Enhancing anomaly detection in distributed power systems using autoencoder-based federated learning
PLOS ONE · 18.08.2023 · 18 (8) · e0290337
DOI: 10.1371/journal.pone.0290337 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 18.08.2023. Verfasst von Kimleang Kea und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of AI Convergence, Pukyong National University, Nam-gu, Busan, South Korea. Hauptthemen laut MEDLINE: Computer Communication Networks, Internet. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Research.
Abstract (Originalsprache)
The growing use of Internet-of-Things devices in electric power systems has resulted in increased complexity and flexibility, making monitoring power usage critical for effective system maintenance and detecting abnormal behavior. However, traditional anomalous power consumption detection methods struggle to handle the vast amounts of data generated by these devices. While deep learning and machine learning are effective in anomaly detection, they require significant amounts of training data collected on centralized servers. This centralized approach results in high response time delays and data leakage problems. To address these challenges, we propose an Autoencoder-based Federated Learning method that combines the AutoEncoder and Federated Learning networks to develop a high-accuracy algorithm for identifying anomalies of power consumption data in distributed power systems. The proposed method allows for decentralized training of anomaly detection models among IoT devices, reducing response time and eventually solving data leakage issues. Our experimental results demonstrate the effectiveness of the FLAE method in detecting anomalies without needing data transferring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of AI Convergence, Pukyong National University, Nam-gu, Busan, South Korea.
- Department of Computer & Information Technology, Incheon Jaeneung University, Dong-gu, Incheon, South Korea.
ORCID-Profile: Kimleang Kea, Tae-Kyung Kim
Förderung
- Korea Institute of Energy Research
Zitieren
APA
Kea, K., Han, Y., & Kim, T. K. (2023). Enhancing anomaly detection in distributed power systems using autoencoder-based federated learning. PLOS ONE, 18(8), e0290337. https://doi.org/10.1371/journal.pone.0290337
Vancouver
Kea K, Han Y, Kim TK. Enhancing anomaly detection in distributed power systems using autoencoder-based federated learning. PLOS ONE. 2023;18(8):e0290337. doi:10.1371/journal.pone.0290337
BibTeX
@article{Kea2023,
author = {Kea, Kimleang and Han, Youngsun and Kim, Tae-Kyung},
title = {Enhancing anomaly detection in distributed power systems using autoencoder-based federated learning},
journal = {PLOS ONE},
year = {2023},
volume = {18},
number = {8},
pages = {e0290337},
doi = {10.1371/journal.pone.0290337}
}
EUVIMED