Safe and Saving: A Joint Learning and Energy-Efficient Scheduling Scheme of UAV Assisted Hierarchical Federated Learning for Remote Inspection Within Large Scale IIoT
- 4 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (13) , 25357-25370
Abstract
In Industrial Internet of Things (IIoT), timely detection of equipment failures and predictive maintenance are crucial. Leveraging Federated Learning (FL) allows for distributed model training on inspection devices, enabling predictive maintenance without compromising data privacy. However, Traditional FL faces communication and scalability challenges in large scale industrial scenarios. While hierarchical federated learning (HFL) improves flexibility, it struggles in signal-unstable scenarios. This paper proposes a UAV-assisted HFL framework for distributed remote inspection in IIoT, where UAVs enhance communication via high-altitude links and act as edge servers to collect and aggregate model parameters, reducing the central server’s communication burden and improving training efficiency. In this framework, energy-constrained edge clients face challenges of energy efficiency and data silos, while UAV deployment and energy limitations must also be addressed. To optimize fair and energy-saving training, we formulate an optimization problem to minimize energy consumption based on communication and training costs. This is decomposed into two sub-problems: (1) client selection, tackled as a multi-objective optimization using a MAB-based algorithm with a customized reward function balancing energy use and fairness; (2) UAV scheduling, addressed with a heuristic algorithm to optimize edge server deployment. Combining these schemes enables efficient scheduling for large-scale IIoT inspections. Finally, simulation experiments demonstrate the proposed strategy’s significant advantages in reducing system energy consumption, enhancing model accuracy, and improving fairness.Keywords
Funding Information
- National Natural Science Foundation of China (62101283, 62371250, U24B20187)
This publication has 40 references indexed in Scilit:
- A hierarchical federated learning incentive mechanism in UAV-assisted edge computing environmentAd Hoc Networks, 2023
- Challenges in predictive maintenance – A reviewCIRP Journal of Manufacturing Science and Technology, 2022
- Freshness-Aware High Definition Map Caching with Distributed MAMAB in Internet of Vehicles2022
- Industry 5.0: Prospect and retrospectJournal of Manufacturing Systems, 2022
- Predictive maintenance in the Industry 4.0: A systematic literature reviewComputers & Industrial Engineering, 2020
- Introducing Intelligence and Autonomy into Industrial Robots to Address Operations into Dangerous Area2019
- The industrial internet of things (IIoT): An analysis frameworkComputers in Industry, 2018
- Industry 4.02016
- Evaluation of Jensen-Shannon Distance over Sparse Data2013
- Intelligent fault prediction system based on internet of thingsComputers & Mathematics with Applications, 2012