Mostrar el registro sencillo del ítem

dc.contributor.authorLópez Martín, Manuel
dc.contributor.authorSánchez Esguevillas, Antonio Javier
dc.contributor.authorHernández Callejo, Luis 
dc.contributor.authorArribas Sánchez, Juan Ignacio 
dc.contributor.authorCarro Martínez, Belén 
dc.date.accessioned2022-07-21T09:21:43Z
dc.date.available2022-07-21T09:21:43Z
dc.date.issued2021
dc.identifier.citationSensors, 2021, vol. 21, n. 9, p. 2979es
dc.identifier.issn1424-8220es
dc.identifier.urihttps://uvadoc.uva.es/handle/10324/54135
dc.descriptionProducción Científicaes
dc.description.abstractThis work proposes a quantile regression neural network based on a novel constrained weighted quantile loss (CWQLoss) and its application to probabilistic short and medium-term electric-load forecasting of special interest for smart grids operations. The method allows any point forecast neural network based on a multivariate multi-output regression model to be expanded to become a quantile regression model. CWQLoss extends the pinball loss to more than one quantile by creating a weighted average for all predictions in the forecast window and across all quantiles. The pinball loss for each quantile is evaluated separately. The proposed method imposes additional constraints on the quantile values and their associated weights. It is shown that these restrictions are important to have a stable and efficient model. Quantile weights are learned end-to-end by gradient descent along with the network weights. The proposed model achieves two objectives: (a) produce probabilistic (quantile and interval) forecasts with an associated probability for the predicted target values. (b) generate point forecasts by adopting the forecast for the median (0.5 quantiles). We provide specific metrics for point and probabilistic forecasts to evaluate the results considering both objectives. A comprehensive comparison is performed between a selection of classic and advanced forecasting models with the proposed quantile forecasting model. We consider different scenarios for the duration of the forecast window (1 h, 1-day, 1-week, and 1-month), with the proposed model achieving the best results in almost all scenarios. Additionally, we show that the proposed method obtains the best results when an additive ensemble neural network is used as the base model. The experimental results are drawn from real loads of a medium-sized city in Spain.es
dc.format.mimetypeapplication/pdfes
dc.language.isoenges
dc.publisherMDPIes
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subject.classificationShort and medium-term electric-load forecastinges
dc.subject.classificationQuantile forecastinges
dc.subject.classificationDeep learninges
dc.subject.classificationMachine learninges
dc.subject.classificationDeep learning additive ensemble modeles
dc.titleAdditive ensemble neural network with constrained weighted quantile loss for probabilistic electric-load forecastinges
dc.typeinfo:eu-repo/semantics/articlees
dc.rights.holder© 2021 The Author(s)es
dc.identifier.doi10.3390/s21092979es
dc.relation.publisherversionhttps://www.mdpi.com/1424-8220/21/9/2979es
dc.identifier.publicationfirstpage2979es
dc.identifier.publicationissue9es
dc.identifier.publicationtitleSensorses
dc.identifier.publicationvolume21es
dc.peerreviewedSIes
dc.description.projectMinisterio de Ciencia, Innovación y Universidades Proyectos de I+D+i ‘‘Retos investigación’’, (grant RTI2018-098958- B-I00)es
dc.identifier.essn1424-8220es
dc.rightsAtribución 4.0 Internacional*
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones
dc.subject.unesco33 Ciencias Tecnológicases


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem