La Trobe
1204663_Yang,W_2023.pdf (3.91 MB)
Download file

Optimizing Federated Learning With Deep Reinforcement Learning for Digital Twin Empowered Industrial IoT

Download (3.91 MB)
journal contribution
posted on 2023-08-18, 02:32 authored by W Yang, Wei XiangWei Xiang, Y Yang, Peng ChengPeng Cheng
The accelerated development of the Industrial Internet of Things (IIoT) is catalyzing the digitalization of industrial production to achieve Industry 4.0. In this article, we propose a novel digital twin (DT) empowered IIoT (DTEI) architecture, in which DTs capture the properties of industrial devices for real-time processing and intelligent decision making. To alleviate data transmission burden and privacy leakage, we aim to optimize federated learning (FL) to construct the DTEI model. Specifically, to cope with the heterogeneity of IIoT devices, we develop the DTEI-assisted deep reinforcement learning method for the selection process of IIoT devices in FL, especially for selecting IIoT devices with high utility values. Furthermore, we propose an asynchronous FL scheme to address the discrete effects caused by heterogeneous IIoT devices. Experimental results show that our proposed scheme features faster convergence and higher training accuracy compared to the benchmark.


The work of Wei Yang and Yuan Yang was supported in part by the Shaanxi Innovation Capability Support project under Grant 2021TD-25 and in part by the Natural Science Basic Research Program of Shaanxi under Grant 2021JQ-478. Paper no. TII-22-1246.(Corresponding authors: Wei Xiang; Yuan Yang.)


Publication Date



IEEE Transactions on Industrial Informatics






10p. (p. 1884-1893)


IEEE - Institute of Electrical and Electronics Engineers



Rights Statement

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see