Open AccessDeep unfolding based hyper‐parameter optimisation for self‐interference cancellation in LTE‐A/5G‐transceivers
Author(s) -
Motz C.,
Paireder T.,
Huemer M.
Publication year - 2021
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/ell2.12230
Subject(s) - transceiver , least mean squares filter , computer science , interference (communication) , algorithm , artificial neural network , electronic engineering , recursive least squares filter , deep learning , single antenna interference cancellation , duplex (building) , function (biology) , frequency domain , adaptive filter , artificial intelligence , telecommunications , engineering , wireless , decoding methods , channel (broadcasting) , dna , evolutionary biology , biology , computer vision , genetics
Deep unfolding is a very promising concept that allows to combine the advantages of traditional estimation techniques, such as adaptive filters, and machine learning approaches, like artificial neural networks. Focusing on a challenging self‐interference problem occurring in frequency‐division duplex radio frequency transceivers, namely modulated spurs, it is shown that deep unfolding enables remarkable performance gains. Based on the hyper‐parameter optimisation of several least‐mean squares (LMS) variants and the recursive‐least squares algorithm, the importance of a well‐chosen loss function are highlighted. Especially the variable step‐size LMS and the transform‐domain LMS vastly benefit without increased runtime complexity.