务作为压缩感测问题，然后通过应用学习迭代的收缩和阈值算法（ListA）来解决所得问题。由于近场特征，基于空间网格的稀疏字典可能会导致频道估计的准确性低和沉重的计算负担。为了解决这个问题，我们进一步提出了一种新的稀疏字典学习lista（SDL-LISTA）算法，该算法将稀疏字典作为神经网络层提出，并将其嵌入Lista神经网络中。数值结果表明，我们提出的算法优于非学习基准方案，而SDL-Lista的性能比降低原子的十倍更好。
Extremely large-scale massive MIMO (XL-MIMO) has been reviewed as a promising technology for future wireless communications. The deployment of XL-MIMO, especially at high-frequency bands, leads to users being located in the near-field region instead of the conventional far-field. This letter proposes efficient model-based deep learning algorithms for estimating the near-field wireless channel of XL-MIMO communications. In particular, we first formulate the XL-MIMO near-field channel estimation task as a compressed sensing problem using the spatial gridding-based sparsifying dictionary, and then solve the resulting problem by applying the Learning Iterative Shrinkage and Thresholding Algorithm (LISTA). Due to the near-field characteristic, the spatial gridding-based sparsifying dictionary may result in low channel estimation accuracy and a heavy computational burden. To address this issue, we further propose a new sparsifying dictionary learning-LISTA (SDL-LISTA) algorithm that formulates the sparsifying dictionary as a neural network layer and embeds it into LISTA neural network. The numerical results show that our proposed algorithms outperform non-learning benchmark schemes, and SDL-LISTA achieves better performance than LISTA with ten times atoms reduction.
