Machine Learning-Based Characterization of SNR in Digital Satellite Communication Links

Abstract

Signals traveling through a Satellite Communication (SatCom) channel are subject to noise and interference effects, impacting their Signal-to-Noise ratio (SNR). Furthermore, nonlinear distortion arising from the nonlinear characteristic of the amplifiers in the system also adversely impacts performance. Current state-of-the-art techniques estimate these effects by including a sequence of known pilot symbols in the transmitted signals. While robust, a downside of these approaches Non-linear is that pilot symbols do not include useful information, thus HPA introducing overhead. This paper presents a Machine Learning (ML) approach to characterize the SNR, using the received signal in the return link of SatCom systems, independent of the User terminal signal's distortion level and without relying on pilot symbols. The proposed technique is validated through a suitable application example: the characterization of SNR in a SatCom system using a 16-APSK modulation scheme.