Application of the NARX neural network as a digital predistortion technique for linearizing microwave power amplifiers

Cargando...
Miniatura

Fecha

2015-09

Autores

Reynoso-Hernández, Apolinar
Rayas-Sánchez, José E.
Aguilar-Lobo, Lina M.
Loo-Yau, José R.
Ortega-Cisneros, Susana
Moreno, Pablo

Título de la revista

ISSN de la revista

Título del volumen

Editor

Microwave and Optical Technology Letters

Resumen

Descripción

This work presents a digital predistortion (DPD) scheme to linearize power amplifiers (PAs) using a recurrent neural network called Nonlinear AutoRegressive with eXogenous input model (NARX) neural network (NARXNN). The architecture of the NARXNN is based on a class of discrete-time nonlinear system named NARX. Its topology has embedded memory at the input and output of the neural architecture, which allows an efficient linearization of PAs. To show the benefits of the DPD with NARXNN, a commercial PA is fed with a long term evolution signal at 2.0 GHz with 10 MHz of bandwidth. Our experimental results show an adjacent channel leakage ratio improvement of 24 dB.

Palabras clave

Power Amplifier, Linearization, Long-Term Memory Effects, Recurrent Neural Nerwork, NARX, Digital Predistorsion

Citación

L. M. Aguilar-Lobo, J. R. Loo-Yau, J. E. Rayas-Sánchez, S. Ortega-Cisneros, P. Moreno, and J. A. Reynoso-Hernández, “Application of the NARX neural network as a digital predistortion technique for linearizing microwave power amplifiers,” Microwave and Optical Technology Letters, vol. 57, no. 9, pp. 2137-2142, Sep. 2015. (ISSN: 0895-2477; DOI 10.1002/mop)