EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust and Communication-Efficient Personalized Federated Learning for False Power Consumption Detection in Heterogeneous Smart Grids

Islam Elgarhy, Mahmoud Badr, Mohamed Mahmoud, Randa F. Soliman, Jianbing Ni, Tariq Alshawi

Energies · 10.11.2026 · 19 (22) · 5392

DOI: 10.3390/en19225392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 10.11.2026. Verfasst von Islam Elgarhy und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Saud University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting false power consumption data injection (FDI) attacks requires utilities to collaborate without sharing consumers’ raw data. Federated learning (FL) enables such collaboration. However, conventional FL exchanges complete models in every round and loses accuracy when the utilities’ data are not independent and identically distributed (non-IID). It also produces a shared detector that a malicious participant can exploit to craft evasion attacks. This paper proposes a personalized federated learning (PFL) approach in which utilities jointly train convolutional feature-extraction layers while keeping their classification layers local. Adversarial examples are incorporated into local training to improve resistance to evasion. The approach requires a single model per utility and no public dataset at the server. We evaluate it on the Ausgrid and Irish Smart Energy Trial datasets, with utilities that differ in both consumption patterns and attack characteristics. Compared with conventional FL, the proposed approach reduces the data exchanged per round and utility from 306.63 KB to 3.50 KB. With adversarial training, it improves accuracy by up to 23.75 and 29.82 percentage points on Ausgrid and ISET, respectively, and lowers the success rates of the evaluated FGSM and BIM attacks. These results show that personalization can ease the accuracy–robustness trade-off while substantially reducing communication costs.

Förderung

  • King Saud University

Zitieren

APA

Elgarhy, I., Badr, M., Mahmoud, M., Soliman, R. F., Ni, J., & Alshawi, T. (2026). Robust and Communication-Efficient Personalized Federated Learning for False Power Consumption Detection in Heterogeneous Smart Grids. Energies, 19(22), 5392. https://doi.org/10.3390/en19225392

Vancouver

Elgarhy I, Badr M, Mahmoud M, Soliman RF, Ni J, Alshawi T. Robust and Communication-Efficient Personalized Federated Learning for False Power Consumption Detection in Heterogeneous Smart Grids. Energies. 2026;19(22):5392. doi:10.3390/en19225392

BibTeX
@article{Elgarhy2026,
  author = {Elgarhy, Islam and Badr, Mahmoud and Mahmoud, Mohamed and Soliman, Randa F. and Ni, Jianbing and Alshawi, Tariq},
  title = {Robust and Communication-Efficient Personalized Federated Learning for False Power Consumption Detection in Heterogeneous Smart Grids},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {22},
  pages = {5392},
  doi = {10.3390/en19225392}
}
Kostenlos starten →