EUVIMEDEUVIMED entdecken
Crossref

Personalized Federated Learning for Detecting False Data Injection Attacks in Power Grids

Mengwei Lv, Ruijuan Zheng, Junlong Zhu, Yongsheng Dong, Qingtao Wu, Xuhui Zhao

Concurrency and Computation: Practice and Experience · 2026-01 · 38 (1)

DOI: 10.1002/cpe.70543 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 07.01.2026. Verfasst von Mengwei Lv und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the context of security protection against false data injection attacks (FDIAs) in power grids, traditional federated learning effectively utilizes decentralized data resources for distributed training and achieves global collaboration. However, during the model aggregation process, it often overlooks or drowns out local sparse key features, significantly increasing the risk of missed detection of specific attack patterns. To address this issue, this paper proposes a personalized detection framework based on federated learning. Initially, the bidirectional transformer detection (BTD) model detection algorithm is deployed on the client side and trained on local data. Subsequently, through personalized federated learning, the client dynamically combines the weights of the global and local models to generate a personalized detection model. The framework employs a collaborative optimization mechanism of “global knowledge sharing and local feature adaptation” to effectively mitigate the feature drowning problem while strictly safeguarding data privacy. Compared to existing methods, this approach significantly enhances detection accuracy and robustness against differentiated attack patterns, thereby establishing a more reliable security defense system for smart grids.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Lv, M., Zheng, R., Zhu, J., Dong, Y., Wu, Q., & Zhao, X. (2026). Personalized Federated Learning for Detecting False Data Injection Attacks in Power Grids. Concurrency and Computation: Practice and Experience, 38(1). https://doi.org/10.1002/cpe.70543

Vancouver

Lv M, Zheng R, Zhu J, Dong Y, Wu Q, Zhao X. Personalized Federated Learning for Detecting False Data Injection Attacks in Power Grids. Concurrency and Computation: Practice and Experience. 2026;38(1). doi:10.1002/cpe.70543

BibTeX
@article{Lv2026,
  author = {Lv, Mengwei and Zheng, Ruijuan and Zhu, Junlong and Dong, Yongsheng and Wu, Qingtao and Zhao, Xuhui},
  title = {Personalized Federated Learning for Detecting False Data Injection Attacks in Power Grids},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {1},
  doi = {10.1002/cpe.70543}
}
Kostenlos starten →