Multi-source domain generalization deep neural network model for predicting energy consumption in multiple office buildings

The effective prediction of building energy consumption can be used to optimize building operating modes and reduce the overall energy consumption and carbon emission of the building. To predict the energy consumption of the same type of building in the same area, it is often necessary to train sepa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy (Oxford) Jg. 299; S. 131467
Hauptverfasser: Jiang, Ben, Li, Yu, Rezgui, Yacine, Zhang, Chengyu, Wang, Peng, Zhao, Tianyi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 15.07.2024
Schlagworte:
carbon
data collection
Deep neural network
domain
Encoder and decoder architecture
energy
Energy consumption prediction
Multi-source domain generalization
neural networks
Office buildings
prediction
Deep neural network
Multi-source domain generalization
Encoder and decoder architecture
Energy consumption prediction
Office buildings
ISSN:0360-5442
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The effective prediction of building energy consumption can be used to optimize building operating modes and reduce the overall energy consumption and carbon emission of the building. To predict the energy consumption of the same type of building in the same area, it is often necessary to train separate prediction models for different buildings, which is usually costly computationally in order to get better prediction results. Therefore, this study will combine deep neural networks and multi-source domain generalization in an encoder-decoder architecture to train a model that can be directly applied to predict the energy consumption of multiple buildings in same type. In order to validate the predictive effectiveness of the model, it will be tested on real office building energy consumption dataset and different comparative experiments will be designed on the source and target domains. The results show that the constructed multi-source domain generalization model is able to accurately predict the energy consumption trend of different buildings 1 h in advance. It also has some energy consumption prediction ability for the unknow training set of buildings. •Combining encoder and decoder architectures to build deep neural networks•Combining TDC and deep neural networks to train generalization model•Model training and testing using real office building energy consumption datasets•Setting up different comparison experiments on the source and target domains
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0360-5442
DOI:10.1016/j.energy.2024.131467