EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nonintrusive Power Load Decomposition Based on Adaptive Graph Convolutional Neural Network

Pinzhang Zhao, Jian Wei, Lihui Wang iD, Yajuan Qiu

Sensors · 09.05.2026 · 26 (10) · 2978

DOI: 10.3390/s26102978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.05.2026. Verfasst von Pinzhang Zhao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Institute of Metrology, Nanjing 210023, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Plan Project of China State Administration for Market Regulation, Science and Technology Program Funding of Jiangsu Provincial Administration for Market Regulation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To fully exploit the correlation between the operating states of appliances, an adaptive graph convolutional neural network (AChebNet) for nonintrusive power load decomposition is proposed. An adaptive adjacency matrix is defined to characterize feature dependencies and uncover the hidden internal connectivity between features at different nodes in the graph model. This paper introduces the adaptive neighbor matrix to the Chebyshev Spectral CNN (ChebNet). By integrating a predefined neighbor matrix generated based on time intervals, we construct adaptive graph convolutions to better learn the graph structure and extract deeper hidden features. We explore the input dimensions of the model and select multiple relevant features based on the Spearman correlation coefficient to evaluate their impact on model performance. The proposed model outperformed ChebNet in experiments, achieving a 48.87% reduction in the mean absolute error (MAE) for the disaggregation of five appliances, and the mean power disaggregation accuracy improved from 87.39% to 92.74%. With multi-feature inputs, the model surpassed single-feature inputs, reducing the MAE by an additional 16.86% and increasing accuracy from 92.74% to 94.58%. Therefore, AChebNet can be effectively applied to reduce decomposition error and enhance overall accuracy in nonintrusive load decomposition.

Schlagwörter

Stichwörter der Autor:innen

adaptive adjacency matrixfeature input dimensiongraph convolutional neural networknonintrusive power load decomposition

Autor:innen und Institutionen

  • Jiangsu Institute of Metrology, Nanjing 210023, China.
  • Key Laboratory of Micro-Inertial Instrument and Advanced Navigation Technology, Ministry of Education, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China.

ORCID-Profile: Lihui Wang

Förderung

  • Science and Technology Plan Project of China State Administration for Market Regulation
  • Science and Technology Program Funding of Jiangsu Provincial Administration for Market Regulation

Zitieren

APA

Zhao, P., Wei, J., Wang, L., & Qiu, Y. (2026). Nonintrusive Power Load Decomposition Based on Adaptive Graph Convolutional Neural Network. Sensors, 26(10), 2978. https://doi.org/10.3390/s26102978

Vancouver

Zhao P, Wei J, Wang L, Qiu Y. Nonintrusive Power Load Decomposition Based on Adaptive Graph Convolutional Neural Network. Sensors. 2026;26(10):2978. doi:10.3390/s26102978

BibTeX
@article{Zhao2026,
  author = {Zhao, Pinzhang and Wei, Jian and Wang, Lihui and Qiu, Yajuan},
  title = {Nonintrusive Power Load Decomposition Based on Adaptive Graph Convolutional Neural Network},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {2978},
  doi = {10.3390/s26102978}
}
Kostenlos starten →