Low-Latency Federated Learning and Blockchain for Edge Association in Digital Twin Empowered 6G Networks

• Published in: IEEE transactions on industrial informatics Vol. 17; no. 7; pp. 5098 - 5107
• Main Authors: Lu, Yunlong, Huang, Xiaohong, Zhang, Ke, Maharjan, Sabita, Zhang, Yan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-07-2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 6G mobile communication; Bandwidths; Blockchain; Collaborative work; communication efficiency; Cryptography; Data models; Data processing; Digital twin; Digital twins; Federated learning; Industrial applications; Internet of Things; Machine learning; Multiagent systems; Network latency; New technology; Optimization; Privacy; Robustness (mathematics); Servers; Wireless communications; Wireless networks
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2020.3017668

Emerging technologies, such as digital twins and 6th generation (6G) mobile networks, have accelerated the realization of edge intelligence in industrial Internet of Things (IIoT). The integration of digital twin and 6G bridges the physical system with digital space and enables robust instant wireless connectivity. With increasing concerns on data privacy, federated learning has been regarded as a promising solution for deploying distributed data processing and learning in wireless networks. However, unreliable communication channels, limited resources, and lack of trust among users hinder the effective application of federated learning in IIoT. In this article, we introduce the digital twin wireless networks (DTWN) by incorporating digital twins into wireless networks, to migrate real-time data processing and computation to the edge plane. Then, we propose a blockchain empowered federated learning framework running in the DTWN for collaborative computing, which improves the reliability and security of the system and enhances data privacy. Moreover, to balance the learning accuracy and time cost of the proposed scheme, we formulate an optimization problem for edge association by jointly considering digital twin association, training data batch size, and bandwidth allocation. We exploit multiagent reinforcement learning to find an optimal solution to the problem. Numerical results on real-world dataset show that the proposed scheme yields improved efficiency and reduced cost compared to benchmark learning methods.