King's College London

Research portal

Prediction of mmWave/THz Link Blockages through Meta-Learning and Recurrent Neural Networks

Research output: Contribution to journalArticlepeer-review

Anders E. Kalor, Osvaldo Simeone, Petar Popovski

Original languageEnglish
Pages (from-to)2815-2819
Number of pages5
JournalIEEE Wireless Communications Letters
Issue number12
Early online date7 Oct 2021
Accepted/In press4 Oct 2021
E-pub ahead of print7 Oct 2021
Published1 Dec 2021

Bibliographical note

Funding Information: This work was supported in part by the Danish Council for Independent Research under Grant 8022-00284B (SEMIOTIC). Publisher Copyright: © 2012 IEEE.


King's Authors


Wireless applications that rely on links that offer high reliability depend critically on the capability of the system to predict link quality within a given time interval. This dependence is especially acute at the high carrier frequencies used by mmWave and THz systems, where the links are susceptible to blockages. Predicting blockages with high reliability requires a large number of data samples to train effective machine learning modules. With the aim of mitigating data requirements, we introduce a framework based on meta-learning, whereby data from distinct deployments are leveraged to optimize a shared initialization that decreases the data set size necessary for any new deployment. Predictors of two different events are studied: (1) at least one blockage occurs in a time window, and (2) the link is blocked for the entire time window. The results show that an RNN-based predictor trained using meta-learning is able to predict blockages after observing fewer samples than predictors trained using standard methods.

Download statistics

No data available

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454