Stage-oe-small.jpg

Article3171: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 20: Zeile 20:
 
}}
 
}}
 
{{Article
 
{{Article
|Referiert=True
+
|Referiert=Ja
 
|Title=Modeling flexibility using artificial neural networks
 
|Title=Modeling flexibility using artificial neural networks
 
|Year=2018
 
|Year=2018
 
|Month=Oktober
 
|Month=Oktober
 
|Journal=Energy Informatics
 
|Journal=Energy Informatics
|Volume=1
+
|Volume=1 (S1)
|Number=S1
 
 
|Pages=21
 
|Pages=21
 
|Publisher=Springer Open
 
|Publisher=Springer Open
Zeile 34: Zeile 33:
 
|ISSN=2520-8942
 
|ISSN=2520-8942
 
|DOI Name=10.1186/s42162-018-0024-4
 
|DOI Name=10.1186/s42162-018-0024-4
|Projekt=C/sells, ENSURE, Grid-control, KASTEL
+
|Projekt=CSells
|Forschungsgruppe=Effiziente Algorithmen
+
|Forschungsgruppe=Effiziente Algorithmen/en
 +
}}
 +
{{Forschungsgebiet Auswahl
 +
|Forschungsgebiet=Energieinformatik
 
}}
 
}}

Aktuelle Version vom 24. August 2021, 19:41 Uhr


Modeling flexibility using artificial neural networks


Modeling flexibility using artificial neural networks



Veröffentlicht: 2018 Oktober

Journal: Energy Informatics

Seiten: 21
Verlag: Springer Open
Volume: 1 (S1)


Referierte Veröffentlichung

BibTeX




Kurzfassung
The flexibility of distributed energy resources (DERs) can be modeled in various ways. Each model that can be used for creating feasible load profiles of a DER represents a potential model for the flexibility of that particular DER. Based on previous work, this paper presents generalized patterns for exploiting such models. Subsequently, the idea of using artificial neural networks in such patterns is evaluated. We studied different types and topologies of ANNs for the presented realization patterns and multiple device configurations, achieving a remarkably precise representation of the given devices in most of the cases. Overall, there was no single best ANN topology. Instead, a suitable individual topology had to be found for every pattern and device configuration. In addition to the best performing ANNs for each pattern and configuration that is presented in this paper all data from our experiments is published online. The paper is concluded with an evaluation of a classification based pattern using data of a real combined heat and power plant in a smart building.

ISSN: 2520-8942
DOI Link: 10.1186/s42162-018-0024-4

Projekt

CSells



Forschungsgruppe

Effiziente Algorithmen/en


Forschungsgebiet

Energieinformatik