Behavioral Model With Multiple States Based on Deep Neural Network for Power Amplifiers

Digital predistortion is widely used to compensate the nonlinear distortion of power amplifiers (PAs). Among the digital predistortion methods, the polynomial or deep neural networks (DNNs) models are only adopted with one specific state. When the operating conditions of PAs change, it is necessary...

Full description

Saved in:
Bibliographic Details
Published inIEEE microwave and wireless components letters Vol. 32; no. 11; pp. 1363 - 1366
Main Authors Hu, Xin, Xie, Shubin, Ji, Xin, Chang, Xuming, Qiu, Yi, Li, Boyan, Liu, Zhijun, Wang, Weidong
Format Journal Article
LanguageEnglish
Published IEEE 01.11.2022
Subjects
Artificial neural networks
Behavioral model
Behavioral sciences
Data models
Deep learning
embedding vectors
Neurons
power amplifiers (PAs)
Predistortion
Wireless communication
Online AccessGet full text

Cover

More Information
Summary:Digital predistortion is widely used to compensate the nonlinear distortion of power amplifiers (PAs). Among the digital predistortion methods, the polynomial or deep neural networks (DNNs) models are only adopted with one specific state. When the operating conditions of PAs change, it is necessary to retrain and update the coefficients of the PA model. The generalization ability of the DNN models cannot be presented. To address this issue, this letter proposes one new modeling method that can build one generalized PA model with multiple states based on DNN. This method embeds a set of coding vectors representing corresponding states to build the generalized model. Compared with the traditional DNN model, experimental results show that the proposed method can construct the PA model containing multiple states while ensuring good modeling performance.
ISSN:1531-1309
1558-1764
DOI:10.1109/LMWC.2022.3186062