.png){kind=icon}
.png){kind=icon}
Return
ECLAR-Net: An expert-guided contrastive learning and adaptive reasoning network for robust electricity theft detection
.png){kind=icon}
PRE
AI
Y
F
J
Q
DOI：10.1016/j.apenergy.2026.128599.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A data-driven framework is proposed for detecting electricity theft in AMI-based distribution systems. • Expert-guided anomaly injection enhances sensitivity to concealed and long-tail non-technical-loss behaviors. • Hybrid structural–sequential learning captures multi-scale consumption patterns for robust theft discrimination. • Tests on real SGCC data demonstrate strong potential for loss monitoring, inspection support, and grid operation analytics.
Journal
IF:
11
Papers:
2.6W
Citations:
17.8W
Organization
No organization information available
Cited Papers