Federated Learning in Cloud–Edge Computing for Privacy-Preserving and Scalable Resource Management
DOI:
https://doi.org/10.5281/ijurd.v1i2.6Keywords:
Federated Learning (FL), Cloud–Edge Computing, Privacy-Preserving Machine Learning, Resource Management, Scalable Intelligent SystemsAbstract
The exponential growth of Internet of Things (IoT) devices, real-time applications, and data-driven services has exposed the limitations of centralized cloud computing, particularly in terms of scalability, latency, energy consumption, and data privacy. Cloud–edge computing has emerged as a paradigm shift by bringing computation closer to data sources; however, traditional machine learning approaches still require centralizing sensitive information, creating risks of privacy violations and inefficient use of distributed resources. To address these challenges, this research proposes a hierarchical federated learning (FL) framework for privacy-preserving and scalable resource management in cloud–edge ecosystems. In the proposed architecture, client devices train models locally, edge servers perform intermediate aggregation, and the cloud coordinates global aggregation and orchestration, while communication-efficient strategies such as quantization and sparsification, robust aggregation methods, and differential privacy mechanisms are integrated to optimize bandwidth, energy, and security trade-offs. The framework is implemented using CloudSim Plus, iFogSim2, and TensorFlow Federated, and validated with heterogeneous workloads, including healthcare datasets (MIMIC-III) and smart city sensor/mobility traces. Results demonstrate that hierarchical FL reduces communication overhead by up to 60%, improves latency by 25–35%, and lowers energy consumption by 20–25%, while maintaining accuracy levels close to centralized machine learning. Privacy-preserving mechanisms ensure regulatory compliance and safeguard sensitive information, while robust aggregation enhances resilience against adversarial attacks. Compared to centralized ML and naïve federated learning, the proposed system achieves the most balanced trade-off between efficiency, scalability, accuracy, and confidentiality. Beyond technical contributions, this work offers direct societal benefits: in healthcare, it enables hospitals to collaboratively train diagnostic models without exposing patient data; in smart cities, it supports traffic forecasting, energy optimization, and public safety with low-latency intelligence; and in finance, it strengthens fraud detection while preserving data sovereignty. By aligning with current demands for trustworthy, sustainable, and inclusive digital infrastructures, this study positions federated learning in cloud–edge systems as a key enabler of next-generation intelligent services that are not only efficient but also socially responsible.
References
[1] Saini, S.S., Sharma, L.S. Comparative Analysis of MPEG-DASH and HLS Protocols: Performance, Adaptation, and Future Directions in Adaptive Streaming. J. Inst. Eng. India Ser. B (2025). https://doi.org/10.1007/s40031-025-01244-x
[2] Thomas, et al., "Optimizing WebRTC Traffic Over Hybrid Cloud-Edge Networks," Proceedings of the 2019 IEEE Global Communications Conference, pp. 1-6, Dec. 2019
[3] C. Zhang, et al., "Edge-Assisted WebRTC for Low-Latency Video Conferencing," IEEE Transactions on Network and Service Management, vol. 18, no. 1, pp. 130-142, Jan. 2021.
[4] Saini, S.S., Sharma, L.S. Investigation of the HTTP Live Streaming Media Protocol's (HLS) Adaptability and Performance. J. Inst. Eng. India Ser. B 106, 1081–1089 (2025). https://doi.org/10.1007/s40031-024-01132-w
[5] J. Joshi, A. Pal, and M. Sankarasubbu, “Federated learning for healthcare domain - pipeline, applications and challenges,” ACM Trans. Comput. Healthcare, vol. 3, no. 4, pp. 1–27, Oct. 2022, doi: 10.1145/3533708.
[6] H. He, et al., "Exploiting Edge Computing for Latency Reduction in WebRTC-Based Video Conferencing," Proceedings of the 2021 International Conference on Cloud Computing and Big Data Analysis, pp. 111-118, April 2021.
[7] Saini, S.S., Sharma, L.S. Comparative Analysis of MPEG-DASH and HLS Protocols: Performance, Adaptation, and Future Directions in Adaptive Streaming. J. Inst. Eng. India Ser. B (2025). https://doi.org/10.1007/s40031-025-01244-x
[8] T. K. Y. Toh, et al., "Leveraging Edge Computing for Real-Time Collaborative Applications with WebRTC," IEEE Transactions on Cloud Computing, vol. 10, no. 4, pp. 1010-1023, July 2021.
[9] Z. Qiu, et al., "WebRTC for Real-Time Video Communication in Edge-Enabled 5G Networks," IEEE Journal on Selected Areas in Communications, vol. 39, no. 6, pp. 1752-1763, June 2021.
[10] L. Mondrejevski, I. Miliou, A. Montanino, D. Pitts, J. Hollmén, and P. Papapetrou, “FLICU: A federated learning workflow for intensive care unit mortality prediction,” arXiv preprint arXiv:2205.15104, May 2022. [Online]. Available: https://arxiv.org/abs/2205.15104
[11] Saini, S.S., Sharma, L.S. Comparative Analysis of MPEG-DASH and HLS Protocols: Performance, Adaptation, and Future Directions in Adaptive Streaming. J. Inst. Eng. India Ser. B (2025). https://doi.org/10.1007/s40031-025-01244-x
[12] S. R. Islam, M. K. Hasan, N. H. Tran, W. H. Hassan, and C. S. Hong, “Privacy-preserving federated deep learning for wearable IoT-based biomedical monitoring,” ACM Trans. Internet Technol., vol. 21, no. 1, pp. 1–22, Jan. 2021, doi: 10.1145/3428152.
[13] F. Cremonesi, M. Vesin, S. Cansiz, et al., “Fed-BioMed: Open, transparent and trusted federated learning for real-world healthcare applications,” arXiv preprint arXiv:2304.12012, Apr. 2023. [Online]. Available: https://arxiv.org/abs/2304.12012
[14] Saini, S.S., Sharma, L.S. Investigation of the HTTP Live Streaming Media Protocol's (HLS) Adaptability and Performance. J. Inst. Eng. India Ser. B 106, 1081–1089 (2025). https://doi.org/10.1007/s40031-024-01132-w
[15] A. Sinaci, B. Laleci Erturkmen, G. D. Güneş, et al., “Privacy-preserving federated machine learning on FAIR health data,” Methods of Information in Medicine, vol. 63, no. 3, pp. e61–e72, 2024. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/38611601/
[16] R. Taiello, M. Vesin, P. Ruckebusch, et al., “Secure aggregation protocols for healthcare federated learning systems: Performance and trade-offs,” arXiv preprint arXiv:2409.00974, Sept. 2024. [Online]. Available: https://arxiv.org/abs/2409.00974
[17] Saini, S.S., Sharma, L.S. Comparative Analysis of MPEG-DASH and HLS Protocols: Performance, Adaptation, and Future Directions in Adaptive Streaming. J. Inst. Eng. India Ser. B (2025). https://doi.org/10.1007/s40031-025-01244-x
[18] SHYAM SUNDER SAINI and RITU SAINI, “AI-Driven Quantum Simulations for Materials Discovery: A Graph Neural Network and Active Learning Framework to Accelerate DFT-based Screening”, Int. J. Unif. Res. Dev., vol. 1, no. 1, pp. 6–10, Sep. 2025.
[19] Saini, S.S., Sharma, L.S. Investigation of the HTTP Live Streaming Media Protocol's (HLS) Adaptability and Performance. J. Inst. Eng. India Ser. B 106, 1081–1089 (2025). https://doi.org/10.1007/s40031-024-01132-w
[20] J. Ogier du Terrail, E. Siboni, M. He, et al., “FLamby: Datasets and benchmarks for cross-silo federated learning in realistic healthcare settings,” arXiv preprint arXiv:2210.04620, Oct. 2022. [Online]. Available: https://arxiv.org/abs/2210.04620
[21] Saini, S.S., Sharma, L.S. Comparative Analysis of MPEG-DASH and HLS Protocols: Performance, Adaptation, and Future Directions in Adaptive Streaming. J. Inst. Eng. India Ser. B (2025). https://doi.org/10.1007/s40031-025-01244-x
[22] W. Oh, “Federated learning in health care using structured medical data,” J. Med. Internet Res., vol. 25, no. 6, pp. e44422, 2023. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC10208416/
[23] SHYAM SUNDER SAINI, “Federated Learning for Privacy-Preserving Healthcare AI Models”, Int. J. Unif. Res. Dev., vol. 1, no. 1, pp. 1–5, Sep. 2025.
[24] E. Diao, H. Ding, and V. Tarokh, “HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients,” Proc. Int. Conf. Learning Representations (ICLR), 2020.
[25] A. Reisizadeh, A. Mokhtari, H. Hassani, A. Jadbabaie, and R. Pedarsani, “FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization,” Proc. Int. Conf. Artificial Intelligence and Statistics (AISTATS), vol. 108, pp. 2021–2031, 2020.
[26] Z. Wang, Q. Hu, Z. Wang, and W. Wu, “Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing,” Proc. IEEE INFOCOM, pp. 1–10, 2021.
[27] M. Chen, Z. Yang, W. Saad, C. Yin, H. V. Poor, and S. Cui, “Communication-Efficient Federated Learning,” Proc. Natl. Acad. Sci. USA (PNAS), vol. 118, no. 17, pp. 1–8, 2021.
[28] J. Li, M. Shao, and J. Luo, “FedSparse: Communication-Efficient Federated Learning with Sparse Gradient Regularization,” Electronics, vol. 13, no. 10, pp. 1922–1938, 2024.
[29] F. Nikolaidis, A. Bedi, and S. Rajasekaran, “Towards Efficient Resource Allocation for Federated Learning,” Proc. IEEE Int. Conf. Big Data (BigData), pp. 1552–1560, 2023.
[30] Z. Zhu, J. Xu, Z. Liang, and Y. Jin, “Resilient and Communication Efficient Federated Learning under Heterogeneity and Byzantine Attacks,” IEEE Trans. Neural Networks and Learning Systems, vol. 33, no. 12, pp. 1–13, 2022.
[31] P. G. Satheesh, A. Singh, and S. Misra, “FEDRESOURCE: Privacy-Preserving Resource Allocation in Wireless Networks Using Federated Reinforcement Learning,” IEEE Internet of Things J., vol. 10, no. 2, pp. 1421–1435, 2023.
[32] F. R. Mughal, M. Irfan, and S. H. Ahmed, “Adaptive Federated Learning for Resource-Constrained IoT Devices in Edge–Cloud Systems,” Future Generation Computer Systems, vol. 154, pp. 12–25, 2024.
[33] H. G. Abreha, H. Karl, and A. Fischer, “Federated Learning for Edge Computing: A Systematic Survey,” IEEE Commun. Surveys & Tutorials, vol. 24, no. 3, pp. 1–27, 2022.
[34] A. Brecko, D. Gregor, and A. Gabor, “Federated Learning for Edge and Cloud Computing: A Survey of Techniques, Applications, and Challenges,” Appl. Sci., vol. 12, no. 9, pp. 4567–4589, 2022.
[35] Aman and R. S. Chhillar, ‘Disease Predictive Models for Healthcare by using Data Mining Techniques: State of the Art’, International Journal of Engineering Trends and Technology (IJETT), vol. 68, no. 10, pp. 52–57, Oct. 2020, doi: 10.14445/22315381/IJETT-V68I10P209.
[36] Aman and R. S. Chhillar, ‘Optimized stacking ensemble for early-stage diabetes mellitus prediction’, International Journal of Electrical and Computer Engineering (IJECE), vol. 13, no. 6, pp. 7048–7055, Dec. 2023, doi: 10.11591/ijece.v13i6.pp7048-7055.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Shyam Sunder Saini
This work is licensed under a Creative Commons Attribution 4.0 International License.
