Reinforcement Learning Strategies for Energy Management in Low Power IoT - Université Bretagne Sud Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Reinforcement Learning Strategies for Energy Management in Low Power IoT

Yohann Rioual
  • Fonction : Auteur
Johann Laurent
Eric Senn
Jean-Philippe Diguet

Résumé

Energy management in low power IoT is a difficult problem. Modeling the consumption of a sensor node is complicated , they operate in a stochastic environment. They harvest energy in their environment but energy sources present time-varying behavior. It becomes hazardous to predict in advance the energy behavior of our system. In this paper we propose a new approach using both neural networks to estimate the harvesting energy and reinforcement learning algorithms to find the operating parameters to maximize the node's performance while preserving its energy resources.
Fichier principal
Vignette du fichier
Regular research paper CSCI-ISOT.pdf (230.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01654931 , version 1 (04-12-2017)

Identifiants

  • HAL Id : hal-01654931 , version 1

Citer

Yohann Rioual, Johann Laurent, Eric Senn, Jean-Philippe Diguet. Reinforcement Learning Strategies for Energy Management in Low Power IoT. CSCI, Dec 2017, Las Vegas, United States. ⟨hal-01654931⟩
243 Consultations
140 Téléchargements

Partager

Gmail Facebook X LinkedIn More