Learning Statistically Robust MIMO Detection with Imperfect CSI

Abstract

In this paper, we investigate the design of statistically robust detectors for multi-input multi-output (MIMO) systems subject to imperfect channel state information (CSI). A robust maximum likelihood (ML) detection problem is formulated by taking into consideration the CSI uncertainties caused by both the channel estimation error and the channel variation. To address the challenging discrete optimization problem, we propose an efficient alternating direction method of multipliers (ADMM)based algorithm, which only requires calculating closed-form solutions in each iteration. Furthermore, a robust detection network RADMMNet is constructed by unfolding the ADMM iterations and employing both model-driven and data-driven philosophies. Moreover, in order to relieve the computational burden, a low-complexity ADMM-based robust detector is developed using the Gaussian approximation, and the corresponding deep unfolding network LCRADMMNet is further established. On the other hand, we also provide a novel robust dataaided Kalman filter (RDAKF)-based channel tracking method, which can effectively refine the CSI accuracy and improve the performance of the proposed robust detectors. Simulation results validate the significant performance advantages of the proposed robust detection networks over the non-robust detectors with different CSI acquisition methods.

面向超可靠低时延通信的有限块长mimo传输理论与技术

“…受此启发, 后续研究者陆续提出了 OAMPNet [78] , ADMMNet [79] 以及 LcgNet [80] 等. 进一步地, 本文的作者同时考虑信道估计误差和信道时变影响, 结合深度展开技 术和数据驱动结构, 研究了抗非理想 CSI 的鲁棒 MIMO 检测网络 RADMMNet [81] .…”