Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Similars in SciELO
Share
RISTI - Revista Ibérica de Sistemas e Tecnologias de Informação
Print version ISSN 1646-9895
Abstract
GONZALEZ-PALACIO, Mauricio; SEPULVEDA-CANO, Lina María; QUIZA-MONTEALEGRE, Jhon and D'AMATO, Juan. Improvement of the algorithm ADR in an Internet of Things network LoRaWAN by using Machine Learning. RISTI [online]. 2020, n.39, pp.67-83. ISSN 1646-9895. https://doi.org/10.17013/risti.39.67-83.
The Internet of Things (IoT) is an enabling paradigm for Industry 4.0, where sensors and actuators connect to the Internet. The protocol LoRaWAN (Long Range Area Network) is one of the most used in the IoT, and its primary objective is to transmit sensor information over long distances with minimal energy consumption. This protocol implements Adaptive Data Rate scheme to optimize the energy consumed per node, which, when evaluated through exhaustive simulations in Omnet ++, has exhibited opportunities for improvement in convergence time. The present work shows machine learning models based on parametric and non-parametric methods based on Support Vector Machines (SVM) and Artificial Neural Networks (ANN). The results indicate that the SVM and ANN methods have a success rate greater than 90% in the estimated parameters.
Keywords : Internet of Things; Industry 4.0; energy consumption; LoRaWAN; Machine Learning.