Y. -L. Hsu, C. -F. Liu, H. -Y. Wei and M. Bennis, "Optimized Data Sampling and Energy Consumption in IIoT: A Federated Learning Approach," in IEEE Transactions on Communications, vol. 70, no. 12, pp. 7915-7931, Dec. 2022, doi: 10.1109/TCOMM.2022.3216353
Optimized data sampling and energy consumption in IIoT : a federated learning approach
|Author:||Hsu, Yung-Lin1; Liu, Chen-Feng2; Wei, Hung-Yu1;|
1Graduate Institute of Communication Engineering, National Taiwan University, Taipei 10617, Taiwan
2Technology Innovation Institute, Masdar City, Abu Dhabi 9639, United Arab Emirates
3Centre for Wireless Communications, University of Oulu, 90014 Oulu, Finland
|Online Access:||PDF Full Text (PDF, 4.6 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe202301183457
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2023-01-18
Real-time environment monitoring is a key application in Industrial Internet of Things, where sensors proactively collect and transmit environmental data to the controller. However, due to limited wireless resources, keeping sensors’ sampled data fresh at the controller is critical. This work aims to investigate the trade-off between the sensor’s data-sampling frequency and long-term data transmission energy consumption while maintaining information freshness. Leveraging the entropic risk measure (ERM), we jointly minimize the global transmission energy’s mean and variance subject to probabilistic constraints on information freshness. Furthermore, while jointly saving the model training energy, we adopt the federated learning (FL) paradigm and propose an FL-based two-stage iterative optimization framework to optimize the aforementioned objective. Specifically, we iteratively learn the sampling frequency via Bayesian optimization and minimize the long-term ERM of the global energy consumption via Lyapunov optimization. Numerical results show that the proposed FL-based scheme saves substantial executing energy with less performance loss. Quantitatively, compared with the centralized learning baseline, the proposed FL-based framework saves up to 69% model training energy at the expense of a mere increased objective outcome, i.e., 6.3% in the global data transmission energy consumption ( 9.936×10⁻⁵ in ERM) under 0.4% bias from the global optimal data-sampling frequency.
IEEE transactions on communications
|Pages:||7915 - 7931|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
213 Electronic, automation and communications engineering, electronics
This work was supported in part by the Ministry of Science and Technology (MOST) of Taiwan under the Graduate Students Study Abroad Program Grant 109-2917-I-002-007, and Grant 111-2221-E-002-097-MY3, in part by the CHIST-ERA project CONNECT, in part by the CHIST-ERA project LeadingEdge, in part by the EU-H2020 project IntellIoT, and in part by the the Nokia Bell Labs project NEGEIN.
|EU Grant Number:||
(957218) IntellIoT - Intelligent, distributed, human-centered and trustworthy IoT environments
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.