Identification of Non-Linear RF Systems Using Backpropagation
Abstract
In this work, we use deep unfolding to view cascaded non-linear RF systems as model-based neural networks. This view enables the direct use of a wide range of neural network tools and optimizers to efficiently identify such cascaded models. We demonstrate the effectiveness of this approach through the example of digital self-interference cancellation in full-duplex communications where an IQ imbalance model and a non-linear PA model are cascaded in series. For a self-interference cancellation performance of approximately 44.5 dB, the number of model parameters can be reduced by 74% and the number of operations per sample can be reduced by 79% compared to an expanded linear-in-parameters polynomial model.
Keywords
Cite
@article{arxiv.2001.09877,
title = {Identification of Non-Linear RF Systems Using Backpropagation},
author = {Andreas Toftegaard Kristensen and Andreas Burg and Alexios Balatsoukas-Stimming},
journal= {arXiv preprint arXiv:2001.09877},
year = {2020}
}
Comments
To be presented at the 2020 IEEE International Conference on Communications (Workshop on Full-Duplex Communications for Future Wireless Networks)