Publication:
A methodology for energy multivariate time series forecasting in smart buildings based on feature selection

Simple item page
dc.contributor.authorGonzález Vidal, Aurora
dc.contributor.authorJiménez Barrionuevo, Fernando
dc.contributor.authorSkarmeta Gómez, Antonio
dc.contributor.departmentIngeniería de la Información y las Comunicaciones
dc.contributor.otherFacultades de la UMU::Facultad de Informática
dc.date.accessioned2026-02-03T09:35:53Z
dc.date.available2026-02-03T09:35:53Z
dc.date.copyright©2019ElsevierB.V
dc.date.issued2019-05-10
dc.description.abstractThe massive collection of data via emerging technologies like the Internet of Things (IoT) requires finding optimal ways to reduce the created features that have a potential impact on the information that can be extracted through the machine learning process. The mining of knowledge related to a concept is done on the basis of the features of data. The process of finding the best combination of features is called feature selection. In this paper we deal with multivariate time-dependent series of data points for energy forecasting in smart buildings. We propose a methodology to transform the time-dependent database into a structure that standard machine learning algorithms can process, and then, apply different types of feature selection methods for regression tasks. We used Weka for the tasks of database transformation, feature selection, regression, statistical test and forecasting. The proposed methodology improves MAE by 59.97% and RMSE by 40.75%, evaluated on training data, and it improves MAE by 42.28% and RMSE by 36.62%, evaluated on test data, on average for 1-step-ahead, 2-step-ahead and 3-step-ahead when compared to not applying any feature selection methodology.
dc.formatapplication/pdf
dc.format.extent12
dc.identifier.citationGonzalez-Vidal, A., Jimenez, F., & Gomez-Skarmeta, A. F. (2019). A methodology for energy multivariate time series forecasting in smart buildings based on feature selection. Energy and Buildings, 196, 71-82.
dc.identifier.doihttps://doi.org/10.1016/j.enbuild.2019.05.021
dc.identifier.issn0378-7788
dc.identifier.urihttp://hdl.handle.net/10201/198609
dc.languageeng
dc.publisherElsevier
dc.relationThis work has been sponsored by MINECO through the PERSEIDES project (ref. TIN2017-86885-R) and grant BES-2015-071956 and by the European Comission through the H2020 IoTCrawler (contract 779852) EU Project. This work was also partially funded by the Spanish Ministry of Science, Innovation and Universities under the SITUS project (Ref: RTI2018-094832-B-I00), and by the European Fund for Regional Development (EFRD, FEDER).
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectEnergy efficiency
dc.subjectTime series
dc.subjectSmart buildings
dc.subjectSmart cities
dc.subjectFeature selection
dc.subject.odsObjetivo 11: Ciudades
dc.titleA methodology for energy multivariate time series forecasting in smart buildings based on feature selection
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dspace.entity.typePublicationes
relation.isAuthorOfPublicationcf8009bf-6088-449d-9f79-a516af312945
relation.isAuthorOfPublication47706328-5460-433a-b86f-dcbcc9841c53
relation.isAuthorOfPublication7dacd587-416b-43e7-bec1-30dbb093d0a4
relation.isAuthorOfPublication.latestForDiscoverycf8009bf-6088-449d-9f79-a516af312945
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
04.option2.pdf
Size:
3.1 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.37 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos