Multi-Section Support Vector Regression-Based Behavioral Modeling of RF GaN Doherty Power Amplifiers

Abstract

A novel behavioral model based on multi-section support vector regression (MS-SVR) of radio frequency (RF) Gallium Nitride (GaN) Doherty power amplifiers (PAs) is proposed in this paper. In this method, the input signal is divided into different sections according to signal amplitude and each section is modeled separately using SVR. Experimental validation is performed using a 2.4 GHz Doherty PA. The results show that the proposed model can effectively reduce the time of parameter extraction and signal processing.