Deep Learning for UL/DL Channel Calibration in Generic Massive MIMO Systems

Abstract

One of the fundamental challenges to realize massive Multiple-Input Multiple-Output (MIMO) communications is the accurate acquisition of channel state information for a plurality of users at the base station. This is usually accomplished in the UpLink (UL) direction profiting from the time division duplexing mode. In practical base station transceivers, there exist inevitably nonlinear hardware components, like signal amplifiers and various analog filters, which complicates the calibration task. To deal with this challenge, we design a deep neural network for channel calibration between the UL and DownLink (DL) directions. During the initial training phase, the deep neural network is trained from both UL and DL channel measurements. We then leverage the trained deep neural network with the instantaneously estimated UL channel to calibrate the DL one, which is not observable during the UL transmission phase. Our numerical results confirm the merits of the proposed approach, and show that it can achieve performance comparable to conventional approaches, like the Agros method and methods based on least squares, that however assume linear hardware behavior models. More importantly, considering generic nonlinear relationships between the UL and DL channels, it is demonstrated that our deep neural network approach exhibits robust performance, even when the number of training sequences is limited.

Learning Parameters of Stochastic Radio Channel Models From Summaries

“…While efforts have been directed towards DL-enabled physical layer design, only a few applications to radio channel modeling and calibration have been proposed. In [27], the authors utilized Deep Neural Network for uplink-downlink channel calibration in massive MIMO. Similar network is utilized for predicting path-loss exponent from millimeter wave channel measurements in [28].…”

Uplink Null-Space Expansion for Multiuser Massive MIMO in Time-Varying Channels Under Unknown Interference

“…Recent trend is to employ a neural network which has high versatility for wireless physical signal processing [35],…”

“…. , N i (35) where each element of h dl,iid and h im,iid are independent and identically distributed (i.i.d.) Rayleigh fading channel coefficient generated by the Jakes' model [29], and R dl ∈ C Nr×Nr and R im ∈ C Nr×Nr are spatial correlation matrices at BS side.…”

Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces

“…Among them are the K-nearest neighbors, support vector machines, and Bayesian learning [9]. Very recently, deep learning methods have demonstrated significant improvements in various applications (e.g., [10], [11]). These methods are capable of outperforming human-level object detection in some tasks, achieving the state-of-the-art results in machine translation and speech processing, as well as improving outdoor localization in massive antenna systems [10].…”