Zur Kurzanzeige

Heat Load Profiles in Industry and the Tertiary Sector: Correlation with Electricity Consumption and Ex Post Modeling

dc.date.accessioned2022-05-30T13:42:26Z
dc.date.available2022-05-30T13:42:26Z
dc.date.issued2022-03-29
dc.identifierdoi:10.17170/kobra-202205176194
dc.identifier.urihttp://hdl.handle.net/123456789/13876
dc.description.sponsorshipGefördert durch den Publikationsfonds der Universität Kasselger
dc.language.isoengeng
dc.rightsNamensnennung 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectload profileseng
dc.subjectelectricityeng
dc.subjectheateng
dc.subjectindustryeng
dc.subjectcorrelationeng
dc.subjectmachine learningeng
dc.subjectLSTMeng
dc.subjectpredictioneng
dc.subjectanomaly detectioneng
dc.subject.ddc600
dc.titleHeat Load Profiles in Industry and the Tertiary Sector: Correlation with Electricity Consumption and Ex Post Modelingeng
dc.typeAufsatz
dcterms.abstractThe accurate prediction of heat load profiles with a daily resolution is required for a broad range of applications, such as potential studies, design, or predictive operation of heating systems. If the heat demand of a consumer mainly originates from (production) processes independent of the ambient temperature, existing load profile prediction methods fail. To close this gap, this study develops two ex post machine learning models for the prediction of the heat demand with a daily resolution. The selected input features are commonly available to each consumer connected to public natural gas and electricity grids or operating an energy monitoring system: Ambient temperature, weekday, electricity consumption, and heat consumption of the last seven days directly before the predicted day. The study’s database covers electricity and natural gas consumption load profiles from 82 German consumers over a period of two years. Electricity and heat consumption correlate strongly with individual patterns for many consumers. Both shallow and deep learning algorithms from the Python libraries Scikit-Learn and Keras are evaluated. A Long Short-Term Memory (LSTM) model achieves the best results (the median of R2 is 0.94). The ex post model architecture makes the model suitable for anomaly detection in energy monitoring systems.eng
dcterms.accessRightsopen access
dcterms.creatorJesper, Mateo
dcterms.creatorPag, Felix
dcterms.creatorVajen, Klaus
dcterms.creatorJordan, Ulrike
dc.relation.doidoi:10.3390/su14074033
dc.relation.issupplementedbydoi:10.48662/daks-9
dc.subject.swdLastprofilger
dc.subject.swdElektrizitätger
dc.subject.swdHitzeger
dc.subject.swdIndustrieger
dc.subject.swdMaschinelles Lernenger
dc.subject.swdPrognoseger
dc.subject.swdAnomalieerkennungger
dc.type.versionpublishedVersion
dcterms.source.identifiereissn:2071-1050
dcterms.source.issueIssue 7
dcterms.source.journalSustainabilityeng
dcterms.source.volumeVolume 14
kup.iskupfalse
dcterms.source.articlenumber4033


Dateien zu dieser Ressource

Thumbnail
Name:
license_rdf
Größe:
908Bytes
Format:
application/rdf+xml
Öffnen
Thumbnail
Name:
sustainability_14_04033_v2.pdf
Größe:
8.344Mb
Format:
PDF
Öffnen

Das Dokument erscheint in:

Zur Kurzanzeige

Namensnennung 4.0 International
Solange nicht anders angezeigt, wird die Lizenz wie folgt beschrieben: Namensnennung 4.0 International