FedTwin: Blockchain-Enabled Adaptive Asynchronous Federated Learning for Digital Twin Networks
- Publisher:
- Institute of Electrical and Electronics Engineers (IEEE)
- Publication Type:
- Journal Article
- Citation:
- IEEE Network, 2022, 36, (6), pp. 183-190
- Issue Date:
- 2022-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Network_Magazine_2021 v2.pdf | Submitted version | 260.21 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
The fast proliferation of digital twin (DT) establishes a direct connection between the physical entity and its deployed digital representation. As markets shift toward mass customization and new service delivery models, the digital representation has become more adaptive and agile by forming digital twin networks (DTN). DTN institutes a real-time single source of truth everywhere. However, there are several issues preventing DTN from further application, which are centralized processing, data falsification, privacy leakage, lack of incentive mechanism, etc. To make DTN better meet the ever-changing demands, we propose a novel blockchain-enabled adaptive asynchronous federated learning (FedTwin) paradigm for privacy-preserving and decentralized DTN. We design Proof-of-Federalism (PoF), which is a tailor-made consensus algorithm for autonomous DTN. In each DT's local training phase, generative adversarial network enhanced differential privacy is used to protect the privacy of local model parameters while a modified Isolation Forest is deployed to filter out the falsified DTs. In the global aggregation phase, an improved Markov decision process is leveraged to select optimal DTs to achieve adaptive asynchronous aggregation while providing a roll-back mechanism to redact the falsified global models. With this paper, we aim to provide insights to the forthcoming researchers and readers in this under-explored domain.
Please use this identifier to cite or link to this item: