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

International audienceOne of the fundamental challenges to realize massive multiple-input multiple-output 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 direction profiting from the Time Division Duplexing mode. In practical base station transceivers, there exist inevitably non-linear 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 uplink and downlink directions. During the initial training phase, the deep neural network is trained from both uplink and downlink channel measurements. We then leverage the trained deep neural network with the instantaneously estimated uplink channel to calibrate the downlink one, which is not observable during the uplink 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 nonlin-ear relationships between the uplink and downlink channels, it is demonstrated that our deep neural network approach exhibits robust performance, even when the number of training sequences is limited