Deep Learning-Based Robust Precoding for Massive MIMO

• Published in: IEEE transactions on communications Vol. 69; no. 11; pp. 7429 - 7443
• Main Authors: Shi, Junchao, Wang, Wenjin, Yi, Xinping, Gao, Xiqi, Li, Geoffrey Ye
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Channel estimation; Communications systems; Complexity; Correlation; Deep learning; Downlink; Eigenvalues; Ergodic processes; Iterative algorithms; Iterative methods; Lagrange multiplier; Machine learning; Massive MIMO; Mathematical analysis; MIMO communication; Neural networks; Parameters; Precoding; precoding structure; Robust precoding; Transmission line matrix methods; Upper bounds
• ISSN: 0090-6778; 1558-0857
• DOI: 10.1109/TCOMM.2021.3105569

In this paper, we consider massive multiple-input-multiple-output (MIMO) communication systems with a uniform planar array (UPA) at the base station (BS) and investigate the downlink precoder design with imperfect channel state information (CSI). By exploiting channel estimates and statistical parameters of channel estimation error, we aim to design precoding vectors to maximize the utility function on the ergodic rates of users subject to a total transmit power constraint. By employing an upper bound of the ergodic rate, we leverage the corresponding Lagrangian formulation and identify the structural characteristics of the optimal precoder as the solution to a generalized eigenvalue problem. The Lagrange multipliers play a crucial role in determining both precoding directions and power parameters, yet are challenging to be solved directly. To figure out the Lagrange multipliers, we develop a general framework underpinned by a properly designed neural network that learns directly from CSI. To further relieve the computational burden, we obtain a low-complexity framework by decomposing the original problem into computationally efficient subproblems with instantaneous and statistical CSI handled separately. With the offline pre-trained neural network, the online computational complexity of precoder is substantially reduced compared with the existing iterative algorithm while maintaining nearly the same performance.