Deep learning for location based beamforming with NLOS channels
This addresses the pilot overhead problem in wireless communication systems, offering a potential efficiency improvement, though it is incremental as it builds on existing location-based beamforming concepts.
The paper tackles the overhead of pilot symbols in massive MIMO systems by proposing a deep learning method that maps user location directly to precoders, enabling location-based beamforming for both LOS and NLOS channels, with promising results on synthetic data.
Massive MIMO systems are highly efficient but critically rely on accurate channel state information (CSI) at the base station in order to determine appropriate precoders. CSI acquisition requires sending pilot symbols which induce an important overhead. In this paper, a method whose objective is to determine an appropriate precoder from the knowledge of the user's location only is proposed. Such a way to determine precoders is known as location based beamforming. It allows to reduce or even eliminate the need for pilot symbols, depending on how the location is obtained. the proposed method learns a direct mapping from location to precoder in a supervised way. It involves a neural network with a specific structure based on random Fourier features allowing to learn functions containing high spatial frequencies. It is assessed empirically and yields promising results on realistic synthetic channels. As opposed to previously proposed methods, it allows to handle both line-of-sight (LOS) and non-line-of-sight (NLOS) channels.