Extremely large-scale multiple-input multiple-output (XL-MIMO) is a promising technique to enable versatile applications for future wireless communications.To realize the huge potential performance gain, accurate channel state information is a fundamental technical prerequisite. In conventional massive MIMO, the channel is often modeled by the far-field planar-wavefront with rich sparsity in the angular domain that facilitates the design of low-complexity channel estimation. However, this sparsity is not conspicuous in XL-MIMO systems due to the non-negligible near-field spherical-wavefront. To address the inherent performance loss of the angular-domain channel estimation schemes, we first propose the polar-domain multiple residual dense network (P-MRDN) for XL-MIMO systems based on the polar-domain sparsity of the near-field channel by improving the existing MRDN scheme. Furthermore, a polar-domain multi-scale residual dense network (P-MSRDN) is designed to improve the channel estimation accuracy. Finally, simulation results reveal the superior performance of the proposed schemes compared with existing benchmark schemes and the minimal influence of the channel sparsity on the proposed schemes.

翻译：超大规模多输入多输出（XL-MIMO）技术是赋能未来无线通信多样化应用的关键技术。为充分发挥其潜在性能增益，获取精确的信道状态信息是基础性技术前提。传统大规模MIMO中，信道通常采用远场平面波前模型，并在角度域呈现显著稀疏性，这为低复杂度信道估计设计提供了便利。然而，在XL-MIMO系统中，由于近场球面波前效应不可忽略，这种稀疏性并不明显。为克服角度域信道估计方案固有的性能损失，本文首先基于近场信道的极域稀疏性，通过改进现有MRDN方案，提出适用于XL-MIMO系统的极域多重残差密集网络（P-MRDN）。此外，进一步设计极域多尺度残差密集网络（P-MSRDN）以提升信道估计精度。仿真结果表明，与现有基准方案相比，所提方案具有优越性能，且信道稀疏性对其影响极小。