EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Privacy preserved and decentralized thermal comfort prediction model for smart buildings using federated learning

Sidra Abbas, Shtwai Alsubai, Gabriel Avelino Sampedro, Mideth Abisado, Ahmad Almadhor, Tai-Hoon Kim

PeerJ Computer Science · 29.02.2024 · 10 · e1899

DOI: 10.7717/peerj-cs.1899 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 29.02.2024. Verfasst von Sidra Abbas und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, COMSATS University, Islamabad, Sahiwal, Pakistan. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thermal comfort is a crucial element of smart buildings that assists in improving, analyzing, and realizing intelligent structures. Energy consumption forecasts for such smart buildings are crucial owing to the intricate decision-making processes surrounding resource efficiency. Machine learning (ML) techniques are employed to estimate energy consumption. ML algorithms, however, require a large amount of data to be adequate. There may be privacy violations due to collecting this data. To tackle this problem, this study proposes a federated deep learning (FDL) architecture developed around a deep neural network (DNN) paradigm. The study employs the ASHRAE RP-884 standard dataset for experimentation and analysis, which is available to the general public. The data is normalized using the min-max normalization approach, and the Synthetic Minority Over-sampling Technique (SMOTE) is used to enhance the minority class’s interpretation. The DNN model is trained separately on the dataset after obtaining modifications from two clients. Each client assesses the data greatly to reduce the over-fitting impact. The test result demonstrates the efficiency of the proposed FDL by reaching 82.40% accuracy while securing the data.

Schlagwörter

Stichwörter der Autor:innen

Federated deep learningMachine learningPrivacySmart buildingsThermal comfort

Autor:innen und Institutionen

  • Department of Computer Science, COMSATS University, Islamabad, Sahiwal, Pakistan.
  • College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia.
  • Faculty of Information and Communication Studies, University of the Philippines Open University, Los Baños, Philippines.
  • Center for Computational Imaging and Visual Innovations, De La Salle University, Malate, Philippines.
  • College of Computing and Information Technologies, National University, Manila, Philippines.
  • Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka, Saudi Arabia.

Zitieren

APA

Abbas, S., Alsubai, S., Sampedro, G. A., Abisado, M., Almadhor, A., & Kim, T. H. (2024). Privacy preserved and decentralized thermal comfort prediction model for smart buildings using federated learning. PeerJ Computer Science, 10, e1899. https://doi.org/10.7717/peerj-cs.1899

Vancouver

Abbas S, Alsubai S, Sampedro GA, Abisado M, Almadhor A, Kim TH. Privacy preserved and decentralized thermal comfort prediction model for smart buildings using federated learning. PeerJ Computer Science. 2024;10:e1899. doi:10.7717/peerj-cs.1899

BibTeX
@article{Abbas2024,
  author = {Abbas, Sidra and Alsubai, Shtwai and Sampedro, Gabriel Avelino and Abisado, Mideth and Almadhor, Ahmad and Kim, Tai-Hoon},
  title = {Privacy preserved and decentralized thermal comfort prediction model for smart buildings using federated learning},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e1899},
  doi = {10.7717/peerj-cs.1899}
}
Kostenlos starten →