Cargando…
FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks
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 differen...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098660/ https://www.ncbi.nlm.nih.gov/pubmed/37050631 http://dx.doi.org/10.3390/s23073570 |
_version_ | 1785024863383060480 |
---|---|
author | Manzoor, Habib Ullah Khan, Ahsan Raza Flynn, David Alam, Muhammad Mahtab Akram, Muhammad Imran, Muhammad Ali Zoha, Ahmed |
author_facet | Manzoor, Habib Ullah Khan, Ahsan Raza Flynn, David Alam, Muhammad Mahtab Akram, Muhammad Imran, Muhammad Ali Zoha, Ahmed |
author_sort | Manzoor, Habib Ullah |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-10098660 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100986602023-04-14 FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks Manzoor, Habib Ullah Khan, Ahsan Raza Flynn, David Alam, Muhammad Mahtab Akram, Muhammad Imran, Muhammad Ali Zoha, Ahmed Sensors (Basel) Article 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. MDPI 2023-03-29 /pmc/articles/PMC10098660/ /pubmed/37050631 http://dx.doi.org/10.3390/s23073570 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Manzoor, Habib Ullah Khan, Ahsan Raza Flynn, David Alam, Muhammad Mahtab Akram, Muhammad Imran, Muhammad Ali Zoha, Ahmed FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title | FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title_full | FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title_fullStr | FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title_full_unstemmed | FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title_short | FedBranched: Leveraging Federated Learning for Anomaly-Aware Load Forecasting in Energy Networks |
title_sort | fedbranched: leveraging federated learning for anomaly-aware load forecasting in energy networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10098660/ https://www.ncbi.nlm.nih.gov/pubmed/37050631 http://dx.doi.org/10.3390/s23073570 |
work_keys_str_mv | AT manzoorhabibullah fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT khanahsanraza fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT flynndavid fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT alammuhammadmahtab fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT akrammuhammad fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT imranmuhammadali fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks AT zohaahmed fedbranchedleveragingfederatedlearningforanomalyawareloadforecastinginenergynetworks |