Unsupervised recognition and prediction of daily patterns in heating loads in buildings

Vista sencilla de ítem
dc.contributor.author Lumbreras Mugaguren, Mikel
dc.contributor.authorDiarce Belloso, Gonzalo
dc.contributor.authorMartín Escudero, Koldobika
dc.contributor.authorGaray Martínez, Roberto
dc.contributor.authorArregi, Beñat
dc.date.accessioned2025-06-19T12:43:30Z
dc.date.available2025-06-19T12:43:30Z
dc.date.issued2023-04-15
dc.date.updated2025-06-19T12:43:30Z
dc.description.abstractThis paper presents a multistep methodology combining unsupervised and supervised learning techniques for the identification of the daily heating energy consumption patterns in buildings. The relevant number of typical profiles is obtained through unsupervised clustering processes. Then Classification and Regression Trees are used to predict the profile type corresponding to external variables, including calendar and climatic variables, from any given day. The methodology is tested with a variety of datasets for three different buildings with different uses connected to the district heating network in Tartu (Estonia). The three buildings under analysis present different energy behaviors (residential, kindergarten and commercial buildings). The paper shows that unsupervised clustering is effective for pattern recognition since the results from the classification and regression trees match the results from the unsupervised clustering. Three main patterns have been identified in each building, seasonality and daily mean temperature being the variables that have the greatest effect. The results concluded that the best classification accuracy is obtained with a small number of clusters with a classification accuracy from 0.7 to 0.85, approximately.en
dc.description.sponsorshipThe authors would like to acknowledge the Spanish Ministry of Science and Innovation (MICINN) for funding through the Sweet-TES research project (RTI2018-099557-B-C22). This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 768567en
dc.identifier.citationLumbreras, M., Diarce, G., Martin, K., Garay-Martinez, R., & Arregi, B. (2023). Unsupervised recognition and prediction of daily patterns in heating loads in buildings. Journal of Building Engineering, 65. https://doi.org/10.1016/J.JOBE.2022.105732
dc.identifier.doi10.1016/J.JOBE.2022.105732
dc.identifier.eissn2352-7102
dc.identifier.urihttps://hdl.handle.net/20.500.14454/3101
dc.language.isoeng
dc.publisherElsevier Ltd
dc.rights© 2022 The Authors
dc.subject.otherDaily profiles
dc.subject.otherHeating loads
dc.subject.otherPattern recognition
dc.subject.otherUnsupervised clustering
dc.titleUnsupervised recognition and prediction of daily patterns in heating loads in buildingsen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleJournal of Building Engineering
oaire.citation.volume65
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
lumbreras_unsupervised_2023.pdf
Tamaño:
10.08 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos