End-to-End Joint Optimization for PAPR Reduction and Digital Predistortion Based on Neural Network

DOI number:10.1109/LMWT.2025.3546643

Affiliation of Author(s):图书馆VIP信息学院

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

Journal:IEEE Microwave and Wireless Technology Letters (Early Access)

Funded by:国家自然科学基金 NNSF 62371436

Key Words:End-to-end optimization, digital predistortion (DPD), peak-to-average power ratio (PAPR) reduction, neural network (NN), power amplifiers (PAs), geometric shaping (GS).

Abstract:The combination of crest factor reduction (CFR) and digital predistortion (DPD) can mitigate the average efficiency reduction of power amplifiers (PAs) due to high peak-to-average power ratio (PAPR) signals. A common CFR method is time-domain (TD) clipping, which causes irreversible signal impairment. To this end, an end-to-end (E2E) joint optimization method based on neural networks (NNs) is proposed in this letter. The E2E architecture consists of a transmitter network, a DPD model, and a PA model, enabling integrated processing of signal transmitted, transmission, and reception. The proposed method uses multiobjective joint optimization to reduce the PAPR of the TD signal through constellation point geometric shaping (GS) in the frequency domain, while simultaneously training the DPD model. While considering the interaction between PAPR reduction and DPD techniques, this approach can reduce PAPR without signal impairment and can allow them to work together to achieve high-quality signal transmission.

First Author:Qianqian Zhang (张牵牵)

Co-author:Renlong Han,Chengye Jiang,Junsen Wang,Hao Chang

Indexed by:Journal paper

Correspondence Author:Falin Liu

Document Code:10.1109/LMWT.2025.3546643

Discipline:Engineering

Document Type:J

Volume:Online

Issue:Online

Page Number:1-4

Translation or Not:no

Date of Publication:2025-03-12