Cargando…
Smart Energy Harvesting for Internet of Things Networks
In this article, we address the problem of prolonging the battery life of Internet of Things (IoT) nodes by introducing a smart energy harvesting framework for IoT networks supported by femtocell access points (FAPs) based on the principles of Contract Theory and Reinforcement Learning. Initially, t...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069813/ https://www.ncbi.nlm.nih.gov/pubmed/33924737 http://dx.doi.org/10.3390/s21082755 |
_version_ | 1783683325139877888 |
---|---|
author | Sangoleye, Fisayo Irtija, Nafis Tsiropoulou, Eirini Eleni |
author_facet | Sangoleye, Fisayo Irtija, Nafis Tsiropoulou, Eirini Eleni |
author_sort | Sangoleye, Fisayo |
collection | PubMed |
description | In this article, we address the problem of prolonging the battery life of Internet of Things (IoT) nodes by introducing a smart energy harvesting framework for IoT networks supported by femtocell access points (FAPs) based on the principles of Contract Theory and Reinforcement Learning. Initially, the IoT nodes’ social and physical characteristics are identified and captured through the concept of IoT node types. Then, Contract Theory is adopted to capture the interactions among the FAPs, who provide personalized rewards, i.e., charging power, to the IoT nodes to incentivize them to invest their effort, i.e., transmission power, to report their data to the FAPs. The IoT nodes’ and FAPs’ contract-theoretic utility functions are formulated, following the network economic concept of the involved entities’ personalized profit. A contract-theoretic optimization problem is introduced to determine the optimal personalized contracts among each IoT node connected to a FAP, i.e., a pair of transmission and charging power, aiming to jointly guarantee the optimal satisfaction of all the involved entities in the examined IoT system. An artificial intelligent framework based on reinforcement learning is introduced to support the IoT nodes’ autonomous association to the most beneficial FAP in terms of long-term gained rewards. Finally, a detailed simulation and comparative results are presented to show the pure operation performance of the proposed framework, as well as its drawbacks and benefits, compared to other approaches. Our findings show that the personalized contracts offered to the IoT nodes outperform by a factor of four compared to an agnostic type approach in terms of the achieved IoT system’s social welfare. |
format | Online Article Text |
id | pubmed-8069813 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-80698132021-04-26 Smart Energy Harvesting for Internet of Things Networks Sangoleye, Fisayo Irtija, Nafis Tsiropoulou, Eirini Eleni Sensors (Basel) Article In this article, we address the problem of prolonging the battery life of Internet of Things (IoT) nodes by introducing a smart energy harvesting framework for IoT networks supported by femtocell access points (FAPs) based on the principles of Contract Theory and Reinforcement Learning. Initially, the IoT nodes’ social and physical characteristics are identified and captured through the concept of IoT node types. Then, Contract Theory is adopted to capture the interactions among the FAPs, who provide personalized rewards, i.e., charging power, to the IoT nodes to incentivize them to invest their effort, i.e., transmission power, to report their data to the FAPs. The IoT nodes’ and FAPs’ contract-theoretic utility functions are formulated, following the network economic concept of the involved entities’ personalized profit. A contract-theoretic optimization problem is introduced to determine the optimal personalized contracts among each IoT node connected to a FAP, i.e., a pair of transmission and charging power, aiming to jointly guarantee the optimal satisfaction of all the involved entities in the examined IoT system. An artificial intelligent framework based on reinforcement learning is introduced to support the IoT nodes’ autonomous association to the most beneficial FAP in terms of long-term gained rewards. Finally, a detailed simulation and comparative results are presented to show the pure operation performance of the proposed framework, as well as its drawbacks and benefits, compared to other approaches. Our findings show that the personalized contracts offered to the IoT nodes outperform by a factor of four compared to an agnostic type approach in terms of the achieved IoT system’s social welfare. MDPI 2021-04-13 /pmc/articles/PMC8069813/ /pubmed/33924737 http://dx.doi.org/10.3390/s21082755 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Sangoleye, Fisayo Irtija, Nafis Tsiropoulou, Eirini Eleni Smart Energy Harvesting for Internet of Things Networks |
title | Smart Energy Harvesting for Internet of Things Networks |
title_full | Smart Energy Harvesting for Internet of Things Networks |
title_fullStr | Smart Energy Harvesting for Internet of Things Networks |
title_full_unstemmed | Smart Energy Harvesting for Internet of Things Networks |
title_short | Smart Energy Harvesting for Internet of Things Networks |
title_sort | smart energy harvesting for internet of things networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069813/ https://www.ncbi.nlm.nih.gov/pubmed/33924737 http://dx.doi.org/10.3390/s21082755 |
work_keys_str_mv | AT sangoleyefisayo smartenergyharvestingforinternetofthingsnetworks AT irtijanafis smartenergyharvestingforinternetofthingsnetworks AT tsiropouloueirinieleni smartenergyharvestingforinternetofthingsnetworks |