Blockage Prediction in Directional mmWave Links Using Liquid Time Constant Network

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

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

41 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.
Original languageEnglish
Title of host publicationProceeding 2023 - 48th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
Number of pages2
PublisherIEEE
Publication dateOct 2023
Article number10299092
ISBN (Print)979-8-3503-3661-0
ISBN (Electronic)979-8-3503-3660-3
DOIs
Publication statusPublished - Oct 2023
Event2023 48th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz) - Montreal, Canada
Duration: 17 Sept 202322 Sept 2023

Conference

Conference2023 48th International Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz)
Country/TerritoryCanada
CityMontreal
Period17/09/202322/09/2023
SeriesInternational Conference on Infrared, Millimeter, and Terahertz Waves (IRMMW-THz)
ISSN2162-2035

Fingerprint

Dive into the research topics of 'Blockage Prediction in Directional mmWave Links Using Liquid Time Constant Network'. Together they form a unique fingerprint.

Cite this