EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Affinity-Driven Transfer Learning for Load Forecasting

Ahmed Rebei iD, Manar Amayri iD, Nizar Bouguila iD

Sensors · 06.09.2024 · 24 (17) · 5802

DOI: 10.3390/s24175802 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.09.2024. Verfasst von Ahmed Rebei und 2 weiteren Autor:innen. Beteiligte Einrichtung: Concordia Institute for Information Systems Engineering, Montreal, QC H3G1M8, Canada. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of 438 Canada (NSERC), Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, we introduce an innovative method for load forecasting that capitalizes on the concept of task affinity score to measure the similarity between various tasks. The task affinity score emerges as a superior technique for assessing task similarity within the realm of transfer learning. Through empirical evaluation on a synthetic dataset, we establish the superiority of the task affinity score over traditional metrics in task selection scenarios. To operationalize this method, we unveil the Affinity-Driven Transfer Learning (ADTL) algorithm to enhance load forecasting precision. The ADTL algorithm enriches the transfer learning framework by incorporating insights from both pre-trained models and datasets, thereby augmenting the accuracy of load forecasting for new and unseen datasets. The robustness of the ADTL algorithm is further evidenced through its application to two empirical datasets, namely the dataset provided by the Australian Energy Market Operator (AEMO) and the Smart Australian dataset. In conclusion, our research underscores the important role of the task affinity score in refining transfer learning methodologies for load forecasting applications.

Schlagwörter

Stichwörter der Autor:innen

load forecastingtask affinity scoretransfer learning

Autor:innen und Institutionen

  • Concordia Institute for Information Systems Engineering, Montreal, QC H3G1M8, Canada.

ORCID-Profile: Ahmed Rebei, Manar Amayri, Nizar Bouguila

Förderung

  • Natural Sciences and Engineering Research Council of 438 Canada (NSERC)
  • Natural Sciences and Engineering Research Council of Canada (NSERC)

Zitieren

APA

Rebei, A., Amayri, M., & Bouguila, N. (2024). Affinity-Driven Transfer Learning for Load Forecasting. Sensors, 24(17), 5802. https://doi.org/10.3390/s24175802

Vancouver

Rebei A, Amayri M, Bouguila N. Affinity-Driven Transfer Learning for Load Forecasting. Sensors. 2024;24(17):5802. doi:10.3390/s24175802

BibTeX
@article{Rebei2024,
  author = {Rebei, Ahmed and Amayri, Manar and Bouguila, Nizar},
  title = {Affinity-Driven Transfer Learning for Load Forecasting},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {17},
  pages = {5802},
  doi = {10.3390/s24175802}
}
Kostenlos starten →