This paper outlines our approach to solving the amplitude modulation-to-amplitude modulation (AM-AM), and amplitude modulation-to-phase modulation (AM-PM) distortions caused by the onboard high-power amplifier (HPA) operating at the saturation point. The approach employs machine learning and artificial intelligence (ML-AI) to predistort the input signal such that the output of the post-HPA pre-distorted signal is identical to the original. The proposed ML-AI approach utilizes an existing MATLAB reinforcement learning technique using Deep Deterministic Policy Gradient (DDPG). The bulk of the research was to incorporate the proposed DDPG pre-distorter into the newly developed GNSS Single Side Band-Multi-Carrier Broadband Waveforms (SSB-MCBBW) and tune the pre-distorter’s hyper-parameters. The fine-tuning process was achieved efficiently by utilizing the parallel computing offered by a computer cluster at California State University Fullerton (CSUF) and has produced promising results in our simulated environment. The performance results of the proposed ML-AI pre-distorter using MATLAB DDPG algorithm are compared with the ideal pre-distorter for various HPA input back-off power (IPBO).

© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Tien M. Nguyen, Jose Aguilar, Charles H. Lee, Danny Paniagua-Rodriguez, Dan Shen, Genshe Chen, John Nguyen, Sam Behseta, Xiwen Kang, and Khanh D. Pham, "Onboard HPA pre-distorter using machine learning and artificial intelligence for future GNSS applications," Proc. SPIE 12546, Sensors and Systems for Space Applications XVI, 1254605 (Presented at SPIE Defense + Commercial Sensing: May 03, 2023; Published: 13 June 2023); https://doi.org/10.1117/12.2663425.