Heterogeneous Basis Parameter Combination Method and Dynamic Transfer Strategy for Digital Predistortion of RF Power Amplifiers

DOI number:10.1109/TMTT.2023.3315791

Affiliation of Author(s):中国科技大学

Teaching and Research Group:电子工程与信息科学系

Journal:IEEE Transactions on Microwave Theory and Techniques （Early access）

Funded by:Natural Science Foundation of China

Key Words:Digital Predistortion (DPD), Parameter Identification, Power Amplifiers (PAs), Principal Component Analysis, Transfer Learning.

Abstract:To accomplish rapid adaptation of the digital predistortion (DPD) model, a low-complexity parameter extraction architecture is proposed in this article. The extracted DPD model coefficients are represented by a linear combination of the previous parameters (or pretrained parameters) in a novel basis parameter combination (BPC) method, thereby avoiding the extraction of high-dimensionality coefficients and significantly lowering the computational cost. Then, we developed a feature mapping technique (FMT) to coordinate the feature spaces corresponding to different DPD model structures, which facilitates the transfer learning of heterogeneous DPD model coefficients as the DPD model structure should be modified with the transmission configuration changes. Due to the good scalability of the proposed method, a dynamic transfer strategy (DTS) is presented to enhance the method's flexibility and avoid incremental complications by combining it with dimensionality reduction techniques. The experimental results demonstrate that the proposed method outperforms the state-of-the-art in terms of computational complexity, adaptability, and modeling precision.

First Author:Guichen Yang (杨贵晨)

Co-author:Chengye Jiang,Renlong Han,Jingchao Tan,Qianqian Zhang

Indexed by:Journal paper

Correspondence Author:Falin Liu

Document Code:10.1109/TMTT.2023.3315791

Discipline:Engineering

Document Type:J

Volume:72

Issue:4

Page Number:2466-2476

Translation or Not:no

Date of Publication:2024-04-01

Included Journals:SCI、EI