Show simple item record

Machine-Learning-Assisted Transmission Power Control for LoRaWAN Considering Environments with High Signal-to-Noise Variation

dc.contributor.authorGonzalez-Palacio M
dc.contributor.authorTobon-Vallejo D
dc.contributor.authorSepulveda-Cano L.M
dc.contributor.authorLuna-delRisco M
dc.contributor.authorRoehrig C
dc.contributor.authorLe L.B.
dc.date.accessioned2024-07-31T21:07:00Z
dc.date.available2024-07-31T21:07:00Z
dc.date.created2024
dc.identifier.issn21693536
dc.identifier.urihttp://hdl.handle.net/11407/8442
dc.descriptionTo achieve an adequate tradeoff between range and energy efficiency, LoRaWAN End Nodes (ENs) choose their transmission parameters using an Adaptive Data Rate (ADR) scheme based on the maximum value of previous Signal-to-Noise (<italic>SNR</italic>) values. However, the ADR only performs well in favorable channel conditions. In fact, if the <italic>SNR</italic> exhibits high variability, these parameters could be inefficiently set and may negatively affect the Packet Delivery Rate (PDR). Therefore, a link margin could be overestimated to improve the PDR by the ADR algorithm, which may, however, waste the EN&#x2019;s energy. This paper proposes a novel ADR that does not rely on the past <italic>SNR</italic> values. Still, our proposed design directly predicts the current <italic>SNR</italic> and transmission parameters using Machine Learning. Specifically, the underlying Machine Learning models were trained using in-field measurements for six months in Medell&#x00ED;n, Colombia, including different environmental variables and their effects on the <italic>SNR</italic>. Our ADR scheme improved energy consumption by 47.1% with a PDR of 99% and reduced collisions in dense networks up to 9.5% compared with the ADR scheme. Furthermore, we show that our proposed design outperforms some enhanced versions of the ADR scheme proposed in the literature in both energy consumption and collision rate. Finally, our proposed framework enables simple implementation since it runs directly in the ENs, improving the response time compared with the traditional ADR scheme. Authors
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics engineers Inc.
dc.relation.isversionofhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85190347221&doi=10.1109%2fACCESS.2024.3387457&partnerID=40&md5=4d2f4987e00ce468badb50467859c5e5
dc.sourceIEEE Access
dc.sourceIEEE Access
dc.sourceScopus
dc.subjectAdaptative Data Rateeng
dc.subjectConvergenceeng
dc.subjectEnergy consumptioneng
dc.subjectHeuristic algorithmseng
dc.subjectInternet of Thingseng
dc.subjectLoRaWANeng
dc.subjectMachine Learningeng
dc.subjectPower controleng
dc.subjectReinforcement learningeng
dc.subjectSignal to noise ratioeng
dc.subjectTransmission Power Controleng
dc.subjectEnergy efficiencyeng
dc.subjectHeuristic algorithmseng
dc.subjectInternet of thingseng
dc.subjectPower controleng
dc.subjectReinforcement learningeng
dc.subjectSignal to noise ratioeng
dc.subjectAdaptative data rateeng
dc.subjectConvergenceeng
dc.subjectData-rateeng
dc.subjectEnergy-consumptioneng
dc.subjectHeuristics algorithmeng
dc.subjectLoRaWANeng
dc.subjectMachine-learningeng
dc.subjectPower-controleng
dc.subjectReinforcement learningseng
dc.subjectTransmission power controleng
dc.subjectEnergy utilizationeng
dc.titleMachine-Learning-Assisted Transmission Power Control for LoRaWAN Considering Environments with High Signal-to-Noise Variationeng
dc.typearticle
dc.rights.accessrightsinfo:eu-repo/semantics/restrictedAccess
dc.publisher.programIngeniería de Telecomunicacionesspa
dc.publisher.programIngeniería en Energíaspa
dc.type.spaArtículo
dc.identifier.doi10.1109/ACCESS.2024.3387457
dc.relation.citationstartpage1
dc.relation.citationendpage1
dc.publisher.facultyFacultad de Ingenieríasspa
dc.affiliationGonzalez-Palacio, M., Universidad de Medell&#x00ED;n, Medell&#x00ED;n, Antioquia, Colombia
dc.affiliationTobon-Vallejo, D., Universidad de Antioquia, Medell&#x00ED;n, Antioquia, Colombia
dc.affiliationSepulveda-Cano, L.M., Universidad EAFIT, Medell&#x00ED;n, Antioquia, Colombia
dc.affiliationLuna-delRisco, M., Universidad de Medell&#x00ED;n, Medell&#x00ED;n, Antioquia, Colombia
dc.affiliationRoehrig, C., Fachhochschule Dortmund, University of Applied Sciences and Arts, Dortmund, Germany
dc.affiliationLe, L.B., Institut National de la Recherche Scientifique, Montreal, QC, Canada
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dc.identifier.reponamereponame:Repositorio Institucional Universidad de Medellín
dc.identifier.repourlrepourl:https://repository.udem.edu.co/
dc.identifier.instnameinstname:Universidad de Medellín


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record