The Library
State-of-the-art in PHY layer deep learning for future wireless communication systems and networks
Tools
Koufos, Konstantinos, El Haloui, Karim, Zhou, Cong, Frascolla, Valerio and Dianati, Mehrdad (2023) State-of-the-art in PHY layer deep learning for future wireless communication systems and networks. In: Hu, Fei and Rasheed, Iftikhar, (eds.) Deep Learning and Its Applications for Vehicle Networks. Boca Raton: Taylor & Francis Ltd., pp. 87-114. ISBN 9781003190691
|
PDF
WRAP-State-of-the-art-PHY-layer-deep-learning-future-wireless-communication-systems-networks-Koufos-2023.pdf - Accepted Version - Requires a PDF viewer. Download (6Mb) | Preview |
Official URL: http://dx.doi.org/10.1201/9781003190691-7
Abstract
Ongoing activities by several standardization bodies, experimental demonstrations in research projects, and recent trends and investments by the telecommunication sector reveal that the next generation of wireless communication systems will offer a multitude of unprecedented use cases, such as enhanced mobile broadband for ultra-high-speed railways, augmented reality, and 3d connectivity involving unmanned aerial vehicles (UAVs) and intelligent reflecting surfaces. Furthermore, well-established and verified mathematical models, such as those utilised for channel equalization, link adaptation, and symbol detection, will likely fall short once applied in wireless systems operating in higher frequencies and deployed in challenging environments. Fortunately, recent advancements in data collection and storage, together with breakthroughs in artificial intelligence (AI) and machine learning (ML), will allow communication engineers to construct data-driven solutions for optimising the performance of envisioned future networks. Motivated by these potentials, in this chapter, we provide the interested readers with a comprehensive analysis and review of the most recent progress in using data-driven and ML-based approaches at the PHY layer of modern communications. We review the performance of purely data-driven auto-encoders and put an emphasis on model-aided transfer learning schemes for PHY layer operation. Key studies reveal that embedding ML into traditional model-based schemes can significantly enhance the performance of various PHY layer functions. Nevertheless, the explicability of neural networks remains an open issue and is expected to be an active area of research in the coming years, lying at the intersection of computer science and PHY layer communications.
Item Type: | Book Item | ||||||
---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||
Publisher: | Taylor & Francis Ltd. | ||||||
Place of Publication: | Boca Raton | ||||||
ISBN: | 9781003190691 | ||||||
Book Title: | Deep Learning and Its Applications for Vehicle Networks | ||||||
Editor: | Hu, Fei and Rasheed, Iftikhar | ||||||
Official Date: | 12 May 2023 | ||||||
Dates: |
|
||||||
Page Range: | pp. 87-114 | ||||||
DOI: | 10.1201/9781003190691-7 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Re-use Statement: | This is an Accepted Manuscript of a book chapter published by Routledge in Deep Learning and Its Applications for Vehicle Networks on 12 May 2023, available online: http://www.routledge.com/9781003190691 | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 11 April 2023 | ||||||
Date of first compliant Open Access: | 12 May 2024 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year