MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yizhuo, Li, Ang, Beikmirza, Mohammadreza, Singh, Gagan Deep, Chen, Qinyu, de Vreede, Leo C. N., Alavi, Morteza, Gao, Chang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911851340627968
author Wu, Yizhuo
Li, Ang
Beikmirza, Mohammadreza
Singh, Gagan Deep
Chen, Qinyu
de Vreede, Leo C. N.
Alavi, Morteza
Gao, Chang
author_facet Wu, Yizhuo
Li, Ang
Beikmirza, Mohammadreza
Singh, Gagan Deep
Chen, Qinyu
de Vreede, Leo C. N.
Alavi, Morteza
Gao, Chang
contents Digital Pre-Distortion (DPD) enhances signal quality in wideband RF power amplifiers (PAs). As signal bandwidths expand in modern radio systems, DPD's energy consumption increasingly impacts overall system efficiency. Deep Neural Networks (DNNs) offer promising advancements in DPD, yet their high complexity hinders their practical deployment. This paper introduces open-source mixed-precision (MP) neural networks that employ quantized low-precision fixed-point parameters for energy-efficient DPD. This approach reduces computational complexity and memory footprint, thereby lowering power consumption without compromising linearization efficacy. Applied to a 160MHz-BW 1024-QAM OFDM signal from a digital RF PA, MP-DPD gives no performance loss against 32-bit floating-point precision DPDs, while achieving -43.75 (L)/-45.27 (R) dBc in Adjacent Channel Power Ratio (ACPR) and -38.72 dB in Error Vector Magnitude (EVM). A 16-bit fixed-point-precision MP-DPD enables a 2.8X reduction in estimated inference power. The PyTorch learning and testing code is publicly available at \url{https://github.com/lab-emi/OpenDPD}.
format Preprint
id arxiv_https___arxiv_org_abs_2404_15364
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers
Wu, Yizhuo
Li, Ang
Beikmirza, Mohammadreza
Singh, Gagan Deep
Chen, Qinyu
de Vreede, Leo C. N.
Alavi, Morteza
Gao, Chang
Signal Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Digital Pre-Distortion (DPD) enhances signal quality in wideband RF power amplifiers (PAs). As signal bandwidths expand in modern radio systems, DPD's energy consumption increasingly impacts overall system efficiency. Deep Neural Networks (DNNs) offer promising advancements in DPD, yet their high complexity hinders their practical deployment. This paper introduces open-source mixed-precision (MP) neural networks that employ quantized low-precision fixed-point parameters for energy-efficient DPD. This approach reduces computational complexity and memory footprint, thereby lowering power consumption without compromising linearization efficacy. Applied to a 160MHz-BW 1024-QAM OFDM signal from a digital RF PA, MP-DPD gives no performance loss against 32-bit floating-point precision DPDs, while achieving -43.75 (L)/-45.27 (R) dBc in Adjacent Channel Power Ratio (ACPR) and -38.72 dB in Error Vector Magnitude (EVM). A 16-bit fixed-point-precision MP-DPD enables a 2.8X reduction in estimated inference power. The PyTorch learning and testing code is publicly available at \url{https://github.com/lab-emi/OpenDPD}.
title MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers
topic Signal Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2404.15364