Repository logo
 
Publication

Multivariate time series clustering and forecasting for building energy analysis: Application to weather data quality control

2021Journal article Restricted access
Simple item page
dc.contributor.authorSanhudo, Luís
dc.contributor.authorCoelho Rodrigues, João Manuel
dc.contributor.authorVasconcelos Filho, Ênio
dc.date.accessioned2021-02-25T14:28:18Z
dc.date.embargo2120
dc.date.issued2021
dc.description.abstractIn recent years, several tools for building energy analysis and simulation have been developed to assist in increasing building energy performance, harvesting its computing capabilities for a reliable and accurate energy performance prediction. To perform this analysis, energy tools typically require crucial data regarding the building's surrounding environment, which is acquired from neighbouring weather stations. However, these stations often experience hardware malfunctions, resulting in either erroneous or missing data. Traditionally, these values are rectified through empirical and geostatistical methods, which, while reflecting several decades of practice, may prove to be inadequate when considering a purely data-driven approach. To this end, the present study introduces a machine learning methodology proposing the application of regression algorithms to rectify the erroneous values in datasets, and the clustering of weather stations, based on their recorded climatic conditions, to enhance the regression models. A shape-based approach for clustering time series of different climatic parameters and weather stations is pursued, using the k-medoids algorithm alongside dynamic time warping as the similarity measure. Both Artificial Neural Networks (ANN) and Support Vector Regression (SVR) models are evaluated as exemplary regression algorithms, with different sets of predictors. Mean Squared Error is used as the performance metric. A data set of different climatic parameters from southeastern Brazil was used, with air temperature being chosen as the response variable, given its importance in energy consumption. Results indicate that a machine learning approach to the problem is indeed viable. ANN slightly outperforms SVR in the prediction of the studied weather variable.Building energy analysispt_PT
dc.description.sponsorshipThis work was partially financially supported by UID/ECI/04708/ 2019 – CONSTRUCT –Instituto de I&D em Estruturas e Construções and UIDB/04234/2020 – CISTER Research Unit, both funded by national funds through the FCT/MCTES (PIDDAC).pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1016/j.jobe.2020.101996pt_PT
dc.identifier.issn2352-7102
dc.identifier.urihttp://hdl.handle.net/10400.22/17149
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherElsevierpt_PT
dc.relationCISTER Research Unit, ref. UIDB/04234/2020pt_PT
dc.relationUID/ECI/04708/ 2019pt_PT
dc.relation.publisherversionhttps://www.sciencedirect.com/science/article/abs/pii/S2352710220336287pt_PT
dc.subjectBuilding energy analysispt_PT
dc.subjectWeather data quality controlpt_PT
dc.subjectTime series clusteringpt_PT
dc.subjectArtificial neural networkspt_PT
dc.subjectSupport vector regressionpt_PT
dc.titleMultivariate time series clustering and forecasting for building energy analysis: Application to weather data quality controlpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage10pt_PT
oaire.citation.issue2021pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleJournal of Building Engineeringpt_PT
oaire.citation.volume35pt_PT
person.familyNameVasconcelos Filho
person.givenNameÊnio
person.identifier.ciencia-idAC16-F8BD-0A1D
person.identifier.orcid0000-0001-5459-6821
person.identifier.ridV-8255-2017
rcaap.rightsclosedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationd3dace3e-3d1c-419f-9243-31cfbcd03839
relation.isAuthorOfPublication.latestForDiscoveryd3dace3e-3d1c-419f-9243-31cfbcd03839

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
ART_CISTER_Enio_2021.pdf
Size:
3.71 MB
Format:
Adobe Portable Document Format
Download

Collections

ISEP – CISTER – Artigos