News of the Kabardino-Balkarian Scientific Center of the Russian Academy of SciencesNews of the Kabardino-Balkarian Scientific Center of the Russian Academy of SciencesИзвестия Кабардино-Балкарского научного центра РАН1991-66392949-194025599610.35330/1991-6639-2024-26-2-26-33RTVEBBИнформатика и информационные процессыInformatics and information processesReview ArticleFederated learning for IoT and AIoT: applications, challenges and perspectivesФедеративное обучение для IoT и AIoT: применения, проблемы и перспективыhttps://orcid.org/0009-0009-1536-7917EleevHazrat-Ali M.ЕлеевХазрат-Али Муратович
Russian Federation

Научно-образовательный центр, аспирант

Scientific and Educational Center, Post-graduate student

khazratalieleev@gmail.comKabardino-Balkarian Scientific Center of the Russian Academy of SciencesКабардино-Балкарский научный центр Российской академии наукru15042024202426226333105202431052024Copyright ©; 2024, Елеев Х.М.Copyright ©; 2024, Eleev H.M.2024Елеев Х.М.Eleev H.M.https://creativecommons.org/licenses/by/4.0https://journals.rcsi.science/1991-6639/article/view/255996

This paper discusses the concept of federated learning (FL), a distributed collaborative approach to artificial intelligence (AI) that enables AI training on distributed IoT devices without need for data sharing. Approaches and methods for implementing FL for AIoT devices have been classified into three types of federated learning architecture for organizing interactions between learning participants, centralized, decentralized, and hybrid. Approaches based on different technologies such as Knowledge Distillation, blockchain, wireless networks like Mesh, Hybrid-IoT, DHA-FL are considered. For each technology considered, the main advantages, problems and challenges are outlined. The paper sums up with conclusions about the prospects of FL development for IoT and AIoT.

В статье рассматривается концепция федеративного обучения (FL) – распределенного совместного подхода к искусственному интеллекту (AI), который позволяет обучать AI на распределенных IoT устройствах без необходимости обмена данными. Подходы и методы реализации FL для AIoT устройств были классифицированы по трем типам архитектуры федеративного обучения для организации взаимодействия между участниками обучения: централизованная, децентрализованная и гибридная. Рассмотрены подходы, основанные на различных технологиях, таких как Knowledge Distillation, блокчейн, беспроводные сети типа Mesh, Hybrid-IoT, DHA-FL. Для каждой рассмотренной технологии обозначены основные преимущества, проблемы и вызовы. В заключение сделаны выводы о перспективах развития FL для IoT и AIoT.

Internet of things (IoT)federated learning (FL)artificial intelligence of things (AIoT)blockchainarchitectureИнтернет вещей (IoT)федеративное обучение (FL)искусственный интеллект вещей (AIoT)блокчейнархитектураKhanna A., Kaur S. Internet of Things (IoT), Applications and challenges: a comprehensive review. Wireless Personal Communications. 2020. Vol. 114. Pp. 1687–1762. DOI: 10.1007/ s11277-020-07446-4Lynn Th., Takako E.P., Maria N.A. et al. The Internet of Things: definitions, key concepts, and reference architectures. The Cloud-to-Thing. 2020. Pp. 1–22. DOI: 10.1109/JIOT.2022.3229374Efremov M.A., Kholod I.I. Development of the architecture of a universal federated learning framework. Programmnyye produkty i sistemy [Software products and systems]. 2022. Vol. 35. No. 2. Pp. 263–272. DOI: 10.15827/0236-235X.138.263-272. (In Russian)Ефремов М. А., Холод И. И. Разработка архитектуры универсального фреймворка федеративного обучения // Программные продукты и системы. 2022. Т. 35. №. 2. Pp. 263–272. DOI: 10.15827/0236-235X.138.263-272Latif U. Khan, Saad W., Han Z. et al. Federated learning for internet of things: recent advances, taxonomy, and open challenges. IEEE Communications Surveys & Tutorials. 2021. Vol. 23. No. 3. Pp. 1759–1799. DOI: 10.1109/COMST.2021.3090430Sanchez-Iborra R. LPWAN and embedded machine learning as enablers for the next generation of wearable devices. Sensors. 2021. Vol. 21. No. 15. P. 5218. DOI: 10.3390/s21155218Fan B., Jiang S., Su X., Hui P. Model-heterogeneous federated learning for internet of things: enabling technologies and future directions [Электронный ресурс]: arXiv – CS – Distributed, Parallel and Cluster Computing, 2023. URL: https://arxiv.org/pdf/2312.12091.pdf (дата обращения: 19.01.2024).Liu T., Ling Z., Xia J. et al. Efficient federated learning for AIoT applications using knowledge distillation. IEEE Internet of Things Journal. 2023. Vol. 10. No. 8. Pp. 7229–7243. DOI: 10.1109/JIOT.2022.3229374Salama A., Stergioulis A., Ali Zaidi S., McLernon D. Decentralized federated learning on the edge over wireless mesh networks. IEEE Access. 2023. Vol. 11. Pp. 124709–124724. DOI: 10.1109/ ACCESS.2023.3329362Liu Y., Ai Z., Sun S. et al. FedCoin: A Peer-to-peer payment system for federated learning [Электронный ресурс]: arXiv, 2023. URL: https://arxiv.org/pdf/2002.11711.pdf (дата обращения: 22 января, 2024).Wu X., Wang Z., Zhao J. et al. FedBC: Blockchain-based decentralized federated learning. IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). Dalian, 2020. Pp. 217–221. DOI: 10.1109/ICAICA50127.2020.9182705Zhao Y., Zhao J., Jiang L. et al. Privacy-preserving blockchain-based federated learning for IoT device. EEE Internet of Things Journal. 2021. Vol. 8. No. 3. Pp. 1817–1829. DOI: 10.1109/ JIOT.2020.3017377Sagirlar G., Carminati B., Ferrari E. et al. Hybrid-IoT: Hybrid blockchain architecture for internet of things – PoW sub-blockchains. IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) / IEEE Computer Society. Los Alamitos, 2018. Pp. 1007–1016. DOI: 10.1109/Cybermatics_2018.2018.00189Gemeliarana I.G.A.K., Sari. R.F. Evaluation of proof of work (POW) blockchains security network on selfish mining. International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). Yogyakarta, 2018. Pp. 126–130. DOI: 10.1109/ISRITI.2018.8864381Fahim S., Mahmood S., Katibur Rahman S.M. Blockchain: A Comparative study of consensus algorithms PoW, PoS, PoA, PoV. International Journal of Mathematical Sciences and Computing (IJMSC). 2023. Vol. 9. No. 3. Pp. 46–57. DOI: 10.5815/ijmsc.2023.03.04Houston Huff W., Balakrishnan R., Hao Feng et al. DHA-FL: Enabling efficient and effective AIoT via decentralized hierarchical asynchronous federated learning. MLSys-RCLWN, Miami, 2023.Zhang T., Gao L., He C. et al. Federated learning for internet of things: applications, challenges, and opportunities. IEEE Internet of Things Magazine, 2022. Vol. 5. No. 1. Pp. 24–29. DOI: 10.1109/IOTM.004.2100182