Augmentation of Self-Interference Cancellation for Full-Duplex using NARX Neural Networks

Qingqing  Dong; Andrew C M Austin; Kevin Sowerby

doi:10.1109/LWC.2023.3344938

Augmentation of Self-Interference Cancellation for Full-Duplex using NARX Neural Networks

Qingqing Dong, Andrew C M Austin, Kevin Sowerby

School of Electrical, Electronic and Mechanical Engineering

Research output: Contribution to journal › Article (Academic Journal) › peer-review

1 Citation (Scopus)

49 Downloads (Pure)

Abstract

A self-interference cancellation augmentation technique based on a NARX (Nonlinear Autoregressive Exogenous) network model is implemented and evaluated on an OFDM-based full-duplex system testbed operating at 2.4 GHz. In a comparison with the state-of-the-art polynomial models, our experimental results demonstrate the significant computational efficiency of the proposed NARX model. Specifically, the NARX model with one hidden layer reduces computations by 83.3% while achieving the same cancellation level within a bandwidth of 2 MHz.

Original language	English
Pages (from-to)	1
Number of pages	1
Journal	IEEE Wireless Communications Letters
DOIs	https://doi.org/10.1109/LWC.2023.3344938
Publication status	E-pub ahead of print - 20 Dec 2023

Bibliographical note

Publisher Copyright:
IEEE

Access to Document

10.1109/LWC.2023.3344938Licence: Unspecified

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at 10.1109/LWC.2023.3344938. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 848 KBLicence: CC BY

Handle.net

Persistent link

Cite this

@article{4b1d1d3d0c9b4c9a9cccd398cb2365ee,

title = "Augmentation of Self-Interference Cancellation for Full-Duplex using NARX Neural Networks",

abstract = "A self-interference cancellation augmentation technique based on a NARX (Nonlinear Autoregressive Exogenous) network model is implemented and evaluated on an OFDM-based full-duplex system testbed operating at 2.4 GHz. In a comparison with the state-of-the-art polynomial models, our experimental results demonstrate the significant computational efficiency of the proposed NARX model. Specifically, the NARX model with one hidden layer reduces computations by 83.3% while achieving the same cancellation level within a bandwidth of 2 MHz.",

author = "Qingqing Dong and Austin, {Andrew C M} and Kevin Sowerby",

note = "Publisher Copyright: IEEE",

year = "2023",

month = dec,

day = "20",

doi = "10.1109/LWC.2023.3344938",

language = "English",

pages = "1",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - Augmentation of Self-Interference Cancellation for Full-Duplex using NARX Neural Networks

AU - Dong, Qingqing

AU - Austin, Andrew C M

AU - Sowerby, Kevin

N1 - Publisher Copyright: IEEE

PY - 2023/12/20

Y1 - 2023/12/20

N2 - A self-interference cancellation augmentation technique based on a NARX (Nonlinear Autoregressive Exogenous) network model is implemented and evaluated on an OFDM-based full-duplex system testbed operating at 2.4 GHz. In a comparison with the state-of-the-art polynomial models, our experimental results demonstrate the significant computational efficiency of the proposed NARX model. Specifically, the NARX model with one hidden layer reduces computations by 83.3% while achieving the same cancellation level within a bandwidth of 2 MHz.

AB - A self-interference cancellation augmentation technique based on a NARX (Nonlinear Autoregressive Exogenous) network model is implemented and evaluated on an OFDM-based full-duplex system testbed operating at 2.4 GHz. In a comparison with the state-of-the-art polynomial models, our experimental results demonstrate the significant computational efficiency of the proposed NARX model. Specifically, the NARX model with one hidden layer reduces computations by 83.3% while achieving the same cancellation level within a bandwidth of 2 MHz.

U2 - 10.1109/LWC.2023.3344938

DO - 10.1109/LWC.2023.3344938

M3 - Article (Academic Journal)

SN - 2162-2337

SP - 1

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

ER -

Augmentation of Self-Interference Cancellation for Full-Duplex using NARX Neural Networks

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this