Energy Saving in a Wireless Sensor Network by Data Prediction by using Self-Organized Maps

Adrien Russo (1) , François Verdier (1) , Benoît Miramond (1)

1 LEAT - Laboratoire d'Electronique, Antennes et Télécommunications

We present in this paper a predictive analysis method based on a unsupervised type of machine learning algorithm : the kohonen maps. This model will be exploited in a network of sensors to reduce the number of transmission on the network. The aim of this paper is to present a learning algorithm and the result obtained in the context of smart city.

Mots clés: Smart-cities; Self-Organizing-Map; Energy Saving; Time Series Prediction

Domaines: Réseau de neurones [cs.NE]; Energie électrique; Systèmes embarqués; Architectures Matérielles [cs.AR]; Electromagnétisme

Adrien Russo, François Verdier, Benoît Miramond. Energy Saving in a Wireless Sensor Network by Data Prediction by using Self-Organized Maps. International Workshop on Recent Advances in Cellular Technologies and 5G for IoT Environments (RACT-5G-IoT 2018), May 2018, Porto, Portugal. pp.1090-1095, ⟨10.1016/j.procs.2018.04.161⟩. ⟨hal-01740303⟩