TU Darmstadt / ULB / TUbiblio

Probabilistic Forecast Combination for Anomaly Detection in Building Heat Load Time Series

Beykirch, Mario ; Janke, Tim ; Tayeche, Imed ; Steinke, Florian (2021)
Probabilistic Forecast Combination for Anomaly Detection in Building Heat Load Time Series.
2021 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). virtual Conference (18.-21.10.2021)
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

We consider the problem of automated anomaly detection for building level heat load time series. An anomaly detection model must be applicable to a diverse group of buildings and provide robust results on heat load time series with low signal-to-noise ratios, several seasonalities, and significant exogenous effects. We propose to employ a probabilistic forecast combination approach based on an ensemble of deterministic forecasts in an anomaly detection scheme that classifies observed values based on their probability under a predictive distribution. We show empirically that forecast based anomaly detection provides improved accuracy when employing a forecast combination approach.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2021
Autor(en): Beykirch, Mario ; Janke, Tim ; Tayeche, Imed ; Steinke, Florian
Art des Eintrags: Bibliographie
Titel: Probabilistic Forecast Combination for Anomaly Detection in Building Heat Load Time Series
Sprache: Englisch
Publikationsjahr: 2021
Veranstaltungstitel: 2021 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)
Veranstaltungsort: virtual Conference
Veranstaltungsdatum: 18.-21.10.2021
Zugehörige Links:
Kurzbeschreibung (Abstract):

We consider the problem of automated anomaly detection for building level heat load time series. An anomaly detection model must be applicable to a diverse group of buildings and provide robust results on heat load time series with low signal-to-noise ratios, several seasonalities, and significant exogenous effects. We propose to employ a probabilistic forecast combination approach based on an ensemble of deterministic forecasts in an anomaly detection scheme that classifies observed values based on their probability under a predictive distribution. We show empirically that forecast based anomaly detection provides improved accuracy when employing a forecast combination approach.

Freie Schlagworte: EnEff Campus LW
Fachbereich(e)/-gebiet(e): 18 Fachbereich Elektrotechnik und Informationstechnik
18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik > Energieinformationsnetze und Systeme (EINS)
18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik
Forschungsfelder
Forschungsfelder > Energy and Environment
Forschungsfelder > Energy and Environment > Integrated Energy Systems
Hinterlegungsdatum: 26 Jul 2021 10:56
Letzte Änderung: 09 Mai 2022 12:02
PPN:
Zugehörige Links:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen