EUVIMEDEUVIMED entdecken
Crossref

A Lightweight Edge-Deployable ANN Model for Real-Time Energy Anomaly Detection in IoT-Driven Smart Grids

Sofiane Benabbes, Wael Aissaoui, Rabah Boucetti

Informatica · 13.04.2026 · 50 (1)

DOI: 10.31449/inf.v50i1.12670 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatica, online erschienen am 13.04.2026. Verfasst von Sofiane Benabbes und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of the Internet of Things (IoT) in smart cities has necessitated efficient, real-time energy anomaly detection. However, complex hybrid deep learning models often exceed the computational capacity of Edge devices. This paper proposes a lightweight, 3-layer Artificial Neural Network (ANN) framework designed for Edge deployment. Using the LEAD (Large-scale Energy Anomaly Detection) dataset, we address class imbalance via the Synthetic Minority Over-sampling Technique (SMOTE). Our model achieves 98.4% accuracy, a macro F1-score of 0.93, and an AUC of 0.91. While these metrics are competitive with state-of-the-art hybrid models, our framework provides a significantly lower memory footprint and sub-millisecond inference latency, making it ideal for resource-constrained Edge environments.

Zitieren

APA

Benabbes, S., Aissaoui, W., & Boucetti, R. (2026). A Lightweight Edge-Deployable ANN Model for Real-Time Energy Anomaly Detection in IoT-Driven Smart Grids. Informatica, 50(1). https://doi.org/10.31449/inf.v50i1.12670

Vancouver

Benabbes S, Aissaoui W, Boucetti R. A Lightweight Edge-Deployable ANN Model for Real-Time Energy Anomaly Detection in IoT-Driven Smart Grids. Informatica. 2026;50(1). doi:10.31449/inf.v50i1.12670

BibTeX
@article{Benabbes2026,
  author = {Benabbes, Sofiane and Aissaoui, Wael and Boucetti, Rabah},
  title = {A Lightweight Edge-Deployable ANN Model for Real-Time Energy Anomaly Detection in IoT-Driven Smart Grids},
  journal = {Informatica},
  year = {2026},
  volume = {50},
  number = {1},
  doi = {10.31449/inf.v50i1.12670}
}
Kostenlos starten →