ADAPTIVE METHOD FOR DYNAMIC RESOURCE CONTROL OF THE INDUSTRIAL INTERNET OF THINGS BORDER LAYER
DOI:
https://doi.org/10.26906/SUNZ.2025.4.088Keywords:
Industrial Internet of Things, edge layer, computing resources, adaptive controlAbstract
In the process of functioning of the Industrial Internet of Things, the shortage of resources of the boundary layer manifests itself as an increase in processing delays, queues, data loss or service degradation. The purpose of this work is to develop an adaptive method for dynamic resource management of the IIoT boundary layer, which will allow for the effective use of computing resources.. The following results were obtained: A conceptual adaptive method for dynamic resource management of the boundary layer in IIoT using a multi-agent approach and horizontal and vertical scaling is proposed. Monitoring, evaluation, decision-making and learning methods are integrated into a single architecture. The developed mathematical model allows formalizing the balance of queues, resources, and task transfer between nodes. The method provides flexible adaptation to variable load and minimizes losses, delays, and also effectively uses limited resources. Conclusions. Adaptive management of computing resources of the edge layer of the IoT allows to increase the efficiency of the system and reduce the impact of resource shortages.Downloads
References
1. Zhang, X., Wang, X., Xu, X. & Duan, L. (2023) Resource Management in Mobile Edge Computing: A Comprehensive Survey. ACM (survey). DOI: https://doi.org/10.1145/3589639
2. Zamzam, M., Elshabrawy, T. & Ashour, M. (2019) Resource management using machine learning in mobile edge computing: A survey. In: Proceedings of the 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS). DOI: https://doi.org/10.1109/ICICIS46948.2019.9014733
3. Li, H., Liu, Y., Zhou, X., Vasilakos, X., Nejabati, R., Yan, S. & Simeonidou, D. (2023) Adaptive resource management for edge network slicing using incremental multi-agent deep reinforcement learning. CoRR (arXiv preprint). arXiv: 2310.17523. URL: https://arxiv.org/abs/2310.17523
4. AlQerm, I., Wang, J., Pan, J. & Liu, Y. (2021) BEHAVE: Behavior-Aware, Intelligent and Fair Resource Management for Heterogeneous Edge-IoT Systems. IEEE Trans. on Mobile Computing. DOI: https://doi.org/10.1109/TMC.2021.3068632
5. Dlamini, T., Gambín, M. (2019) Adaptive resource management for a virtualized computing platform within edge computing. Proceedings of the 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC/SAHCN). DOI: https://doi.org/10.1109/SAHCN.2019.8824927
6. Sun, W., Lei, S., Wang, L., Liu, Z. & Zhang, Y. (2020) Adaptive federated learning and digital twin for Industrial Internet of Things. CoRR (arXiv preprint). arXiv: 2010.13058, URL: https://arxiv.org/abs/2010.13058
7. Mhamdi, L. & Abdul Khalek, H. (2023) Congestion control in constrained Internet of Things networks. IET Wireless Sensor Systems, 13(6), pp.247–255. DOI: https://doi.org/10.1049/wss2.12072
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sergii Klivets, Alexander Kuleshov, Tetiana Kulieshova
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
