Machine Learning-Based Linearization Schemes for Radio Over Fiber Systems

This work proposes a novel machine learning (ML)-based linearization scheme for radio-over-fiber (RoF) systems with external modulation. The proposed approach has the advantage of not requiring new training campaigns in case the Mach-Zehnder modulator (MZM) parameters are changed over time. Our inno...

Full description

Saved in:
Bibliographic Details
Published in:IEEE photonics journal 2022-12, Vol.14 (6), p.1-10
Main Authors: Pereira, Luiz A. M., Mendes, Luciano L., Bastos-Filho, Carmelo J. A., Jr, Arismar Cerqueira S.
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Complexity
Complexity theory
digital pre-distortion
Errors
Feedback linearization
Mach-Zehnder interferometers
Machine learning
Mean square errors
Multilayer perceptrons
Multilayers
neural network and radio-over-fiber
Optical distortion
Optical fiber devices
Radio
Radio frequency
RF signals
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work proposes a novel machine learning (ML)-based linearization scheme for radio-over-fiber (RoF) systems with external modulation. The proposed approach has the advantage of not requiring new training campaigns in case the Mach-Zehnder modulator (MZM) parameters are changed over time. Our innovative digital pre-distortion (DPD) was designed to favor enhanced remote areas (eRAC) scenarios, in which the non-linearities introduced by the MZM become more severe. It employs a multi-layer perceptron (MLP) artificial neural network (ANN) to model the RoF system and estimate its post-inverse response, which is then applied to the DPD block. We investigate the ML-based DPD performance in terms of adjacent channel leakage ratio (ACLR), normalized mean square error (NMSE), resultant signal root mean square error vector magnitude error (EVM_\mathrm{RMS}), and complexity. Numerical results demonstrate that the intended DPD method is less complex and outperforms the orthogonal scalar feedback linearization (OSFL) scheme, which has been considered a state-of-the-art DPD technique. The proposal has the potential to effectively and efficiently compensate for the RoF nonlinear distortions, especially in a time-variant system, without needing new training campaigns.
ISSN:1943-0655
1943-0655
1943-0647
DOI:10.1109/JPHOT.2022.3210454