CVAE-Transformer-based industrial short-term load forecasting

Accurate industrial load forecasting is essential for maintaining a balance between power supply and demand within intelligent power systems. In response to the challenges presented by the intricate, nonlinear, and temporal nature of industrial load data, a novel method integrating a Conditional Var...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series Jg. 3043; H. 1; S. 12149 - 12154
Hauptverfasser: Li, Jiawei, Wang, Yuanyuan, Liu, Yonghuan, Liao, Xiaoyu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bristol IOP Publishing 01.06.2025
Schlagworte:
Electrical loads
Feature extraction
Forecasting
ISSN:1742-6588, 1742-6596
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Accurate industrial load forecasting is essential for maintaining a balance between power supply and demand within intelligent power systems. In response to the challenges presented by the intricate, nonlinear, and temporal nature of industrial load data, a novel method integrating a Conditional Variational Autoencoder (CVAE) with a Transformer is introduced. The CVAE, conditioned on meteorological and economic data, excels in precise feature extraction from load data, effectively identifying critical patterns that influence load behavior. This specialized feature extraction is complemented by the Transformer, which refines the understanding of complex load dynamics through its temporal encoding and attention mechanisms. Experimental results using datasets from China and South Korea reveal substantial enhancements in forecasting precision compared to current models
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/3043/1/012149