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.
翻译:将XL-MIMO(XL-MIMO)的部署,特别是高频波段的部署,导致用户位于近地地区,而不是传统的远地。本信提出了基于模型的高效深学习算法,用于估计XL-MIMO通信的近地无线频道。特别是,我们首先利用基于空间网格的扩增字典,将XL-MIMO(SDL-LISTA)的估算任务作为压缩的感测问题,然后通过应用学习透析和缓冲 Algorithm(LISTA)来解决由此产生的问题。由于近地特征,基于空间网格的扩增字典可能会导致低频道估计精度和沉重的计算负担。为了解决这个问题,我们进一步提出一个新的将词典学习-LISTA(SDL-LISTA)(SDL-LISTA)算法算法,该算法将字典编成一个神经网络层,并将其嵌入STRA 神经网络网络。由于近地特征特征特征特征特征,因此,SDLA ASLA 的性演算算方法比SDIFA(SDLA) 10次的演算算法比得得更好。