Complex Radial Basis Function Networks Trained by QR-Decomposition Recursive Least Square Algorithms Applied in Behavioral Modeling of Nonlinear Power Amplifiers

摘要

In this article, we propose a novel complex radial basis function network approach for dynamic behavioral modeling of nonlinear power amplifier with memory in 3 G systems. The proposed approach utilizes the complex QR-decomposition based recursive least squares (QRD-RLS) algorithm, which is implemented using the complex Givens rotations, to update the weighting matrix of the complex radial basis function (RBF) network. Comparisons with standard least squares algorithms, in batch and recursive process, the QRD-RLS algorithm has the characteristics of good numerical robustness and regular structure, and can significantly improve the complex RBF network modeling accuracy. In this approach, only the signal's complex envelope is used for the model training and validation. The model has been validated using ADS simulated and real measured data. Finally, parallel implementation of the resulting method is briefly discussed.