Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems

The design of conventional digital predistortion (DPD) requires an analogue-to-digital converter (ADC) with a sampling frequency that is multiple times the signal bandwidth, which is extremely challenging for sub-Nyquist sampling systems with undersampled signals. To address this, this paper propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengqiu Liu, Xining Yang, Jian Gao, Sen Cao, Guisheng Liao, Gaopan Hou, Dawei Gao
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082426832814080
author Mengqiu Liu
Xining Yang
Jian Gao
Sen Cao
Guisheng Liao
Gaopan Hou
Dawei Gao
author_facet Mengqiu Liu
Xining Yang
Jian Gao
Sen Cao
Guisheng Liao
Gaopan Hou
Dawei Gao
author_sort Mengqiu Liu
collection DOAJ
description The design of conventional digital predistortion (DPD) requires an analogue-to-digital converter (ADC) with a sampling frequency that is multiple times the signal bandwidth, which is extremely challenging for sub-Nyquist sampling systems with undersampled signals. To address this, this paper proposes a neural network (NN)-assisted wideband power amplifier (PA) DPD method for sub-Nyquist sampling systems, wherein a dual-stage architecture is designed to handle the ambiguity caused by subsampled communications signals. In the first stage, the time-delayed polynomial reconstruction method is employed to estimate the wideband DPD nonlinearity coarsely with the undersampled signals with limited pilots. In the second stage, an NN-based DPD method is proposed for the virtual training of the DPD, which learns the up-sampled DPD behavior by taking advantage of the pre-estimated DPD model and the input data signals, which reduces the length of the training sequence significantly and refines the DPD behavior efficiently. Simulation results demonstrate the efficacy of the proposed method in tackling the wideband PA nonlinearity and its ability to outperform the conventional method in terms of power spectrum, error vector magnitude, and bit error rate.
format Article
id doaj-art-c3b9a8d81380469999acfed0aec24621
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c3b9a8d81380469999acfed0aec246212025-08-20T02:44:32ZengMDPI AGSensors1424-82202025-02-01254110610.3390/s25041106Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling SystemsMengqiu Liu0Xining Yang1Jian Gao2Sen Cao3Guisheng Liao4Gaopan Hou5Dawei Gao6Hangzhou Institute of Technology, Xidian University, Hangzhou 311200, China29th Research Institute of China Electronics Technology Group Corporation, Chengdu 610036, China29th Research Institute of China Electronics Technology Group Corporation, Chengdu 610036, China29th Research Institute of China Electronics Technology Group Corporation, Chengdu 610036, ChinaHangzhou Institute of Technology, Xidian University, Hangzhou 311200, ChinaHangzhou Institute of Technology, Xidian University, Hangzhou 311200, ChinaHangzhou Institute of Technology, Xidian University, Hangzhou 311200, ChinaThe design of conventional digital predistortion (DPD) requires an analogue-to-digital converter (ADC) with a sampling frequency that is multiple times the signal bandwidth, which is extremely challenging for sub-Nyquist sampling systems with undersampled signals. To address this, this paper proposes a neural network (NN)-assisted wideband power amplifier (PA) DPD method for sub-Nyquist sampling systems, wherein a dual-stage architecture is designed to handle the ambiguity caused by subsampled communications signals. In the first stage, the time-delayed polynomial reconstruction method is employed to estimate the wideband DPD nonlinearity coarsely with the undersampled signals with limited pilots. In the second stage, an NN-based DPD method is proposed for the virtual training of the DPD, which learns the up-sampled DPD behavior by taking advantage of the pre-estimated DPD model and the input data signals, which reduces the length of the training sequence significantly and refines the DPD behavior efficiently. Simulation results demonstrate the efficacy of the proposed method in tackling the wideband PA nonlinearity and its ability to outperform the conventional method in terms of power spectrum, error vector magnitude, and bit error rate.https://www.mdpi.com/1424-8220/25/4/1106digital predistortion (DPD)undersamplingmemory polynomialattention mechanism model
spellingShingle Mengqiu Liu
Xining Yang
Jian Gao
Sen Cao
Guisheng Liao
Gaopan Hou
Dawei Gao
Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
Sensors
digital predistortion (DPD)
undersampling
memory polynomial
attention mechanism model
title Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
title_full Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
title_fullStr Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
title_full_unstemmed Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
title_short Neural Network-Assisted DPD of Wideband PA Nonlinearity for Sub-Nyquist Sampling Systems
title_sort neural network assisted dpd of wideband pa nonlinearity for sub nyquist sampling systems
topic digital predistortion (DPD)
undersampling
memory polynomial
attention mechanism model
url https://www.mdpi.com/1424-8220/25/4/1106
work_keys_str_mv AT mengqiuliu neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT xiningyang neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT jiangao neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT sencao neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT guishengliao neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT gaopanhou neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems
AT daweigao neuralnetworkassisteddpdofwidebandpanonlinearityforsubnyquistsamplingsystems