Energy-Efficient Federated Learning at the Wireless Edge: A Survey

Authors

  • Christopher Aseer J Albert

    Department of Computer Engineering, Agnel Charities’ Fr. C. Rodrigues Institute of Technology, Navi Mumbai 400703, India
  • Ashli Paul

    Department of Computer Engineering, Agnel Charities’ Fr. C. Rodrigues Institute of Technology, Navi Mumbai 400703, India
  • Chaitanya V Mahamuni

    Electronics and Telecommunication Engineering, University of Mumbai, Mumbai 400032, India
  • Sophia Chavakula John

    Department of Computer Engineering, Agnel Charities’ Fr. C. Rodrigues Institute of Technology, Navi Mumbai 400703, India
  • Earnest Ebenezer

    Department of Computer Engineering, Agnel Charities’ Fr. C. Rodrigues Institute of Technology, Navi Mumbai 400703, India

DOI:

https://doi.org/10.30564/jeis.v7i2.10982
Received: 5 July 2025 | Revised: 22 August 2025 | Accepted: 1 September 2025 | Published Online: 9 September 2025

Abstract

The recent surge in edge computing and wireless connectivity has accelerated the adoption of Federated Learning (FL), a paradigm that enables privacy-preserving distributed intelligence across resource-constrained devices. However, implementing FL in practical wireless edge networks introduces significant challenges, particularly excessive energy consumption and communication overhead. This survey provides a system-level exploration of energy-efficient FL strategies, examining algorithmic advances and deployment challenges. Core techniques—such as model compression, update sparsification, and adaptive client scheduling—are analyzed with respect to their trade-offs in scalability, convergence, and long-term energy sustainability, especially under non-IID data distributions and heterogeneous device conditions. Practical insights are drawn from case studies in the Internet of Things (IoT), 5G/6G wireless ecosystems, and ultra-low-power device deployments, highlighting both limitations and optimization opportunities for real-world implementations. In addition, the survey explores emerging enablers, including blockchain-based trust frameworks, neuromorphic processors, and reinforcement learning-driven orchestration, which hold potential for achieving robust, sustainable FL in dynamic edge environments. By integrating perspectives from communication theory, distributed systems, and sustainable computing, this work delivers an interdisciplinary roadmap for the realistic deployment of energy-efficient FL in next-generation wireless systems, aiming to guide future research toward scalable, fair, and sustainable federated intelligence at the wireless edges.

Keywords:

Federated Learning; Wireless Edge Networks; Energy Efficiency; Communication Bottlenecks; Client Heterogeneity; IoT; 5G/6G; Privacy-Energy Trade-Offs

References

[1] Lorincz, J., Capone, A., Wu, J., et al., 2019. Greener, Energy-Efficient and Sustainable Networks: State-of-the-Art and New Trends. Sensors. 19(22), 4864. DOI: https://doi.org/10.3390/s19224864

[2] Murshed, M.G.S., Murphy, C., Hou, D., et al., 2021. Machine Learning at the Network Edge A Survey. ACM Computing Surveys. 54(8), 1–37. DOI: https://doi.org/10.1145/3469029

[3] Beltrán, E.T.M., Pérez, M.Q., Sánchez, P.M.S., et al., 2023. Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges. IEEE Communications Surveys & Tutorials. 25(4), 2983–3013. DOI: https://doi.org/10.1109/COMST.2023.3315746

[4] Cheikh, I., Roy, S., Sabir, E.,et al., 2025. Energy, Scalability, Data and Security in Massive IoT: Current Landscape and Future Directions. arXiv preprint. arXiv:2505.03036. DOI: https://doi.org/10.48550/arXiv.2505.03036

[5] Yang, Z., Chen, M., Wong, K.-K., 2022. Federated Learning for 6G: Applications, Challenges, and Opportunities. Engineering. 8, 33–41. DOI: https://doi.org/10.1016/j.eng.2021.12.002

[6] Rahmani, H., Shetty, D., Wagih, M., et al., 2023. Next-Generation IoT Devices: Sustainable Eco-Friendly Manufacturing, Energy Harvesting, and Wireless Connectivity. IEEE Journal of Microwaves. 3(1), 237–255. DOI: https://doi.org/10.1109/JMW.2022.3228683

[7] López, O.L.A., Rosabal, O.M., Ruiz-Guirola, D.E, et al., 2023. Energy-Sustainable IoT Connectivity: Vision, Technological Enablers, Challenges, and Future Directions. IEEE Open Journal of the Communications Society. 4, 2609–2666. DOI: https://doi.org/10.1109/OJCOMS.2023.3323832

[8] Li, L., 2025. Research on Future 6G Green Wireless Networks. Green Technologies and Sustainability. 3(5), 100156. DOI: https://doi.org/10.1016/j.grets.2024.100156

[9] Chen, Y., Huang, S., Gan, W., et al., 2023. Federated Learning for Metaverse: A Survey. In Proceedings of the WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023, Austin, TX, USA, 30 April–4 May 2023. pp. 1151–1160.DOI: https://doi.org/10.1145/3543873.3587584

[10] Trigka, M., Dritsas, E., 2025. Edge and Cloud Computing in Smart Cities. Future Internet. [17(3), 118. DOI: https://doi.org/10.3390/fi17030118

[11] Lu, M., Fu, G., Osman, N.B., et al., 2021. Green Energy Harvesting Strategies on Edge-Based Urban Computing in Sustainable Internet of Things. Sustainable Cities and Society. 75, 103349. DOI: https://doi.org/10.1016/j.scs.2021.103349

[12] Sharma, A., Sharma, P., 2021. Energy Harvesting Technology for IoT Edge Applications. In: Kheng, T.Y. (Ed.). Smart Manufacturing-When Artificial Intelligence Meets the Internet of Things. DOI: https://doi.org/10.5772/intechopen.92565

[13] Nguyen, D.C., Ding, M., Pathirana, P.N.,et al., 2021. Federated Learning for Internet of Things: A Comprehensive Survey. IEEE Communications Surveys & Tutorials. 23(3), 1622–1658. DOI: https://doi.org/10.1109/COMST.2021.3075439

[14] Banabilah, S., Aloqaily, M., Alsayed, E., et al., 2022. Federated Learning Survey: Fundamentals, Enabling Technologies, and Future Applications. Information Processing & Management. 59(6), 103061. DOI: https://doi.org/10.1016/j.ipm.2022.103061

[15] Mestoukirdi, M., 2023. Reliable and Communication-Efficient Federated Learning for Future Intelligent Edge Networks [PhD thesis]. Sorbonne Université: Paris, France. Available from: https://theses.hal.science/tel-04470748v1

[16] Zhu, J., Cao, J., Saxena, D., et al., 2023. Blockchain-Empowered Federated Learning: Challenges, Solutions, and Future Directions. ACM Computing Surveys. 55(11), 1–31. DOI: https://doi.org/10.1145/3570953

[17] Salehi, M., Hossain, E., 2021. Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks. IEEE Transactions on Communications. 69(8), 5136–5151. DOI: https://doi.org/10.1109/TCOMM.2021.3081746

[18] Evgenidis, N.G., Mitsiou, N.A., Koutsioumpa, V.I., et al., 2024. Multiple Access in the Era of Distributed Computing and Edge Intelligence. Proceedings of the IEEE. 112(9), 1497–1526. DOI: https://doi.org/10.1109/JPROC.2024.3417528

[19] Wang, Y., Xu, Y., Shi, Q., et al., 2021. Quantized Federated Learning under Transmission Delay and Outage Constraints. IEEE Journal on Selected Areas in Communications. 40(1), 323–341. DOI: https://doi.org/10.1109/JSAC.2021.3126081

[20] Fekri, M.N., Grolinger, K., Mir, S., 2023. Asynchronous Adaptive Federated Learning for Distributed Load Forecasting with Smart Meter Data. International Journal of Electrical Power & Energy Systems. 153, 109285. DOI: https://doi.org/10.1016/j.ijepes.2023.109285

[21] Khajehali, N., Yan, S., Chow, Y.-W., et al., 2023. A Comprehensive Overview of IoT-Based Federated Learning: Focusing on Client Selection Methods. Sensors. 23(16), 7235. DOI: https://doi.org/10.3390/s23167235

[22] Jouini, O., Sethom, K., Namoun, A., et al., 2024. A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions. Technologies. 12(6), 81. DOI: https://doi.org/10.3390/technologies12060081

[23] Hoefler, T., Alistarh, D., Ben-Nun, T., et al., 2021. Sparsity in Deep Learning: Pruning and Growth for Efficient Inference and Training in Neural Networks. Journal of Machine Learning Research. 23, 1–124.

[24] Paparounas, F., Christofas, V., Amanatidis, P., et al., 2024. Evaluating Knowledge Distillation and Compression Techniques for Edge Class Devices. In Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and Informatics, Athens, Greece, 13–15 December 2024; pp. 444–449.

[25] Caldas, S., Duddu, S.M.K., Wu, P., 2019. LEAF: A Benchmark for Federated Settings. Available from: https://github.com/TalwalkarLab/leaf (28th June 2025)

[26] Huang, S., 2020. Low Rank Approximations for Efficient DNN Training [Master’s thesis]. The George Washington University: Washington, DC, USA.

[27] Singh, S., Kumar, S., 2024. Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques. arXiv prepreint. arXiv:2502.07634. DOI: https://doi.org/10.48550/arXiv.2502.07634

[28] Peng, C., Li, F., 2018. A Survey on Recent Advances in Event-Triggered Communication and Control. Information Sciences. 457–458, 113–125. DOI: https://doi.org/10.1016/j.ins.2018.04.055

[29] Nadiradze, G., Sabour, A., Alistarh, D., et al., 2019. Asynchronous Decentralized SGD with Quantized and Local Updates. arxiv preprint. arXiv:1910.12308. DOI: https://doi.org/10.48550/arXiv.1910.12308

[30] Fu, L., Zhang, H., Gao, G., et al., 2023. Client Selection in Federated Learning: Principles, Challenges, and Opportunities. IEEE Internet of Things Journal. 10(24), 21811–21819. DOI: https://doi.org/10.48550/arXiv.2211.01549

[31] Ertem, M., 2024. Renewable Energy-Aware Machine Scheduling under Intermittent Energy Supply. IEEE Access. 12, 23613–23625. DOI: https://doi.org/10.1109/ACCESS.2024.3365074

[32] Liu, J., Xu, H., Wang L., et al., 2021. Adaptive Asynchronous Federated Learning in Resource-Constrained Edge Computing. IEEE Transactions on Mobile Computing. 22(2), 674–690. DOI: https://doi.org/10.1109/TMC.2021.3096846

[33] Sun, H., Liu, Y., Al-Tahmeesschi, A., et al., 2025. Advancing 6G: Survey for Explainable AI on Communications and Network Slicing. IEEE Open Journal of the Communications Society. 6, 1372–1412. DOI: https://doi.org/10.1109/OJCOMS.2025.3534626

[34] Pham, Q.-V., Fang, F., Ha, V.N., et al., 2020. A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art. IEEE Access. 8, 116974–117017. DOI: https://doi.org/10.1109/ACCESS.2020.3001277

[35] Mushtaq, M.U., Venter, H., Singh, A., et al., 2025. Advances in Energy Harvesting for Sustainable Wireless Sensor Networks: Challenges and Opportunities. Hardware. 3(1), 1. DOI: https://doi.org/10.3390/hardware3010001

[36] Xu, F., Hussain, T., Ahmed M., et al., 2023. The State of AI-Empowered Backscatter Communications: A Comprehensive Survey. IEEE Internet of Things Journal. 10(24), 21763–21786. DOI: https://doi.org/10.1109/JIOT.2023.3299210

[37] Hameed, R.T., Mohamad, O.A., 2023. Federated Learning in IoT: A Survey on Distributed Decision Making. Babylonian Journal of Internet of Things. 2023, 1–7. DOI: https://doi.org/10.58496/BJIoT/2023/001

[38] Bambagini, M., Marinoni, M., Aydin, H., et al., 2016. Energy-Aware Scheduling for Real-Time Systems: A Survey. ACM Transactions on Embedded Computing Systems. 15(1), 1–34. DOI: https://doi.org/10.1145/2808231

[39] Berkani, M.R.A., Chouchane, A., Himeur, Y., et al., 2025. Advances in Federated Learning: Applications and Challenges in Smart Building Environments and Beyond. Computers. 14(4), 124.

[40] Kanellopoulos, D.N., Sharma, V.K., 2022. Dynamic Load Balancing Techniques in the IoT: A SurveyReview. Symmetry. 14(12), 2554. DOI: https://doi.org/10.3390/sym14122554

[41] Ahmed, A., Choi, B.J., 2023. FRIMFL: A Fair and Reliable Incentive Mechanism in Federated Learning. Electronics. 12(15), 3259.

[42] Nanayakkara, S.I., Pokhrel, S.R., Li, G., 2024. Understanding Global Aggregation and Optimization of Federated Learning. Future Generation Computer Systems. 159, 114–133. DOI: https://doi.org/10.1016/j.future.2024.05.009

[43] Bayram, F., Aupke, P., Ahmed, B.S., et al., 2023. DA-LSTM: A Dynamic Drift-Adaptive Learning Framework for Interval Load Forecasting with LSTM Networks. Engineering Applications of Artificial Intelligence. 123, 106480. DOI: https://doi.org/10.1016/j.engappai.2023.106480

[44] Demelius, L., Kern, R., Trügler, A., 2025. Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey. ACM Computing Surveys. 57(6), 1–28. DOI: https://doi.org/10.1145/3712000

[45] Zhang, Y., Behnia, R., Yavuz, A.A., et al., 2024. Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning. arXiv preprint. arXiv:2410.09676. DOI: https://doi.org/10.48550/arXiv.2410.09676

[46] Kokila, M., Reddy, S.K., 2025. Authentication, Access Control and Scalability Models in Internet of Things Security–A Review. Cyber Security and Applications. 3, 100057. DOI: https://doi.org/10.1016/j.csa.2024.100057

[47] Aljrees, T., Kumar, A., Singh, K.U., et al., 2023. Enhancing IoT Security through a Green and Sustainable Federated Learning Platform: Leveraging Efficient Encryption and the Quondam Signature Algorithm. Sensors. 23(19), 8090.

[48] Jiang, J.C., Kantarci, B., Oktug, S., et al., 2020. Federated Learning in Smart City Sensing: Challenges and Opportunities. Sensors. 20(21), 6230.

[49] Wen, J., Zhang, Z., Lan, Y., et al., 2023. A Survey on Federated Learning: Challenges and Applications. International Journal of Machine Learning and Cybernetics. 14, 513–535. DOI: https://doi.org/10.1007/s13042-022-01647-y

[50] Žalik, K.R., Žalik, M., 2023. A Review of Federated Learning in Agriculture. Sensors. 23(23), 9566. DOI: https://doi.org/10.3390/s23239566

[51] Dembani, R., Karvelas, I., Akbar, N.A., et al., 2025. Agricultural Data Privacy and Federated Learning: A Survey of Challenges and Opportunities. Computers and Electronics in Agriculture. 232, 110048. DOI: https://doi.org/10.1016/j.compag.2025.110048

[52] Wang, T., Du, Y., Gong, Y., et al., 2023. Applications of Federated Learning in Mobile Health: Scoping Survey. Journal of Medical Internet Research. 25, e43006. DOI: https://doi.org/10.2196/43006

[53] Rani, S., Kataria, A., Kumar, S., et al., 2023. Federated Learning for Secure IoMT-Applications in Smart Healthcare Systems: A Comprehensive RSeviewurvey. Knowledge-Based Systems. 274, 110658. DOI: https://doi.org/10.1016/j.knosys.2023.110658

[54] Gambito, M.A., Carnevale, L., Jabbarpour, M.R., et al., 2024. Hierarchical Federated Learning for Natural Disaster Management. In Proceedings of the IEEE/ACM 17th International Conference on Utility and Cloud Computing (UCC), Sharjah, United Arab Emirates, 16–19 December 2024; pp. 282–289.

[55] El Hoffy, A., Kwon, S.S.-C., Yeh, H.-G., 2023. Federated/Deep Learning in UAV Networks for Wildfire Surveillance. In Proceedings of the 2023 Wireless Telecommunications Symposium (WTS), Boston, MA, USA, 19–21 April 2023; pp. 1–9.

[56] Li, A., Markovic, M., Edwards, P., et al., 2024. Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing. Expert Systems with Applications. 242, 122847. DOI: https://doi.org/10.1016/j.eswa.2023.122847

[57] Li, J., Zhang, Y., Li, Y., et al., 2024. FedSparse: A Communication-Efficient Federated Learning Framework Based on Sparse Updates. Electronics. 13(24), 5042. DOI: https://doi.org/10.3390/electronics13245042

[58] Glasgow, M.R., Yuan, H., Ma, T., 2022. Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, online, 28–30 March 2022; pp. 9050–9090.

[59] Marfo, W., Tosh, D.K., Moore, S.V., 2025. Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case. arXiv preprint. arXiv:2501.15038. DOI: https://doi.org/10.48550/arXiv.2501.15038

[60] Zehtabi, S., Hosseinalipour, S., Brinton, C.G., 2022. Event-Triggered Decentralized Federated Learning over Resource-Constrained Edge Devices. arXiv preprint. arXiv:2211.12640. DOI: https://doi.org/10.48550/arXiv.2211.12640

[61] Mohammadi, S., Symeonidis, I., Balador, A., et al., 2025. Empirical Analysis of Asynchronous Federated Learning on Heterogeneous Devices: Efficiency, Fairness, and Privacy Trade-offs. arXiv preprint. arXiv:2505.07041. DOI: https://doi.org/10.48550/arXiv.2505.07041

[62] Bi, Y., 2024. Empirical Validation of Federated Learning with YOLO v7-Tiny for Road Sign Detection: A Simulation-Based Comparative Study. Applied and Computational Engineering. 49, 92–101. DOI: https://doi.org/10.54254/2755-2721/49/20241067

[63] Zhao, H., Peng, P., Chen, C., et al., 2025. FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing. arXiv preprint. arXiv:2505.08325. DOI: https://doi.org/10.48550/arXiv.2505.08325

[64] Sani, M., 2022. Cross-Layer Optimization Techniques in Federated Learning for Improving Privacy and Performance. DOI: https://doi.org/10.13140/RG.2.2.26907.68648

[65] Ma, X., Zhu, J., Lin, Z., et al., 2022. A State-of-the-Art Survey on Solving Non-IID Data in Federated Learning. Future Generation Computer Systems. 135, 244–258. DOI: https://doi.org/10.1016/j.future.2022.05.003

[66] Lee, J., Seif, M., Cho, J., et al., 2024. Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning. IEEE Network. 38(6), 388–395. DOI: https://doi.org/10.1109/MNET.2024.3395904

[67] Hu, S., Li, Y., Liu, X., et al., 2022. The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems. ACM Transactions on Intelligent Systems and Technology. 13(4), 1–32. DOI: https://doi.org/10.1145/3510540

[68] Agiollo, A., Bellavista, P., Mendula M., et al., 2024. EneA-FL: Energy-Aware Orchestration for Serverless Federated Learning. Future Generation Computer Systems. 154, 219–234. DOI: https://doi.org/10.1016/j.future.2024.01.007

[69] Millar, J., Haddadi, H., Madhavapeddy, A., 2025. Energy-Aware Deep Learning on Resource-Constrained Hardware. arXiv preprint. arXiv:2505.12523. DOI: https://doi.org/10.48550/arXiv.2505.12523

[70] Kumar, P., Debele, S.E., Sahani, J., et al., 2021. An Overview of Monitoring Methods for Assessing the Performance of Nature-Based Solutions Against Natural Hazards. Earth-Science Surveys. 217, 103603. DOI: https://doi.org/10.1016/j.earscirev.2021.103603

[71] Nikolaidis, F., Symeonides, M., Trihinas, D., 2023. Towards Efficient Resource Allocation for Federated Learning in Virtualized Managed Environments. Future Internet. 15(8), 261. DOI: https://doi.org/10.3390/fi15080261

[72] Chauhan, M., Sahoo, D.R., 2024. Towards a Greener Tomorrow: Exploring the Potential of AI, Blockchain, and IoT in Sustainable Development. Nature Environment and Pollution Technology. 23(2), 1105–1113. DOI: https://doi.org/10.46488/NEPT.2024.v23i02.044

[73] Alghamedy, F.H., El-Hagga, N., Alsumayt, A., et al., 2024. Unlocking a Promising Future: Integrating Blockchain Technology and FL-IoT in the Journey to 6G. IEEE Access. 12, 115411–115447. DOI: https://doi.org/10.1109/ACCESS.2024.3435968

[74] Qi, J., Zhou, Q., Lei, L., et al., 2021. Federated Reinforcement Learning: Techniques, Applications, and Open Challenges. arXiv preprint. arXiv:2108.11887. DOI: https://doi.org/10.48550/arXiv.2108.11887

[75] Wang, Z., Wu, F., Yu, F., et al., 2024. Federated Continual Learning for Edge-AI: A Comprehensive Survey. arXiv preprint. arXiv:2411.13740. DOI: https://doi.org/10.48550/arXiv.2411.13740

[76] Zhang, K., Cao, X., 2024. Federated Learning With Energy Harvesting Devices: An MDP Framework. arXiv preprint. arXiv:2405.10513. DOI: https://doi.org/10.48550/arXiv.2405.10513

[77] Kamble, G.U., Patil, C.S., Alman, V.V., et al., 2024. Neuromorphic Computing: Cutting-Edge Advances and Future Directions. In: Bai, K.J., Yi, Y. (Eds.). Recent Advances in Neuromorphic Computing. DOI: https://doi.org/10.5772/intechopen.1006712

Downloads

How to Cite

Albert, C. A. J., Paul, A., Mahamuni, C. V., John, S. C., & Ebenezer, E. (2025). Energy-Efficient Federated Learning at the Wireless Edge: A Survey. Journal of Electronic & Information Systems, 7(2), 66–86. https://doi.org/10.30564/jeis.v7i2.10982

Issue

Vol. 7 , Iss. 2 (October 2025)

Article Type

REVIEW

License

Copyright © 2025 Christopher Aseer J Albert, Ashli Paul, Chaitanya V Mahamuni, Sophia Chavakula John, Earnest Ebenezer

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC