A Novel Deep Learning Approach to CSI Feedback Reporting for NR 5G Cellular Systems
Elisa Zimaglia, Daniel Gaetano Riviello, Roberto Garello, Roberto Fantini · 2020
In this paper, we study 5G Channel State Information feedback reporting. We show that a Deep Learning approach based on Convolutional Neural Networks can be used to learn efficient encoding and decoding algorithms. We set up a fully compliant link level 5G-New Radio simulator with clustered delay line channel model and we consider a realistic scenario with multiple transmitting/receiving antenna schemes and noisy downlink channel estimation. Results show that our Deep Learning approach achieves results comparable with traditional methods and can also outperform them in some conditions.