Publication :
Measuring fuel consumption in vehicle routing : new estimation models using supervised learning

Notice brève
ali.license-refhttps://creativecommons.org/licenses/by-nd/4.0fr
ali.license-ref.start-date2022-07-06fr
bul.description.provenanceelmon chlacfr
bul.rights.dateAccepPubl2021-07-06fr
bul.rights.periodeEmbargoP1Yfr
bul.rights.typeDatedatePublicationfr
dc.contributor.authorHeni, Hamza
dc.contributor.authorDiop, Serigne Arona
dc.contributor.authorRenaud, Jacques
dc.contributor.authorCoelho, Leandro C.
dc.date.accessioned2021-07-26T20:35:47Z
dc.date.available2022-07-06T00:00:00Z
dc.date.issued2021-07-06
dc.description.abstractIn this paper, we propose and assess the accuracy of new fuel consumption estimation models for vehicle routing. Based on real-world data consisting of instantaneous fuel consumption, time-varying speeds observations, and high-frequency traffic, we propose effective methods to estimate fuel consumption. By carrying out nonlinear regression analysis using supervised learning methods, namely Neural Networks, Support Vector Machines, Conditional Inference Trees, and Gradient Boosting Machines, we develop new models that provide better prediction accuracy than classical models. We correctly estimate consumption for time-dependent point-to-point routing under realistic conditions. Our methods provide a more precise alternative to classical regression methods used in the literature, as they are developed for a specific situation. Extensive computational experiments under realistic conditions show the effectiveness of the proposed machine learning consumption models, clearly outperforming macroscopic and microscopic consumption models such as the Comprehensive Modal Emissions Model (CMEM) and the Methodology for Estimating air pollutant Emissions from Transport (MEET). Based on sensitivity analyses we show that MEET underestimates real-world consumption by 24.94% and CMEM leads to an overestimation of consumption by 7.57% with optimised parameters. Our best machine learning model (Gradient Boosting Machines) exhibited superior estimation accuracy with a gap of only 1.70%.fr
dc.identifier.doi10.1080/00207543.2021.1948133fr
dc.identifier.issn0020-7543fr
dc.identifier.urihttp://hdl.handle.net/20.500.11794/69721
dc.languageengfr
dc.publisherTaylor & Francis Groupfr
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subjectConsumption modelsfr
dc.subjectMachine learningfr
dc.subjectAnalyticsfr
dc.subjectTime-dependent routingfr
dc.subjectMonte Carlo simulationfr
dc.subject.rvmProblèmes de tournées -- Modèles mathématiquesfr
dc.subject.rvmCamions -- Carburants -- Consommationfr
dc.subject.rvmApprentissage automatiquefr
dc.subject.rvmMéthode de Monte-Carlofr
dc.titleMeasuring fuel consumption in vehicle routing : new estimation models using supervised learningfr
dc.typearticle de recherche
dc.type.legacyCOAR1_1::Texte::Périodique::Revue::Contribution à un journal::Article::Article de recherchefr
dcterms.bibliographicCitationInternational Journal of Production Research, (2021)fr
dspace.accessstatus.time2023-05-24 18:03:38
dspace.entity.typePublication
relation.isAuthorOfPublication206696ce-cbc1-471b-a7c6-08099e1f3c81
relation.isAuthorOfPublication76540993-c067-4248-8ed9-1818a830fc05
relation.isAuthorOfPublicatione006d6c6-48a1-46a0-9506-8832d93189fa
relation.isAuthorOfPublicatione3ed4930-989b-4b53-89dd-d457ffcecb79
relation.isAuthorOfPublication.latestForDiscovery206696ce-cbc1-471b-a7c6-08099e1f3c81
relation.isResourceTypeOfPublication4c433ef5-3937-4530-8252-cca17d715747
relation.isResourceTypeOfPublication.latestForDiscovery4c433ef5-3937-4530-8252-cca17d715747
rioxxterms.project.funder-nameNatural Sciences and Engineering Research Council of Canadafr
rioxxterms.project.funder-nameCentre d’innovation en logistique et chaîne d’approvisionnement durablefr
rioxxterms.project.funder-nameTransition énergétique Québecfr
rioxxterms.versionAccepted Manuscript (AM)fr
rioxxterms.version-of-recordhttps://doi.org/10.1080/00207543.2021.1948133fr
Fichiers
Bundle original
Voici les éléments 1 - 1 sur 1
Vignette d'image
Nom :
fuel_consumption_IJPR.pdf
Taille :
3.07 MB
Format :
Adobe Portable Document Format
Description :
Télécharger
Collections
Articles publiés dans des revues avec comité de lecture