Non-intrusive Load Identification Algorithm Based on Stacking Modeling

The non-intrusive power load identification relies on the smart meter’s voltage, current and power signals, which can realize the classification and monitoring of the domestic electric load. The load identification algorithm is the core of the system. Non-intrusive power load intelligent identificat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series Jg. 2418; H. 1; S. 12106 - 12111
Hauptverfasser: Miao, Weiwei, Zeng, Zeng, Teng, Changzhi, Zhang, Rui, Li, Shihao, Bi, Sibo, Wang, Jijun, Zhou, Haocheng, Li, Fubao, Zhang, Yongze
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bristol IOP Publishing 01.02.2023
Schlagworte:
Accuracy
Algorithms
Decomposition
Electrical loads
Machine learning
Markov chains
Model accuracy
Modelling
Monitoring
Physics
Stacking
ISSN:1742-6588, 1742-6596
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The non-intrusive power load identification relies on the smart meter’s voltage, current and power signals, which can realize the classification and monitoring of the domestic electric load. The load identification algorithm is the core of the system. Non-intrusive power load intelligent identification systems are generally based on a single model for aggregation, and commonly used models include hidden Markov models, graphical models and deep learning models. Usually, a single model is only effective in identifying certain types of electrical loads, and its universality and generality need to be improved. Improving the decomposition accuracy of the model is the main purpose of implementing non-intrusive powerload monitoring. The stacking integration algorithm is used to optimize the non-intrusive powerload monitoring model. The stacking integration model is divided into two layers. The base model initially decomposes the load and realizes the load accuracy through the meta-model. Experiment results show that the non-intrusive load identification algorithm based on Stacking modeling proposed in this paper can accurately decompose the minute-level sampled data. Compared to a single model, the decomposition accuracy of this method is improved by 8.2%.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2418/1/012106