The recent emergence of advanced computing technologies has opened a world of possibilities for bridging virtual-physical spaces in the future of urban air mobility (UAM). Digital twin technology (DT) introduces a coupled virtual-physical asset system that evolves over time in their digital and physical state-spaces associated with the real-time exchange of observed data and control inputs for high-fidelity operational services in UAM, such as traffic management, or vehicle maintenance. On the other hand, edge computing has been envisioned as a dominant computing paradigm in future UAM infrastructures to enable infinitesimal-latency processing of massive and heterogeneous data acquired from ubiquitous devices and vehicles. Furthermore, federated learning (FL) has recently been proposed to resolve the performance and security problems of traditional AI techniques featured by centralized data collection and training to offer a decentralized and cooperative data training pattern among a huge number of devices/vehicles (aka., agents) in multi agent DT systems for UAM. Lastly, the blockchain has emerged as a ledger technology in which data and processes are divided into tiny data blocks and concatenated into a series to reinforce the security and scalability of decentralized computing patterns. Realizing the advances and integration of the emerging technologies mentioned above is of paramount importance for the development of DT systems in UAM. Previous studies have not completely considered the integration and harmony of these existing technologies for the development of UAM DT systems. There has also been a significant lack in comprehension and integration of emerging technologies for the development of UAM-DT systems. In that context, this study proposes a comprehensive integrated UAM-DT platform and solution of FL with the blockchain in edge computing for the development of UAM-DT systems, called BlockFE-DT. First, we introduce the adoption of a probabilistic graphical model as a formal mathematical foundation of coupled digital-physical twin systems for UAM, particularly for unmanned aircrafts. Afterwards, we review the fundamental concepts of FL, blockchain, and edge computing technologies to explore and propose an integration framework of FL with the blockchain in edge computing in the context of UAM-DT systems. Key issues in the integration are assimilated including explainable AI, dependability, and security. This work provides ground-breaking concepts and architectures for a blockchain empowered FL framework with edge computing in future UAM-DT systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Blockchain Empowered Federated Learning with Edge Computing for Digital Twin Systems in Urban Air Mobility


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Lee, Sangchul (Herausgeber:in) / Han, Cheolheui (Herausgeber:in) / Choi, Jeong-Yeol (Herausgeber:in) / Kim, Seungkeun (Herausgeber:in) / Kim, Jeong Ho (Herausgeber:in) / Nguyen, Tuan Anh (Autor:in) / Kaliappan, Vishnu Kumar (Autor:in) / Jeon, Sangwoo (Autor:in) / Jeon, Kwon-su (Autor:in) / Lee, Jae-Woo (Autor:in)

    Kongress:

    Asia-Pacific International Symposium on Aerospace Technology ; 2021 ; Korea (Republic of) November 15, 2021 - November 17, 2021



    Erscheinungsdatum :

    30.09.2022


    Format / Umfang :

    16 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    AFLChain: Blockchain-enabled Asynchronous Federated Learning in Edge Computing Network

    Huang, Xiaoge / Deng, Xuesong / Chen, Qianbin et al. | IEEE | 2023


    Blockchain-Enabled Federated Learning for Enhanced Collaborative Intrusion Detection in Vehicular Edge Computing

    Abou El Houda, Zakaria / Moudoud, Hajar / Brik, Bouziane et al. | IEEE | 2024


    A Clustered ZC in Cloud Computing Empowered by Blockchain

    Huo, Ligang / Bu, Bing / Li, Qichang et al. | IEEE | 2022


    Twin Scenarios Establishment for Autonomous Vehicle Digital Twin Empowered SOTIF Assessment

    Hou, Zhonglin / Wang, Shouwei / Liu, Hong et al. | IEEE | 2024