.png){kind=icon}
.png){kind=icon}
Return
A hierarchical federated learning approach based on cloud–fog–edge computing architecture for distributed smart manufacturing systems
.png){kind=icon}
PRE
AI
W
T
Y
H
G
DOI：10.1016/j.rcim.2026.103312.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Hierarchical modeling of distributed manufacturing systems via a cloud–fog–edge computing architecture. • Design of a federated learning algorithm with a convergence proof, effectively mitigating statistical heterogeneity. • Closed-form solutions derived for cloud and fog nodes, with local optimizers for edge nodes. • The proposed method is scalable and downward-compatible, FedAvg and FedProx are special cases. • An accelerated variant enables asynchronous fog–cloud optimization to improve efficiency.
Keywords:
hierarchical federated learning
cloud–fog–edge computing
distributed manufacturing systems
statistical heterogeneity
asynchronous optimization
Journal
R
IF:
11.4
Papers:
3.3K
Citations:
1.3W
Organization
Cited Papers