Hybrid CNN–Transformer Network for Electricity Theft Detection in Smart Grids
Sensors · 12.10.2023 · 23 (20) · 8405
DOI: 10.3390/s23208405 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.10.2023. Verfasst von Yu Bai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Liaoning Province Education Administration.
Abstract (Originalsprache)
Illicitly obtaining electricity, commonly referred to as electricity theft, is a prominent contributor to power loss. In recent years, there has been growing recognition of the significance of neural network models in electrical theft detection (ETD). Nevertheless, the existing approaches have a restricted capacity to acquire profound characteristics, posing a persistent challenge in reliably and effectively detecting anomalies in power consumption data. Hence, the present study puts forth a hybrid model that amalgamates a convolutional neural network (CNN) and a transformer network as a means to tackle this concern. The CNN model with a dual-scale dual-branch (DSDB) structure incorporates inter- and intra-periodic convolutional blocks to conduct shallow feature extraction of sequences from varying dimensions. This enables the model to capture multi-scale features in a local-to-global fashion. The transformer module with Gaussian weighting (GWT) effectively captures the overall temporal dependencies present in the electricity consumption data, enabling the extraction of sequence features at a deep level. Numerous studies have demonstrated that the proposed method exhibits enhanced efficiency in feature extraction, yielding high F1 scores and AUC values, while also exhibiting notable robustness.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronical and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China.
ORCID-Profile: Lili Zhang
Förderung
- Liaoning Province Education Administration
Zitieren
APA
Bai, Y., Sun, H., Zhang, L., & Wu, H. (2023). Hybrid CNN–Transformer Network for Electricity Theft Detection in Smart Grids. Sensors, 23(20), 8405. https://doi.org/10.3390/s23208405
Vancouver
Bai Y, Sun H, Zhang L, Wu H. Hybrid CNN–Transformer Network for Electricity Theft Detection in Smart Grids. Sensors. 2023;23(20):8405. doi:10.3390/s23208405
BibTeX
@article{Bai2023,
author = {Bai, Yu and Sun, Haitong and Zhang, Lili and Wu, Haoqi},
title = {Hybrid CNN–Transformer Network for Electricity Theft Detection in Smart Grids},
journal = {Sensors},
year = {2023},
volume = {23},
number = {20},
pages = {8405},
doi = {10.3390/s23208405}
}
EUVIMED