Location- and Orientation-Aided Millimeter Wave Beam Selection Using Deep Learning

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

149 Downloads (Pure)

Abstrakt

Location-aided beam alignment methods exploit the user location and prior knowledge of the propagation environment to identify the beam directions that are more likely to maximize the beamforming gain, allowing for a reduction of the beam training overhead. They have been especially popular for vehicle to everything (V2X) applications where the receive array orientation is approximately constant for each considered location, but are not directly applicable to pedestrian applications with arbitrary orientation of the user handset. This paper proposes a deep neural network based beam selection method that leverages position and orientation of the receiver to recommend a shortlist of the best beam pairs, thus significantly reducing the alignment overhead. Moreover, we use multi-labeled classification to not only capture the beam pair with highest received strength but also enrich the neural network with information of alternative beam pairs with high received signal strength, providing robustness against blockage. Simulation results show the better performance of the proposed method compared to a generalization of the inverse fingerprinting algorithm in terms of the misalignment and outage probabilities.
OriginalsprogEngelsk
TitelICC 2020 - 2020 IEEE International Conference on Communications (ICC)
Antal sider6
ForlagIEEE
Publikationsdato27 jul. 2020
Artikelnummer9149272
ISBN (Trykt)978-1-7281-5090-1
ISBN (Elektronisk)978-1-7281-5089-5
DOI
StatusUdgivet - 27 jul. 2020
Begivenhed2020 IEEE International Conference on Communications, ICC 2020 - Dublin, Irland
Varighed: 7 jun. 202011 jun. 2020
https://icc2020.ieee-icc.org/

Konference

Konference2020 IEEE International Conference on Communications, ICC 2020
LandIrland
ByDublin
Periode07/06/202011/06/2020
Internetadresse
NavnIEEE International Conference on Communications
ISSN1938-1883

Fingeraftryk Dyk ned i forskningsemnerne om 'Location- and Orientation-Aided Millimeter Wave Beam Selection Using Deep Learning'. Sammen danner de et unikt fingeraftryk.

  • Citationsformater

    Rezaie, S., Manchon, C. N., & De Carvalho, E. (2020). Location- and Orientation-Aided Millimeter Wave Beam Selection Using Deep Learning. I ICC 2020 - 2020 IEEE International Conference on Communications (ICC) [9149272] IEEE. IEEE International Conference on Communications https://doi.org/10.1109/ICC40277.2020.9149272