文献类型：期刊文献

英文题名：FedTwin: Blockchain-Enabled Adaptive Asynchronous Federated Learning for Digital Twin Networks

作者：Qu, Youyang[1];Gao, Longxiang[2];Xiang, Yong[3];Shen, Shigen[5];Yu, Shui[4]

机构：[1]Commonwealth Sci & Ind Res Org, Data61, Canberra, Australia;[2]Qilu Univ Technol, Shandong Acad Sci, Jinan, Shandong, Peoples R China;[3]Deakin Univ, Geelong, Vic, Australia;[4]Univ Technol Sydney, Ultimo, NSW, Australia;[5]Shaoxing Univ, Shaoxing, Peoples R China

年份：2022

卷号：36

期号：6

起止页码：183

外文期刊名：IEEE NETWORK

收录：SCI-EXPANDED(收录号：WOS:001011249700024)、、EI(收录号：20223312567033)、Scopus(收录号：2-s2.0-85135749924)、WOS

基金：This work is partially supported by the Zhejiang Provincial Natural Science Foundation of China under Grant LZ22F020002

语种：英文

外文关键词：Training; Adaptation models; Computational modeling; Task analysis; Blockchains; Privacy; Digital twins

外文摘要：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 (DTNs). The DTN institutes a real-time single source of truth everywhere. However, there are several issues preventing DTNs from further application, including centralized processing, data falsification, privacy leakage, lack of incentive mechanism, and so on. To make DTN better meet the ever changing demands, we propose a novel block-chain-enabled adaptive asynchronous federated learning (FedTwin) paradigm for privacy-preserving and decentralized DTNs. We design Proof-of-Federalism (PoF), which is a tailor-made consensus algorithm for autonomous DTNs. 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 rollback mechanism to redact the falsified global models. With this article, we aim to provide insights to forthcoming researchers and readers in this under-explored domain.