Residual Neural Networks for Digital Predistortion
Paper in proceeding, 2020

Tracking the nonlinear behavior of an RF power amplifier (PA) is challenging. To tackle this problem, we build a connection between residual learning and the PA nonlinearity, and propose a novel residual neural network structure, referred to as the residual real-valued time-delay neural network (R2TDNN). Instead of learning the whole behavior of the PA, the R2TDNN focuses on learning its nonlinear behavior by adding identity shortcut connections between the input and output layer. In particular, we apply the R2TDNN to digital predistortion and measure experimental results on a real PA. Compared with neural networks recently proposed by Liu et at. and Wang et at., the R2TDNN achieves the best linearization performance in terms of normalized mean square error and adjacent channel power ratio with less or similar computational complexity. Furthermore, the R2TDNN exhibits significantly faster training speed and lower training error.

Behavioral modeling

Radio Frequency amplifiers

Power amplifiers

Author

Yibo Wu

Chalmers, Electrical Engineering, Communication and Antenna Systems, Communication Systems

Ericsson

Ulf Gustavsson

Ericsson

Alexandre Graell I Amat

Chalmers, Electrical Engineering, Communication and Antenna Systems, Communication Systems

Henk Wymeersch

Chalmers, Electrical Engineering, Communication and Antenna Systems, Communication Systems

2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings

9322327

2020 IEEE Global Communications Conference, GLOBECOM 2020
Virtual, Taipei, Taiwan,

Subject Categories

Telecommunications

Communication Systems

Signal Processing

DOI

10.1109/GLOBECOM42002.2020.9322327

More information

Latest update

4/26/2021