Practical Evaluation of Federated Learning in Edge AI for IoT

Sauryadeep Pal - Multimedia University, Cyberjaya, 63100, Malaysia
Muhammad Umair - Multimedia University, Cyberjaya, 63100, Malaysia
Wooi-Haw Tan - Multimedia University, Cyberjaya, 63100, Malaysia
Yee-Loo Foo - Multimedia University, Cyberjaya, 63100, Malaysia

Citation Format:



AI running locally on IoT Edge devices is called Edge AI. Federated Learning (FL) is a Machine Learning (ML) technique that builds upon the concept of distributed computing and preserves data privacy while still supporting trainable AI models. This paper evaluates the FL regarding practical CPU usage and training time. Additionally, the paper presents how biased IoT Edge clients affect the performance of an AI model. Existing literature on the performance of FL indicates that it is sensitive to imbalanced data distributions and does not easily converge in the presence of heterogeneous data. Furthermore, model training uses significant on-device resources, and low-power IoT devices cannot train complex ML models. This paper investigates optimal training parameters to make FL more performant and researches the use of model compression to make FL more accessible to IoT Edge devices. First, a flexible test environment is created that can emulate clients with biased data samples. Each compressed version of the ML model is used for FL. Evaluation is done regarding resources used and the overall ML model performance. Our current study shows an accuracy improvement of 1.16% from modifying training parameters, but a balance is needed to prevent overfitting. Model compression can reduce resource usage by 5.42% but tends to accelerate overfitting and increase model loss by 9.35%.


Internet-of-Things (IoT); Edge AI; Machine Learning (ML); Federated Learning (FL).

Full Text:



P. K M and N. B S, “AIoT - Artificial Intelligence of Things,†Int. J. Adv. Res. Sci. Commun. Technol., pp. 88–92, Apr. 2021, doi: 10.48175/ijarsct-v4-i3-013.

A. Matin, M. R. Islam, X. Wang, H. Huo, and G. Xu, “AIoT for sustainable manufacturing: Overview, challenges, and opportunities,†Internet of Things, vol. 24, p. 100901, Dec. 2023, doi: 10.1016/J.IOT.2023.100901.

Y. Wu, “Cloud-Edge Orchestration for the Internet of Things: Architecture and AI-Powered Data Processing,†IEEE Internet Things J., vol. 8, no. 16, pp. 12792–12805, Aug. 2021, doi: 10.1109/JIOT.2020.3014845.

F. Firouzi, B. Farahani, and A. Marinšek, “The convergence and interplay of edge, fog, and cloud in the AI-driven Internet of Things (IoT),†Inf. Syst., vol. 107, p. 101840, Jul. 2022, doi: 10.1016/J.IS.2021.101840.

U. F. Mustapha, A. W. Alhassan, D. N. Jiang, and G. L. Li, “Sustainable aquaculture development: a review on the roles of cloud computing, internet of things and artificial intelligence (CIA),†Rev. Aquac., vol. 13, no. 4, pp. 2076–2091, Sep. 2021, doi: 10.1111/RAQ.12559.

J. Ren, D. Zhang, S. He, Y. Zhang, and T. Li, “A Survey on End-Edge-Cloud Orchestrated Network Computing Paradigms,†ACM Comput. Surv., vol. 52, no. 6, Oct. 2019, doi: 10.1145/3362031.

C. Mwase, Y. Jin, T. Westerlund, H. Tenhunen, and Z. Zou, “Communication-efficient distributed AI strategies for the IoT edge,†Futur. Gener. Comput. Syst., vol. 131, pp. 292–308, Jun. 2022, doi: 10.1016/J.FUTURE.2022.01.013.

P. Mell and T. Grance, “The NIST definition of cloud computing,†National Institute of Standards and Technology, Gaithersburg, MD, 2011. doi: 10.6028/NIST.SP.800-145.

D. Saadia, “Integration of Cloud Computing, Big Data, Artificial Intelligence, and Internet of Things: Review and Open Research Issues,†, vol. 16, no. 1, pp. 10–17, Jan. 2021, doi: 10.4018/IJWLTT.2021010102.

G. K. Sriram, “Edge Computing Vs. Cloud Computing: an Overview of Big Data Challenges and Opportunities for Large Enterprises,† @International Res. J. Mod. Eng., vol. 04, no. 01, pp. 1–6, 2022.

L. Sun, L. Sun, X. Jiang, H. Ren, H. Ren, and Y. Guo, “Edge-Cloud Computing and Artificial Intelligence in Internet of Medical Things: Architecture, Technology and Application,†IEEE Access, vol. 8, pp. 101079–101092, 2020, doi: 10.1109/ACCESS.2020.2997831.

S. Duan et al., “Distributed Artificial Intelligence Empowered by End-Edge-Cloud Computing: A Survey,†IEEE Commun. Surv. Tutorials, vol. 25, no. 1, pp. 591–624, 2023, doi: 10.1109/COMST.2022.3218527.

F. Saeik et al., “Task offloading in Edge and Cloud Computing: A survey on mathematical, artificial intelligence and control theory solutions,†Comput. Networks, vol. 195, p. 108177, Aug. 2021, doi: 10.1016/J.COMNET.2021.108177.

A. Singh, S. C. Satapathy, A. Roy, and A. Gutub, “AI-Based Mobile Edge Computing for IoT: Applications, Challenges, and Future Scope,†Arab. J. Sci. Eng. 2021 478, vol. 47, no. 8, pp. 9801–9831, Jan. 2022, doi: 10.1007/S13369-021-06348-2.

K. Cao, Y. Liu, G. Meng, and Q. Sun, “An Overview on Edge Computing Research,†IEEE Access, vol. 8, pp. 85714–85728, 2020, doi: 10.1109/ACCESS.2020.2991734.

Z. Xu, W. Liu, J. Huang, C. Yang, J. Lu, and H. Tan, “Artificial Intelligence for Securing IoT Services in Edge Computing: A Survey,†Secur. Commun. Networks, vol. 2020, 2020, doi: 10.1155/2020/8872586.

Y. Xiao, Y. Jia, C. Liu, X. Cheng, J. Yu, and W. Lv, “Edge Computing Security: State-of-The-Art and Challenges,†Proc. IEEE, vol. 107, no. 8, pp. 1608–1631, Aug. 2019, doi: 10.1109/JPROC.2019.2918437.

H. Zeyu, X. Geming, W. Zhaohang, and Y. Sen, “Survey on Edge Computing Security,†Proc. - 2020 Int. Conf. Big Data, Artif. Intell. Internet Things Eng. ICBAIE 2020, pp. 96–105, Jun. 2020, doi: 10.1109/ICBAIE49996.2020.00027.

M. Caprolu, R. Di Pietro, F. Lombardi, and S. Raponi, “Edge Computing Perspectives: Architectures, Technologies, and Open Security Issues,†Proc. - 2019 IEEE Int. Conf. Edge Comput. EDGE 2019 - Part 2019 IEEE World Congr. Serv., pp. 116–123, Jul. 2019, doi: 10.1109/EDGE.2019.00035.

S. S. Ambarkar and N. Shekokar, “Toward Smart and Secure IoT Based Healthcare System,†Stud. Syst. Decis. Control, vol. 266, pp. 283–303, 2020, doi: 10.1007/978-3-030-39047-1_13/COVER.

H. A. El Zouka and M. M. Hosni, “Secure IoT communications for smart healthcare monitoring system,†Internet of Things, vol. 13, p. 100036, Mar. 2021, doi: 10.1016/J.IOT.2019.01.003.

J. B. Awotunde, R. G. Jimoh, S. O. Folorunso, E. A. Adeniyi, K. M. Abiodun, and O. O. Banjo, “Privacy and Security Concerns in IoT-Based Healthcare Systems,†Internet of Things, pp. 105–134, 2021, doi: 10.1007/978-3-030-75220-0_6/COVER.

S. Soro, “TinyML for Ubiquitous Edge AI,†no. 20, Feb. 2021.

T. Sipola, J. Alatalo, T. Kokkonen, and M. Rantonen, “Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software,†Conf. Open Innov. Assoc. Fruct, vol. 2022-April, no. i, pp. 320–331, 2022, doi: 10.23919/FRUCT54823.2022.9770931.

C. Zhang, Y. Xie, H. Bai, B. Yu, W. Li, and Y. Gao, “A survey on federated learning,†Knowledge-Based Syst., vol. 216, p. 106775, 2021, doi: 10.1016/j.knosys.2021.106775.

T. Liu, J. Ding, T. Wang, M. Pan, and M. Chen, “Towards Fast and Accurate Federated Learning with Non-IID Data for Cloud-Based IoT Applications,†J. Circuits, Syst. Comput., vol. 31, no. 13, pp. 1–10, 2022, doi: 10.1142/S0218126622502358.

Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and V. Chandra, “Federated Learning with Non-IID Data,†Comput. J., no. May, Jun. 2018, doi: 10.48550/arXiv.1806.00582.

T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated Optimization in Heterogeneous Networks,†2018.

M. Tahir and M. I. Ali, “On the Performance of Federated Learning Algorithms for IoT,†IoT, vol. 3, no. 2, pp. 273–284, 2022, doi: 10.3390/iot3020016.

Y. Gao et al., “End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things,†Proc. IEEE Symp. Reliab. Distrib. Syst., vol. 2020-Septe, pp. 91–100, 2020, doi: 10.1109/SRDS51746.2020.00017.

M. Koklu and I. A. Ozkan, “Multi-class classification of dry beans using computer vision and machine learning techniques,†Comput. Electron. Agric., vol. 174, p. 105507, Jul. 2020, doi: 10.1016/j.compag.2020.105507.

Z. Liu, M. Sun, T. Zhou, G. Huang, and T. Darrell, “Rethinking the value of network pruning,†7th Int. Conf. Learn. Represent. ICLR 2019, pp. 1–21, 2019.

S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding,†4th Int. Conf. Learn. Represent. ICLR 2016 - Conf. Track Proc., pp. 1–14, 2016.

B. Jacob et al., “Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference,†Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 2704–2713, 2018, doi: 10.1109/CVPR.2018.00286.