Online unsupervised deep unfolding for MIMO channel estimation
This addresses the problem of unrealistic system configuration requirements in MIMO channel estimation for base stations, offering an incremental improvement by adding flexibility to existing models.
The paper tackles channel estimation in massive MIMO systems by proposing an online unsupervised deep unfolding method that corrects imperfect physical models using incoming data, achieving channel estimation error nearly as low as a perfectly calibrated system.
Channel estimation is a difficult problem in MIMO systems. Using a physical model allows to ease the problem, injecting a priori information based on the physics of propagation. However, such models rest on simplifying assumptions and require to know precisely the system configuration, which is unrealistic.In this paper, we propose to perform online learning for channel estimation in a massive MIMO context, adding flexibility to physical models by unfolding a channel estimation algorithm (matching pursuit) as a neural network. This leads to a computationally efficient neural network that can be trained online when initialized with an imperfect model. The method allows a base station to automatically correct its channel estimation algorithm based on incoming data, without the need for a separate offline training phase.It is applied to realistic channels and shows great performance, achieving channel estimation error almost as low as one would get with a perfectly calibrated system.