Knowledge and Data Dual-Driven Channel Estimation and Feedback for Ultra-Massive MIMO Systems Under Hybrid Field Beam Squint Effect

• Published in: IEEE transactions on wireless communications 2024-09, Vol.23 (9), p.11240-11259
• Main Authors: Wang, Kuiyu, Gao, Zhen, Chen, Sheng, Ning, Boyu, Chen, Gaojie, Su, Yu, Wang, Zhaocheng, Poor, H. Vincent
• Format: Article
• Language: English
• Subjects: Analog to digital converters; Artificial neural networks; Broadband; Channel estimation; CSI feedback; Data acquisition; Downlink; Downlinking; Far fields; Feedback; Hardware; hybrid near- and far- field channels; knowledge and data dual-driven; Message passing; Millimeter wave communication; Millimeter waves; MIMO communication; Noise measurement; orthogonal frequency division multiplexing (OFDM); Quadratures; Training; Ultra-massive multiple input multiple output (UM-MIMO); Uplink; Wideband
• ISSN: 1536-1276; 1558-2248
• DOI: 10.1109/TWC.2024.3380638

Acquiring accurate channel state information (CSI) at an access point (AP) is challenging for wideband millimeter wave (mmWave) ultra-massive multiple-input and multiple-output (UM-MIMO) systems, due to the high-dimensional channel matrices, hybrid near- and far- field channel behavior, beam squint effects, and imperfect hardware constraints, such as low-resolution analog-to-digital converters, and in-phase and quadrature imbalance. To overcome these challenges, this paper proposes an efficient downlink channel estimation (CE) and CSI feedback approach based on knowledge and data dual-driven deep learning (DL) networks. Specifically, we first propose a data-driven residual neural network de-quantizer (ResNet-DQ) to pre-process received pilot signals at user equipment (UEs), where the noise and distortion brought by imperfect hardware can be mitigated. A knowledge-driven generalized multiple measurement vector learned approximate message passing (GMMV-LAMP) network is then developed to jointly estimate the channels by exploiting the approximately same physical angle shared by different subcarriers. In particular, two wideband redundant dictionaries (WRDs) are proposed such that the measurement matrices of the GMMV-LAMP network can accommodate the far-field and near-field beam squint effect, respectively. Finally, we propose an encoder at the UEs and a decoder at the AP by a data-driven CSI residual network (CSI-ResNet) to compress the CSI matrix into a low-dimensional quantized bit vector for feedback, thereby reducing the feedback overhead substantially. Simulation results show that the proposed knowledge and data dual-driven approach outperforms conventional downlink CE and CSI feedback methods, especially in the case of low signal-to-noise ratios.