Artificial Intelligence based Power-Temperature Inclusive Digital Pre-Distortion

This paper investigates the effects of the signal average power and the ambient temperature on the behavioral modeling and pre-distortion of high-power amplifiers concurrently. The measurement results showed that in addition to the signal average power, the behavior of a high-power PA is a function of ambient temperature as well. This paper proposes a novel smart Digital Pre-Distortion (DPD) model that considers both average Power and Temperature (PTI-DPD). The PTI-DPD is implemented using Artificial Intelligence (AI) based model and it benefits from sets of data formats containing the signal, its delayed versions, signal average power, and ambient temperature. The devised apparatus provides an uninterrupted linearization across the ambient temperature and signal average power span without need for any feedback or multiple models. A series of measurements have been conducted to study the PTI-DPD performance across the temperature and average power range. According to the results, the PTI-DPD achieves an average of -48.5 dBc Adjacent Channel Power Ratio (ACPR) across the average power and temperature span.