Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Energy efficiency remains a major challenge in deploying IoT systems, especially in scenarios requiring large numbers of devices while balancing computational requirements and operational lifetimes. This paper proposes a federated reinforcement learning framework for adaptive load balancing in the edge-fog-cloud continuum that optimizes energy efficiency and supports diverse quality of service requirements. The proposed framework addresses the limitations of traditional centralized machine learning approaches that require collecting sensitive operational information and transmitting it to cloud servers for centralized analysis. This increases the risk of privacy violations and introduces communication overheads that limit the responsiveness of IoT systems. The proposed framework employs a federated reinforcement learning approach, enabling edge nodes to collaboratively learn an optimal load-balancing policy without transmitting operational information. The proposed framework uses a context-aware reward function that optimizes multiple objectives based on temporal patterns, device energy levels, and application criticality. This enables the proposed framework to adapt its optimization objectives and balance energy efficiency and performance maximization. The proposed framework introduces a new action-space pruning mechanism that accelerates the optimization process by leveraging domain knowledge of possible load-balancing patterns. The proposed framework uses a distributed experience replay buffer to reduce trial-and-error in reinforcement learning. The proposed framework demonstrates its effectiveness in optimizing energy efficiency through a series of experiments in a real-world IoT environment and a centralized machine learning approach. The proposed framework demonstrates that distributed machine learning approaches can outperform centralized ones for optimizing energy efficiency in IoT systems.

Keywords

Federated reinforcement learning Load balancing Edge-fog-cloud continuum Energy efficiency Internet of Things

Article Details

How to Cite
Liu, S., & Chakkaravarthy, M. (2026). Federated reinforcement learning for energy-aware load balancing in edge-fog-cloud IoT continuum. Future Technology, 5(3), 85–96. Retrieved from https://fupubco.com/futech/article/view/887
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. E. Dritsas, M. Trigka, Federated learning for IoT: A survey of techniques, challenges, and applications, Journal of Sensor and Actuator Networks 14(1) (2025) 9. https://doi.org/10.3390/jsan14010009
  2. M. Latifi, N. Derakhshanfard, H. Heydari, Optimizing the distribution of tasks in Internet of Things using edge processing-based reinforcement learning, Intelligent Systems with Applications (2025) 200585. https://doi.org/10.1016/j.iswa.2025.200585
  3. H. Li, L. Ge, L. Tian, Survey: federated learning data security and privacy-preserving in edge-Internet of Things, Artificial Intelligence Review 57(5) (2024) 130. DOI:10.1007/s10462-024-10774-7
  4. B. Kar, W. Yahya, Y.-D. Lin, A. Ali, Offloading using traditional optimization and machine learning in federated cloud–edge–fog systems: A survey, IEEE Communications Surveys & Tutorials 25(2) (2023) 1199-1226. DOI: 10.1109/COMST.2023.3239579
  5. P. Tam, R. Corrado, C. Eang, S. Kim, Applicability of deep reinforcement learning for efficient federated learning in massive IoT communications, Applied Sciences 13(5) (2023) 3083. https://doi.org/10.3390/app13053083
  6. B. Sellami, A. Hakiri, S.B. Yahia, P. Berthou, Energy-aware task scheduling and offloading using deep reinforcement learning in SDN-enabled IoT network, Computer Networks 210 (2022) 108957. https://doi.org/10.1016/j.comnet.2022.108957
  7. G. Nieto, I. De la Iglesia, U. Lopez-Novoa, C. Perfecto, Deep Reinforcement Learning techniques for dynamic task offloading in the 5G edge-cloud continuum, Journal of Cloud Computing 13(1) (2024) 94. https://doi.org/10.1186/s13677-024-00658-0
  8. Z. Zabihi, A.M. Eftekhari Moghadam, M.H. Rezvani, Reinforcement learning methods for computation offloading: a systematic review, ACM Computing Surveys 56(1) (2023) 1-41. https://doi.org/10.1145/3603703
  9. M. Zolghadri, P. Asghari, S. Dashti, A. Hedayati, Ai-driven energy-aware task offloading with network traffic considerations in fog-cloud environments, Cluster Computing 28(10) (2025) 680. https://doi.org/10.1007/s10586-025-05446-2
  10. H. Mashal, M.H. Rezvani, Multiobjective offloading optimization in fog computing using deep reinforcement learning, Journal of Computer Networks and Communications 2024(1) (2024) 6255511. https://doi.org/10.1155/2024/6255511
  11. H. Zhou, Y. Zheng, X. Jia, Towards robust and privacy-preserving federated learning in edge computing, Computer Networks 243 (2024) 110321. https://doi.org/10.1016/j.comnet.2024.110321
  12. V. Vijayalakshmi, M. Saravanan, Reinforcement learning-based multi-objective energy-efficient task scheduling in fog-cloud industrial IoT-based systems: V. Vijayalakshmi, M. Saravanan, Soft Computing 27(23) (2023) 17473-17491. https://doi.org/10.1007/s00500-023-09159-9
  13. T. Allaoui, K. Gasmi, T. Ezzedine, Reinforcement learning based task offloading of IoT applications in fog computing: algorithms and optimization techniques, Cluster Computing 27(8) (2024) 10299-10324. https://doi.org/10.1007/s10586-024-04518-z
  14. W. Almuseelem, Deep reinforcement learning-enabled computation offloading: a novel framework to energy optimization and security-aware in vehicular edge-cloud computing networks, Sensors 25(7) (2025) 2039. https://doi.org/10.3390/s25072039
  15. F.R. Mughal, J. He, B. Das, F.A. Dharejo, N. Zhu, S.B. Khan, S. Alzahrani, Adaptive federated learning for resource-constrained IoT devices through edge intelligence and multi-edge clustering, Scientific Reports 14(1) (2024) 28746. https://doi.org/10.1038/s41598-024-78239-z
  16. D.C. Nguyen, M. Ding, P.N. Pathirana, A. Seneviratne, J. Li, H.V. Poor, Federated learning for internet of things: A comprehensive survey, IEEE communications surveys & tutorials 23(3) (2021) 1622-1658. DOI:10.48550/arXiv.2104.07914
  17. J.P. Singh, A. Aqsa, I. Ghani, R. Sonani, V. Govindarajan, Privacy-aware hierarchical federated learning in healthcare: integrating differential privacy and secure multi-party computation, Future Internet 17(8) (2025) 345. https://doi.org/10.1145/3659099
  18. A. Maurya, R. Haripriya, M. Pandey, J. Choudhary, D.P. Singh, S. Solanki, D. Sharma, Federated learning for privacy-preserving severity classification in healthcare: A secure edge-aggregated approach, IEEE Access (2025). DOI:10.1109/ACCESS.2025.3576135
  19. S.K. Jagatheesaperumal, M. Rahouti, A. Alfatemi, N. Ghani, V.K. Quy, A. Chehri, Enabling trustworthy federated learning in industrial IoT: bridging the gap between interpretability and robustness, IEEE Internet of Things Magazine 7(5) (2024) 38-44. DOI:10.48550/arXiv.2409.02127
  20. E.C. Pinto Neto, S. Sadeghi, X. Zhang, S. Dadkhah, Federated reinforcement learning in IoT: Applications, opportunities and open challenges, Applied Sciences 13(11) (2023) 6497. https://doi.org/10.3390/app13116497
  21. Y. Liu, Y. Dong, H. Wang, H. Jiang, Q. Xu, Distributed fog computing and federated-learning-enabled secure aggregation for IoT devices, IEEE Internet of Things Journal 9(21) (2022) 21025-21037. DOI:10.1109/JIOT.2022.3176305
  22. M. Jammal, M. AbuSharkh, Machine learning for edge-aware resource orchestration for IoT applications, 2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT), IEEE, 2021, pp. 37-44. DOI: 10.1109/GCAIoT53516.2021.9692940
  23. A. Alwarafy, M. Abdallah, B.S. Ciftler, A. Al-Fuqaha, M. Hamdi, The frontiers of deep reinforcement learning for resource management in future wireless HetNets: Techniques, challenges, and research directions, IEEE Open Journal of the Communications Society 3 (2022) 322-365. DOI: 10.1109/OJCOMS.2022.3153226
  24. H.M.F. Noman, E. Hanafi, K.A. Noordin, K. Dimyati, M.N. Hindia, A. Abdrabou, F. Qamar, Machine learning empowered emerging wireless networks in 6G: Recent advancements, challenges and future trends, IEEe Access 11 (2023) 83017-83051. DOI: 10.1109/ACCESS.2023.3302250
  25. E. Rahimov, T. Aghayev, Predictive Load Balancing in Distributed Systems: A Comparative Study of Round Robin, Weighted Round Robin, and a Machine Learning Approach, Engineering Proceedings 122(1) (2026) 26. https://doi.org/10.3390/engproc2026122026
  26. X. Qin, B. Li, L. Ying, Distributed threshold-based offloading for large-scale mobile cloud computing, IEEE INFOCOM 2021-IEEE Conference on Computer Communications, IEEE, 2021, pp. 1-10. DOI: 10.1109/INFOCOM42981.2021.9488821
  27. Z. Zhao, G. Min, W. Gao, Y. Wu, H. Duan, Q. Ni, Deploying edge computing nodes for large-scale IoT: A diversity aware approach, IEEE Internet of Things Journal 5(5) (2018) 3606–3614. DOI: 10.1109/JIOT.2018.2823498