Mejoramiento del algoritmo ADR en una red de internet de las cosas LoRaWAN usando aprendizaje de máquina

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.