Blockage Prediction in Directional mmWave Links Using Liquid Time Constant Network

Martin Hedegaard Nielsen, Chia-Yi Yeh, Ming Shen, Muriel Medard

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

65 Downloads (Pure)

Abstract

We propose to use a liquid time constant (LTC) network to predict the future blockage status of a millimeter wave (mmWave) link using only the received signal power as the input to the system.
The LTC network is based on an ordinary differential equation (ODE) system inspired by biology and specialized for near-future prediction for time sequence observation as the input.
Using an experimental dataset at 60 GHz, we show that our proposed use of LTC can reliably predict the occurrence of blockage and the length of the blockage without the need for scenario-specific data. The results show that the proposed LTC can predict with upwards of 97.85% accuracy without prior knowledge of the outdoor scenario or retraining/tuning. These results highlight the promising gains of using LTC networks to predict time series-dependent signals, which can lead to more reliable and low-latency communication.
OriginalsprogEngelsk
TitelProceeding 2023 - 48th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
Antal sider2
ForlagIEEE (Institute of Electrical and Electronics Engineers)
Publikationsdatookt. 2023
Artikelnummer10299092
ISBN (Trykt)979-8-3503-3661-0
ISBN (Elektronisk)979-8-3503-3660-3
DOI
StatusUdgivet - okt. 2023
Begivenhed2023 48th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - Montreal, Canada
Varighed: 17 sep. 202322 sep. 2023

Konference

Konference2023 48th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz)
Land/OmrådeCanada
ByMontreal
Periode17/09/202322/09/2023
NavnInternational Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz)
ISSN2162-2035

Fingeraftryk

Dyk ned i forskningsemnerne om 'Blockage Prediction in Directional mmWave Links Using Liquid Time Constant Network'. Sammen danner de et unikt fingeraftryk.

Citationsformater