Boosted Model Tree-Based Behavioral Modeling for Digital Predistortion of RF Power Amplifiers

• Published in: IEEE transactions on microwave theory and techniques Vol. 69; no. 9; pp. 3976 - 3988
• Main Authors: Li, Yue, Wang, Xiaoyu, Pang, Jingzhou, Zhu, Anding
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Behavioral modeling; Boosting; Broadband; Complexity; Complexity theory; Data models; decision tree; Decision trees; digital predistortion (DPD); Hardware; machine learning; Modelling; Optimization; power amplifier (PA); Power amplifiers; Radio frequency
• ISSN: 0018-9480; 1557-9670; 1557-9670
• DOI: 10.1109/TMTT.2021.3081096

In this article, we propose a new behavioral modeling approach, called boosted model tree, to characterize and compensate for the complex nonlinear distortions induced by wideband high-efficiency radio frequency power amplifiers. With the proposed model, the input data are classified into different zones by decision trees and each zone is assigned separate submodels. We also employ a model boosting technique to build multiple parallel tree structures that jointly model the desired nonlinear behavior. By designing dedicated optimization procedures, both tree structures and submodel coefficients can be efficiently identified. It is demonstrated that the combination of piecewise and parallel structures provides a powerful and hardware-efficient way to model nonlinear memory effect and cross terms. Based on the experimental results, the proposed method can achieve improved linearization performance with low hardware complexity under challenging wideband predistortion scenarios.