Research on the provincial-level centralized function of integrating neural networks with electricity billing data analysis

Fangchu Zhao, Xin Su, Xiaoxiao Lu, Feiya Si, Lingling Lang and Wenlei Sun

International Journal of Low-Carbon Technologies, 2025, vol. 20, 1-22

Abstract: This paper proposes a provincial-scale system integrating neural networks with electricity rate data analysis to enhance prediction accuracy and anomaly detection efficiency while ensuring user privacy. At its core is the electric rate analysis neural network (EANN), which combines LSTM and GCN to effectively capture the temporal dynamics of billing data and the relational structure among users. The system also introduces a privacy protection scheme based on personalized federated learning for secure cross-regional analysis. Experiments show that EANN improves prediction accuracy by 2.3% and reduces computational latency by 6.3% compared to traditional CNN–LSTM methods.

Keywords: electricity bill management; neural network; LSTM; GCN; federated learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctae283 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:20:y:2025:i::p:1-22.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().