A new augmented support vector regression‐based behavioral model for multi‐device power amplifiers

Abstract

AbstractA new behavioral model based on augmented time‐delay support vector regression (SVR) for multi‐device radio frequency (RF) nonlinear power amplifiers (PAs), is proposed in this paper. The theory of the proposed modeling technique is provided, along with a detailed modeling procedure. Experimental results show that the proposed new augmented SVR (NASVR) model leads to significant performance improvements when compared with basic SVR models and existing Augmented SVR (ASVR) models. When applied to a multi‐device Doherty PA, a normalized mean square error (NMSE) between model prediction and measurement data of −44.4 dB is obtained, representing a more than 9 and 4.5 dB improvement compared with the basic SVR model and the existing ASVR model, respectively.