DOI码：10.1109/TMTT.2023.3315791

所属单位：中国科技大学

教研室：电子工程与信息科学系

发表刊物：IEEE Transactions on Microwave Theory and Techniques

项目来源：国家自然科学基金

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

摘要：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.

合写作者：Chengye Jiang,Renlong Han,Jingchao Tan,Qianqian Zhang

第一作者：Guichen Yang (杨贵晨)

论文类型：期刊论文

通讯作者：Falin Liu

论文编号：10.1109/TMTT.2023.3315791

学科门类：工学

文献类型：J

卷号：72

期号：4

页面范围：2466-2476

是否译文：否

发表时间：2024-04-01

收录刊物：SCI、EI