Self-Evolving IoT Systems through Edge-Based Autonomous Learning
DOI:
https://doi.org/10.15662/IJEETR.2023.0506011Keywords:
Autonomous IoT Systems, Edge AI, Federated Learning, Intelligent IoT, Distributed Machine Learning, Edge Intelligence, Smart CitiesAbstract
The rapid expansion of Internet of Things (IoT) deployments across industrial, urban, healthcare, and critical infrastructure environments has created highly dynamic cyber-physical systems that cannot be efficiently managed using cloud-centric intelligence alone. Centralized learning introduces latency, bandwidth bottlenecks, privacy exposure, and limited adaptability to local conditions. This paper presents a self-evolving IoT architecture in which edge devices continuously learn, adapt, and coordinate through autonomous on-device intelligence and federated learning. The proposed framework allows IoT nodes to dynamically modify sensing, inference, and communication policies in response to environmental and operational changes without centralized retraining cycles. We demonstrate through simulated smart-manufacturing and smart-city deployments that the architecture significantly improves fault-detection accuracy, response latency, and network efficiency. These results establish self-evolving edge intelligence as a foundational paradigm for next-generation autonomous IoT ecosystems. This approach directly addresses the scalability, security, and real-time decision-making challenges inherent in modern large-scale IoT deployments, where traditional centralized architectures prove inadequate due to latency, privacy concerns, and excessive resource consumption [1], [2].
References
[1] L. Atzori, A. Iera, and G. Morabito, “The Internet of Things: A survey,” IEEE Communications Surveys & Tutorials, vol. 15, no. 3, pp. 1125–1140, 2013.
[2] M. Chiang and T. Zhang, “Fog and IoT: An overview of research opportunities,” IEEE Internet of Things Journal, vol. 3, no. 6, pp. 854–864, 2016..
[3] K. Zhang, Y. Mao, S. Leng, A. Vinel, and Y. Zhang, “Delay constrained offloading for mobile edge computing in cloud-enabled vehicular networks,” IEEE Internet of Things Journal, vol. 4, no. 6, pp. 1–12, 2017.
[4] T. T. Chow, U. Raza, I. Mavromatis, and A. Khan, “FLARE: Detection and Mitigation of Concept Drift for Federated Learning based IoT Deployments,” arXiv (Cornell University) , May 2023, doi: 10.48550/arxiv.2305.08504.
[5] J. Konečný, H. B. McMahan, D. Ramage, and P. Richtárik, “Federated optimization: Distributed machine learning for on-device intelligence,” arXiv preprint arXiv:1610.02527, 2016.
[6] H. B. McMahan et al., “Communication-efficient learning of deep networks from decentralized data,” in Proc. 20th Int. Conf. on Artificial Intelligence and Statistics (AISTATS), pp. 1273–1282, 2017.
[7] P. Pace, G. Fortino, Y. Zhang⋆, and A. Liotta, “Intelligence at the Edge of Complex Networks: The Case of Cognitive Transmission Power Control,” IEEE Wireless Communications , vol. 26, no. 3, p. 97, Jun. 2019, doi: 10.1109/mwc.2019.1800354.
[8] S. Wang, T. Tuor, T. Salonidis, K. K. Leung, C. Makaya, T. He, and K. Chan, “Adaptive federated learning in resource constrained edge computing systems,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1205–1221, 2019.
[9] Y. Wang, Z. Tian, X. Fan, Y. Huo, C. Nowzari, and K. Zeng, “Distributed Swarm Learning for Internet of Things at the Edge: Where Artificial Intelligence Meets Biological Intelligence,” arXiv (Cornell University) , Nov. 2022, doi: 10.48550/arxiv.2210.16705.
[10] X. Zhang, S. Wang, and C. Liu, “Deep learning for IoT big data and streaming analytics: A survey,” Information Fusion, vol. 55, pp. 1–16, 2020.
[11] D. Gündüz, D. B. Kurka, M. Jankowski, M. M. Amiri, E. Özfatura, and S. Sreekumar, “Communicate to Learn at the Edge,” IEEE Communications Magazine , vol. 58, no. 12, p. 14, Dec. 2020, doi: 10.1109/mcom.001.2000394.
[12] P. Abudu and A. Markham, “Learning distributed communication and computation in the IoT,” Computer Communications , vol. 161, p. 150, Jul. 2020, doi: 10.1016/j.comcom.2020.07.001.
[13] Y. Liu, J. E. Fieldsend, and J. Zhu, “Edge computing for industrial Internet of Things,” IEEE Internet of Things Journal, vol. 7, no. 4, pp. 1–13, 2020.
[14] Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: Concept and applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 1–19, 2019.
[15] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge computing: Vision and challenges,” IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, 2016.
[16] T. Chen, J. Zhang, and Y. Zhou, “Machine learning for industrial IoT anomaly detection,” IEEE Network, vol. 34, no. 3, pp. 128–135, 2020.
[17] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, 2018.
[18] I. Michailidis et al. , “Embedding autonomy in large-scale IoT ecosystems using CAO and L4G-CAO,” Discover Internet of Things , vol. 1, no. 1, Feb. 2021, doi: 10.1007/s43926-021-00003-w.
[19] M. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
[20] C. Zhang, P. Patras, and H. Haddadi, “Deep learning in mobile and wireless networking,” IEEE Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2224–2287, 2019
[21] A. Imteaj and M. H. Rahman, “Federated learning for resource-constrained IoT devices,” IEEE Internet of Things Journal, vol. 7, no. 5, pp. 1–11, 2020.
[22] D. Li, Y. Wang, and Y. Zhang, “Distributed edge intelligence for autonomous IoT systems,” IEEE Access, vol. 10, pp. 44561–44574, 2022.
[23] P. Mach and Z. Becvar, “Mobile edge computing: A survey on architecture and computation offloading,” IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1628–1656, 2017.
[24] S. Samarakoon, M. Bennis, W. Saad, and M. Debbah, “Distributed federated learning for ultra-reliable low-latency vehicular communications,” IEEE Journal on Selected Areas in Communications, vol. 38, no. 10, pp. 1–15, 2020.
[25] F. Zhou, R. Q. Hu, Z. Li, and Y. Wang, “Mobile edge computing in unmanned aerial vehicle networks,” IEEE Transactions on Mobile Computing, vol. 20, no. 2, pp. 1–14, 2021.
[26] Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, “A survey on mobile edge computing,” IEEE Communications Surveys & Tutorials, vol. 19, no. 4, pp. 2322–2358, 2017.
[27] J. Park, M. Bennis, and S. L. Kim, “Wireless network intelligence at the edge,” IEEE Internet of Things Journal, vol. 6, no. 4, pp. 1–12, 2019
[28] M. Chen, W. Saad, and C. Yin, “Echo state networks for proactive caching in cloud-based IoT systems,” IEEE Network, vol. 33, no. 2, pp. 1–7, 2019.
[29] S. Niknam, H. S. Dhillon, and J. H. Reed, “Federated learning for wireless communications,” IEEE Communications Magazine, vol. 58, no. 1, pp. 46–51, 2020.
[30] A. Yousefpour et al., “All one needs to know about fog computing,” IEEE Communications Surveys & Tutorials, vol. 20, no. 3, pp. 1999–2037, 2018.
[31] H. Ye, G. Y. Li, and B.-H. Juang, “Deep reinforcement learning for resource allocation in V2V communications,” IEEE Transactions on Vehicular Technology, vol. 68, no. 4, pp. 1–14, 2019.
[32] L. Wang, M. Chen, and X. Li, “AI-driven autonomous networking for future IoT systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 8, pp. 1–14, 2022.
[33] T. Zhang, C. He, T. Ma, L. Gao, M. Ma, and S. Avestimehr, “Federated Learning for Internet of Things,” p. 413, Nov. 2021, doi: 10.1145/3485730.3493444.
[34] A. Farajzadeh, A. Yadav, and H. Yanıkömeroğlu, “Multi-Tier Hierarchical Federated Learning-assisted NTN for Intelligent IoT Services,” arXiv (Cornell University) , May 2023, doi: 10.48550/arxiv.2305.05463.
[35] A. Z. H. Yapp et al. , “Communication-efficient and Scalable Decentralized Federated Edge Learning,” p. 5032, Aug. 2021, doi: 10.24963/ijcai.2021/720.
[36] S. Liu et al. , “Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey,” arXiv (Cornell University) , Sep. 2023, doi: 10.48550/arxiv.2309.15467.
[37] L. Ridolfi, D. Naseh, S. S. Shinde, and D. Tarchi, “Implementation and Evaluation of a Federated Learning Framework on Raspberry PI Platforms for IoT 6G Applications,” Future Internet , vol. 15, no. 11, p. 358, Oct. 2023, doi: 10.3390/fi15110358.
[38] S. Liu et al. , “Enabling Resource-Efficient AIoT System With Cross-Level Optimization: A Survey,” IEEE Communications Surveys & Tutorials , vol. 26, no. 1, p. 389, Sep. 2023, doi: 10.1109/comst.2023.3319952.
[39] T. Zhang, L. Gao, C. He, M. Zhang, B. Krishnamachari, and S. Avestimehr, “Federated Learning for Internet of Things: Applications, Challenges, and Opportunities,” arXiv (Cornell University) , Nov. 2021, doi: 10.48550/arxiv.2111.07494.
[40] A. Akhtarshenas, M. A. Vahedifar, N. Ayoobi, B. Maham, and T. Alizadeh, “Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications,” arXiv (Cornell University) , Oct. 2023, doi: 10.48550/arxiv.2310.05269.
[41] M. A. Ferrag et al. , “Edge Learning for 6G-Enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses,” IEEE Communications Surveys & Tutorials , vol. 25, no. 4, p. 2654, Jan. 2023, doi: 10.1109/comst.2023.3317242.
[42] H. Fang, X. Wang, Z. Xiao, and L. Hanzo, “Autonomous Collaborative Authentication with Privacy Preservation in 6G: From Homogeneity to Heterogeneity,” IEEE Network , vol. 36, no. 6, p. 28, Jul. 2022, doi: 10.1109/mnet.002.2100312.
[43] J. Konečný, H. B. McMahan, D. Ramage, and P. Richtárik, “Federated Optimization: Distributed Machine Learning for On-Device Intelligence,” arXiv (Cornell University) , Oct. 2016, doi: 10.48550/arxiv.1610.02527.
