Deep Learning Approach for Precise Positioning of Millimeter Wave in 5G for V2V Links

DOI

10.2991/978-94-6463-082-4_11How to use a DOI?

Keywords

V2V Technology; V2X; 5G; mmWave of 5G; Deep learning; AIoT

Abstract

The millimeter-wave of 5G will usher in a new era in Vehicle-to-Vehicle (V2V) communication. The ensuing radiation from a millimeter-wave of 5G bounces off most visible things, creating enriched multi-directional environments, particularly in sub-urban scenarios. Physical impediments were once primarily connected with signal attenuation; nevertheless, their existence now introduces complicated, non-linear phenomena such as reflections and scattering. As a result of the impediments faced, a multipath propagation environment emerges, suggesting the presence of concealed spatial information within the received signal for a dense vehicular environment. The key contributions of this research are to discuss and evaluate a self-proposed deep neural network for the beamformed fingerprint location problem in connected cars. Training of deep learning model and simulation environment has been performed using AMD Ryzen 7 GPU environment. Results show that in a realistic outdoor sub-urban scenario with predominantly non-line-of-sight (NLoS) positions, average estimation errors of less than 1.69 m can be achieved, paving the way for novel positioning systems beneficial for V2V links with low computational power. Furthermore, the self-proposed deep learning model is compared with the long-short-term memory (LSTM) in terms of computational complexity. Self-proposed DNN outperform LSTM in terms of training time by 50 min.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - H. T. Ahmed
AU  - Jun Jiat Tiang
AU  - Azwan Bin Mahmud
AU  - Gwo Chin Chung
PY  - 2022
DA  - 2022/12/23
TI  - Deep Learning Approach for Precise Positioning of Millimeter Wave in 5G for V2V Links
BT  - Proceedings of the Multimedia University Engineering Conference (MECON 2022)
PB  - Atlantis Press
SP  - 97
EP  - 107
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-082-4_11
DO  - 10.2991/978-94-6463-082-4_11
ID  - Ahmed2022
ER  -