EUVIMEDEUVIMED entdecken
Crossref

A Heterogeneity-Aware Adaptive Federated Learning Framework for Short-Term Forecasting in Electric IoT Systems

Cheng Tong, Linghua Zhang, Yin Ding, Dong Yue

IEEE Internet of Things Journal · 01.06.2025 · 12 (11) · 15388-15403

DOI: 10.1109/jiot.2025.3528545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2025. Verfasst von Cheng Tong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Postgraduate Research and Practice Innovation Program of Jiangsu Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of Electric Internet of Things (EIoT) systems has led to an increased demand for accurate and secure methodologies capable of handling short-term energy information forecasting, which is crucial for optimizing energy management and maintaining smart grid stability. Current federated learning (FL) frameworks, however, struggle to cope with the inherent heterogeneity of devices and the constrained communication environments typical in EIoT settings. To overcome these challenges, we introduce the federated heterogeneity-aware adaptive framework (FedHA), a novel approach that combines an adaptive asynchronous federated aggregation (AAF) framework with a hierarchical knowledge distillation (HKD) strategy. The AAF framework reduces global model aggregation time and minimizes the impact of straggling clients by enabling parallel training and dynamically adjusting learning rates based on client participation. Concurrently, HKD improves the stability and consistency of model convergence, particularly in non-IID data scenarios, by distilling and leveraging knowledge from clients that most accurately represents the global gradient direction. Furthermore, we developed FedHAL, a light-weight version of FedHA, which optimizes communication efficiency, making it ideal for deployment in resource-constrained edge environments. Extensive experiments on real-world EIoT datasets confirm that FedHA outperforms existing FL algorithms in terms of both prediction accuracy and adaptability, underscoring its potential for widespread application in dynamic and diverse EIoT contexts.

Förderung

  • National Natural Science Foundation of China
  • Postgraduate Research and Practice Innovation Program of Jiangsu Province, China

Zitieren

APA

Tong, C., Zhang, L., Ding, Y., & Yue, D. (2025). A Heterogeneity-Aware Adaptive Federated Learning Framework for Short-Term Forecasting in Electric IoT Systems. IEEE Internet of Things Journal, 12(11), 15388-15403. https://doi.org/10.1109/jiot.2025.3528545

Vancouver

Tong C, Zhang L, Ding Y, Yue D. A Heterogeneity-Aware Adaptive Federated Learning Framework for Short-Term Forecasting in Electric IoT Systems. IEEE Internet of Things Journal. 2025;12(11):15388-15403. doi:10.1109/jiot.2025.3528545

BibTeX
@article{Tong2025,
  author = {Tong, Cheng and Zhang, Linghua and Ding, Yin and Yue, Dong},
  title = {A Heterogeneity-Aware Adaptive Federated Learning Framework for Short-Term Forecasting in Electric IoT Systems},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {11},
  pages = {15388--15403},
  doi = {10.1109/jiot.2025.3528545}
}
Kostenlos starten →