Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

ML-Enabled Outdoor User Positioning in 5G NR Systems via Uplink SRS Channel Estimates

Ráth, Andre LU ; Pjanić, Dino LU ; Bernhardsson, Bo LU orcid and Tufvesson, Fredrik LU orcid (2023) 2023 IEEE International Conference on Communications, ICC 2023 In IEEE International Conference on Communications 2023-May. p.2215-2220
Abstract

Cellular user positioning is a promising service provided by Fifth Generation New Radio (5G NR) networks. Besides, Machine Learning (ML) techniques are foreseen to become an integrated part of 5G NR systems improving radio performance and reducing complexity. In this paper, we investigate ML techniques for positioning using 5G NR fingerprints consisting of uplink channel estimates from the physical layer channel. We show that it is possible to use Sounding Reference Signals (SRS) channel fingerprints to provide sufficient data to infer user position. Furthermore, we show that small fully-connected moderately Deep Neural Networks, even when applied to very sparse SRS data, can achieve successful outdoor user positioning with meter-level... (More)

Cellular user positioning is a promising service provided by Fifth Generation New Radio (5G NR) networks. Besides, Machine Learning (ML) techniques are foreseen to become an integrated part of 5G NR systems improving radio performance and reducing complexity. In this paper, we investigate ML techniques for positioning using 5G NR fingerprints consisting of uplink channel estimates from the physical layer channel. We show that it is possible to use Sounding Reference Signals (SRS) channel fingerprints to provide sufficient data to infer user position. Furthermore, we show that small fully-connected moderately Deep Neural Networks, even when applied to very sparse SRS data, can achieve successful outdoor user positioning with meter-level accuracy in a commercial 5G environment.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
5G, beamforming, deep neural network, localization, machine learning, positioning, radio access network, sounding reference signal
host publication
ICC 2023 - IEEE International Conference on Communications : Sustainable Communications for Renaissance - Sustainable Communications for Renaissance
series title
IEEE International Conference on Communications
editor
Zorzi, Michele ; Tao, Meixia and Saad, Walid
volume
2023-May
pages
6 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2023 IEEE International Conference on Communications, ICC 2023
conference location
Rome, Italy
conference dates
2023-05-28 - 2023-06-01
external identifiers
  • scopus:85178294151
ISSN
1550-3607
ISBN
9781538674628
DOI
10.1109/ICC45041.2023.10279249
language
English
LU publication?
yes
id
b70a0b45-945e-403f-ab5e-2fe1ed1a9005
date added to LUP
2024-01-02 15:38:15
date last changed
2025-04-04 14:26:30
@inproceedings{b70a0b45-945e-403f-ab5e-2fe1ed1a9005,
  abstract     = {{<p>Cellular user positioning is a promising service provided by Fifth Generation New Radio (5G NR) networks. Besides, Machine Learning (ML) techniques are foreseen to become an integrated part of 5G NR systems improving radio performance and reducing complexity. In this paper, we investigate ML techniques for positioning using 5G NR fingerprints consisting of uplink channel estimates from the physical layer channel. We show that it is possible to use Sounding Reference Signals (SRS) channel fingerprints to provide sufficient data to infer user position. Furthermore, we show that small fully-connected moderately Deep Neural Networks, even when applied to very sparse SRS data, can achieve successful outdoor user positioning with meter-level accuracy in a commercial 5G environment.</p>}},
  author       = {{Ráth, Andre and Pjanić, Dino and Bernhardsson, Bo and Tufvesson, Fredrik}},
  booktitle    = {{ICC 2023 - IEEE International Conference on Communications : Sustainable Communications for Renaissance}},
  editor       = {{Zorzi, Michele and Tao, Meixia and Saad, Walid}},
  isbn         = {{9781538674628}},
  issn         = {{1550-3607}},
  keywords     = {{5G; beamforming; deep neural network; localization; machine learning; positioning; radio access network; sounding reference signal}},
  language     = {{eng}},
  pages        = {{2215--2220}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE International Conference on Communications}},
  title        = {{ML-Enabled Outdoor User Positioning in 5G NR Systems via Uplink SRS Channel Estimates}},
  url          = {{http://dx.doi.org/10.1109/ICC45041.2023.10279249}},
  doi          = {{10.1109/ICC45041.2023.10279249}},
  volume       = {{2023-May}},
  year         = {{2023}},
}