6533b7d8fe1ef96bd126b756
RESEARCH PRODUCT
Preamble Transmission Prediction for mMTC Bursty Traffic : A Machine Learning based Approach
Thilina N. WeerasingheFrank Y. LiIndika A. M. BalapuwadugeAasmund Soraasubject
Artificial neural networkComputer sciencebusiness.industryComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS05 social sciences050801 communication & media studies020206 networking & telecommunicationsComputingMilieux_LEGALASPECTSOFCOMPUTING02 engineering and technologyMachine learningcomputer.software_genrePreambleBase station0508 media and communicationsRecurrent neural networkTransmission (telecommunications)Traffic volume0202 electrical engineering electronic engineering information engineeringArtificial intelligencebusinesscomputerVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550description
The evolution of Internet of things (IoT) towards massive IoT in recent years has stimulated a surge of traffic volume among which a huge amount of traffic is generated in the form of massive machine type communications. Consequently, existing network infrastructure is facing challenges when handling rapidly growing traffic load, especially under bursty traffic conditions which may more often lead to congestion. By proactively predicting the occurrence of congestion, we can implement necessary means and conceivably avoid congestion. In this paper, we propose a machine learning (ML) based model for predicting successful preamble transmissions at a base station and subsequently forecasting the possible occurrence of congestion under bursty traffic conditions. The model is composed of a recurrent neural network ML algorithm which is built based on the long short-term memory architecture. Through extensive simulations, we demonstrate that the proposed model achieves precise predictions on successful preamble transmissions relying merely on the data collected priori to congestion occurrence.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-12-01 |