FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks
Sensors · 29.03.2023 · 23 (7) · 3570
DOI: 10.3390/s23073570 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2023. Verfasst von Habib Ullah Manzoor und 6 weiteren Autor:innen. Beteiligte Einrichtung: James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon 2020 Research programme.
Abstract (Originalsprache)
Increased demand for fast edge computation and privacy concerns have shifted researchers’ focus towards a type of distributed learning known as federated learning (FL). Recently, much research has been carried out on FL; however, a major challenge is the need to tackle the high diversity in different clients. Our research shows that using highly diverse data sets in FL can lead to low accuracy of some local models, which can be categorised as anomalous behaviour. In this paper, we present FedBranched, a clustering-based framework that uses probabilistic methods to create branches of clients and assigns their respective global models. Branching is performed using hidden Markov model clustering (HMM), and a round of branching depends on the diversity of the data. Clustering is performed on Euclidean distances of mean absolute percentage errors (MAPE) obtained from each client at the end of pre-defined communication rounds. The proposed framework was implemented on substation-level energy data with nine clients for short-term load forecasting using an artificial neural network (ANN). FedBranched took two clustering rounds and resulted in two different branches having individual global models. The results show a substantial increase in the average MAPE of all clients; the biggest improvement of 11.36% was observed in one client.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK.
- Department of Electrical Engineering, University of Engineering and Technology, Lahore-Faisalabad Campus, Faisalabad 38000, Pakistan.
- Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, 19086 Tallinn, Estonia.
ORCID-Profile: Habib Ullah Manzoor, Ahsan Raza Khan, David Flynn, Muhammad Mahtab Alam, Muhammad Ali Imran, Ahmed Zoha
Förderung
- European Union’s Horizon 2020 Research programme
Zitieren
APA
Manzoor, H. U., Khan, A. R., Flynn, D., Alam, M. M., Akram, M., Imran, M. A., & Zoha, A. (2023). FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks. Sensors, 23(7), 3570. https://doi.org/10.3390/s23073570
Vancouver
Manzoor HU, Khan AR, Flynn D, Alam MM, Akram M, Imran MA, et al. FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks. Sensors. 2023;23(7):3570. doi:10.3390/s23073570
BibTeX
@article{Manzoor2023,
author = {Manzoor, Habib Ullah and Khan, Ahsan Raza and Flynn, David and Alam, Muhammad Mahtab and Akram, Muhammad and Imran, Muhammad Ali and Zoha, Ahmed},
title = {FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks},
journal = {Sensors},
year = {2023},
volume = {23},
number = {7},
pages = {3570},
doi = {10.3390/s23073570}
}
EUVIMED