TY - JOUR
T1 - Federated Learning for Industrial Internet of Things in Future Industries
AU - Nguyen, Dinh C.
AU - Ding, Ming
AU - Pathirana, Pubudu N.
AU - Seneviratne, Aruna
AU - Li, Jun
AU - Niyato, Dusit
AU - Poor, H. Vincent
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/12/1
Y1 - 2021/12/1
N2 - The Industrial Internet of Things (IIoT) offers promising opportunities to revolutionize the operation of industrial systems and become a key enabler of future industries. Recently, artificial intelligence (AI) has been widely utilized for realizing intelligent IIoT applications where AI techniques require centralized data collection and processing. However, this is not always feasible in realistic scenarios due to the high scalability of modern IIoT networks and growing industrial data confidentiality. Federated Learning (FL), as an emerging collaborative AI approach, is particularly attractive for intelligent IIoT networks by coordinating multiple IIoT devices and machines to perform AI training at the network edge while helping protect user privacy and confidential business information. In this article, we provide a detailed overview and discussions of the emerging applications of FL in several key IIoT services and applications. A case study is also provided to demonstrate the feasibility of FL in IIoT. Finally, we highlight a range of interesting open research topics that need to be addressed for the full realization of FL-IIoT in future industries.
AB - The Industrial Internet of Things (IIoT) offers promising opportunities to revolutionize the operation of industrial systems and become a key enabler of future industries. Recently, artificial intelligence (AI) has been widely utilized for realizing intelligent IIoT applications where AI techniques require centralized data collection and processing. However, this is not always feasible in realistic scenarios due to the high scalability of modern IIoT networks and growing industrial data confidentiality. Federated Learning (FL), as an emerging collaborative AI approach, is particularly attractive for intelligent IIoT networks by coordinating multiple IIoT devices and machines to perform AI training at the network edge while helping protect user privacy and confidential business information. In this article, we provide a detailed overview and discussions of the emerging applications of FL in several key IIoT services and applications. A case study is also provided to demonstrate the feasibility of FL in IIoT. Finally, we highlight a range of interesting open research topics that need to be addressed for the full realization of FL-IIoT in future industries.
UR - http://www.scopus.com/inward/record.url?scp=85118049603&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118049603&partnerID=8YFLogxK
U2 - 10.1109/MWC.001.2100102
DO - 10.1109/MWC.001.2100102
M3 - Article
AN - SCOPUS:85118049603
SN - 1536-1284
VL - 28
SP - 192
EP - 199
JO - IEEE Wireless Communications
JF - IEEE Wireless Communications
IS - 6
ER -