EUVIMEDEUVIMED entdecken
Crossref

Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM

Dawid Połap, Gautam Srivastava, Antoni Jaszcz

IEEE Transactions on Consumer Electronics · 2024-02 · 70 (1) · 990-999

DOI: 10.1109/tce.2023.3325941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2024-02. Verfasst von Dawid Połap und 2 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Silesian University of Technology, Poland, Natural Sciences and Engineering Research Council of Canada (NSERC) through the Discovery Grants Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid pace of development of the Internet of Things (IoT) and the requirements of various devices have allowed calculations to be performed at the edge, especially in terms of consumer electronics. Such progress makes it possible to design new solutions for energy distribution and prediction for smart homes. In this paper, we propose a solution that can be used to optimize energy distribution by analyzing energy demand in individual homes. The proposed methodology is based on edge technology, where a dedicated LSTM network with a multi-head self-attention network is trained with measurement data from different sensors for predicting energy demand. Training of this network is extended to a decentralized learning process with an additional aggregation decision module (that allows rejection of the model is added when the adaption of private data is poor). In order to increase data security, a blockchain network is added with a Byzantine strategy and Proof of Stake (PoS) consensus. The solution is tested on a publicly available database in order to demonstrate the possibilities and advantages of such an architecture.

Förderung

  • Silesian University of Technology, Poland
  • Natural Sciences and Engineering Research Council of Canada (NSERC) through the Discovery Grants Program

Zitieren

APA

Połap, D., Srivastava, G., & Jaszcz, A. (2024). Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM. IEEE Transactions on Consumer Electronics, 70(1), 990-999. https://doi.org/10.1109/tce.2023.3325941

Vancouver

Połap D, Srivastava G, Jaszcz A. Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM. IEEE Transactions on Consumer Electronics. 2024;70(1):990-999. doi:10.1109/tce.2023.3325941

BibTeX
@article{Poap2024,
  author = {Połap, Dawid and Srivastava, Gautam and Jaszcz, Antoni},
  title = {Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2024},
  volume = {70},
  number = {1},
  pages = {990--999},
  doi = {10.1109/tce.2023.3325941}
}
Kostenlos starten →