TW_onecco.pdf (661.31 kB)

Transfer learning and meta learning-based fast downlink beamforming adaptation

Download (661.31 kB)
journal contribution
posted on 25.03.2021, 10:08 by Yi Yuan, Gan Zheng, Kai-Kit Wong, Björn Ottersten, Zhi-Quan Luo
This article studies fast adaptive beamforming optimization for the signal-to-interference-plus-noise ratio balancing problem in a multiuser multiple-input single-output downlink system. Existing deep learning based approaches to predict beamforming rely on the assumption that the training and testing channels follow the same distribution which may not hold in practice. As a result, a trained model may lead to performance deterioration when the testing network environment changes. To deal with this task mismatch issue, we propose two offline adaptive algorithms based on deep transfer learning and meta-learning, which are able to achieve fast adaptation with the limited new labelled data when the testing wireless environment changes. Furthermore, we propose an online algorithm to enhance the adaptation capability of the offline meta algorithm in realistic non-stationary environments. Simulation results demonstrate that the proposed adaptive algorithms achieve much better performance than the direct deep learning algorithm without adaptation in new environments. The meta-learning algorithm outperforms the deep transfer learning algorithm and achieves near optimal performance. In addition, compared to the offline meta-learning algorithm, the proposed online meta-learning algorithm shows superior adaption performance in changing environments.

Funding

Unlocking Potentials of MIMO Full-duplex Radios for Heterogeneous Networks (UPFRONT)

Engineering and Physical Sciences Research Council

Find out more...

Leverhulme Trust Research Project under Grant RPG-2017-129

Unlocking Potentials of MIMO Full-duplex Radios for Heterogeneous Networks (UPFRONT)

Engineering and Physical Sciences Research Council

Find out more...

H2020-ERC-AdG-AGNOSTIC under Grant 742648

Leading Talents of Guangdong Province Program under Grant 00201501

National Natural Science Foundation of China under Grant 61731018

Development and Reform Commission of Shenzhen Municipality

Shenzhen Fundamental Research Fund under Grant KQTD201503311441545

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Published in

IEEE Transactions on Wireless Communications

Volume

20

Issue

3

Pages

1742 - 1755

Publisher

IEEE

Version

AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

26/10/2020

Publication date

2020-11-16

Copyright date

2020

ISSN

1536-1276

eISSN

1558-2248

Language

en

Depositor

Dr Gan Zheng. Deposit date: 18 March 2021