EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Federated Learning Multi-Task Scheduling Mechanism Based on Trusted Computing Sandbox

Hongbin Liu, Han Zhou, Hao Chen, Yong Yan, Jianping Huang, Ao Xiong, Shaojie Yang, Jiewei Chen, Shaoyong Guo

Sensors · 13.02.2023 · 23 (4) · 2093

DOI: 10.3390/s23042093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.02.2023. Verfasst von Hongbin Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: State Grid Corporation of China, Beijing 100031, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Corporation of China Science and Technology Project “Research and application of industry chain finance key technology based on blockchain”.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

At present, some studies have combined federated learning with blockchain, so that participants can conduct federated learning tasks under decentralized conditions, sharing and aggregating model parameters. However, these schemes do not take into account the trusted supervision of federated learning and the case of malicious node attacks. This paper introduces the concept of a trusted computing sandbox to solve this problem. A federated learning multi-task scheduling mechanism based on a trusted computing sandbox is designed and a decentralized trusted computing sandbox composed of computing resources provided by each participant is constructed as a state channel. The training process of the model is carried out in the channel and the malicious behavior is supervised by the smart contract, ensuring the data privacy of the participant node and the reliability of the calculation during the training process. In addition, considering the resource heterogeneity of participant nodes, the deep reinforcement learning method was used in this paper to solve the resource scheduling optimization problem in the process of constructing the state channel. The proposed algorithm aims to minimize the completion time of the system and improve the efficiency of the system while meeting the requirements of tasks on service quality as much as possible. Experimental results show that the proposed algorithm has better performance than the traditional heuristic algorithm and meta-heuristic algorithm.

Schlagwörter

Stichwörter der Autor:innen

blockchaincomputing sandboxdata privacydeep reinforcement learningresource scheduling

Autor:innen und Institutionen

  • State Grid Corporation of China, Beijing 100031, China.
  • State Key Laboratory of Network and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China.
  • State Grid Zhejiang Electric Power Co., LTD., Hangzhou 310007, China.

Förderung

  • State Grid Corporation of China Science and Technology Project “Research and application of industry chain finance key technology based on blockchain”

Zitieren

APA

Liu, H., Zhou, H., Chen, H., Yan, Y., Huang, J., Xiong, A., Yang, S., Chen, J., & Guo, S. (2023). A Federated Learning Multi-Task Scheduling Mechanism Based on Trusted Computing Sandbox. Sensors, 23(4), 2093. https://doi.org/10.3390/s23042093

Vancouver

Liu H, Zhou H, Chen H, Yan Y, Huang J, Xiong A, et al. A Federated Learning Multi-Task Scheduling Mechanism Based on Trusted Computing Sandbox. Sensors. 2023;23(4):2093. doi:10.3390/s23042093

BibTeX
@article{Liu2023,
  author = {Liu, Hongbin and Zhou, Han and Chen, Hao and Yan, Yong and Huang, Jianping and Xiong, Ao and Yang, Shaojie and Chen, Jiewei and Guo, Shaoyong},
  title = {A Federated Learning Multi-Task Scheduling Mechanism Based on Trusted Computing Sandbox},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {4},
  pages = {2093},
  doi = {10.3390/s23042093}
}
Kostenlos starten →