Behavioral Modeling of Power Amplifiers Leveraging Multi-Channel Convolutional Long Short-Term Deep Neural Network

R Li, Z Yao, Y Wang, Y Lin, T Ohtsuki… - IEEE Transactions on …, 2025‏ - ieeexplore.ieee.org
To improve the performance metrics of power amplifier (PA) nonlinear modeling while
reducing the complexity of neural networks (NN), this paper proposes a multi-channel …

Augmented Phase-Normalized Recurrent Neural Network for RF Power Amplifier Linearization

A Fischer-Bühner, L Anttila, M Turunen… - IEEE Transactions …, 2024‏ - ieeexplore.ieee.org
In this article, we present a highly accurate recurrent neural network (RNN) for behavioral
modeling and digital predistortion (DPD) of radio frequency (RF) power amplifiers (PAs). We …

DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion

A Li, H Wu, Y Wu, Q Chen, LCN de Vreede… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The increasing adoption of Deep Neural Network (DNN)-based Digital Pre-distortion (DPD)
in modern communication systems necessitates efficient hardware implementations. This …

Implementation of Predistortion Technique on OFDM System for LOS and NLOS Environments Using USRP-LabView

MW Gunawan, IGP Astawa… - 2024 IEEE International …, 2024‏ - ieeexplore.ieee.org
Power Amplifiers (PA) exhibit nonlinear characteristics that can cause nonlinear distortion
when applied to OFDM transmission systems, particularly in Line-of-Sight (LOS) and Non …

A Multi-branch Digital Pre-distortion Scheme with Reduced Sampling Rate for DACs.

W Ma, Z Ning, C Fan, Q Xu, S Shao, Y Liu - Authorea Preprints, 2024‏ - authorea.com
Digital pre-distortion (DPD) technology is an efficient method to linearize power amplifiers
(PAs). Current DPD techniques usually demand a sampling rate 5-7 times the source signal …