Abstract
With the development of artificial intelligence and Internet of Things (IoT), the era of industry 4.0 has come. According to the prediction of IBM, with the continuous popularization of 5G technology, the IoT technology will be more widely used in factories. In recent years, federated learning has become a hot topic for Industrial Internet of Things (IIoT) researchers. However, many devices in the IIoT currently have a problem of low computing power, so these devices cannot perform well facing the tasks of training and updating models in federated learning. In order to solve the above problems, we introduce edge computing into the IIot, so that the device can complete the federated learning operation. In order to ensure the security of data transmission, blockchain is introduced as the main algorithm of equipment authentication in the system. What's more, in order to increase the efficiency and versatility of training model in IIoT, we introduce transfer learning to improve the system performance. The experimental results show that our algorithm can achieve high security and high training accuracy.
Highlights
At present, with the rapid development of Internet of Things (IoT) technology and the arrival of industry 4.0 era, Industrial Internet of Things (IIoT) has begun to enter our production and life [1]
Based on IIoT technology, modern sensors and controllers with sensing and monitoring capabilities can be integrated into the process of industrial production, and real-time data collection, intelligent analysis and mobile communication can be realized to improve the level of industrial manufacturing, realize the transformation of traditional industrial manufacturing to modernization and intelligence, and achieve a qualitative breakthrough
In order to solve the problem that the IIoT devices cannot optimize the model due to its low computing power, a federated learning mechanism based on edge computing and blockchain is designed in this manuscript to enable multiple factory edge servers to upload parameters and distribute them uniformly after cloud training model
Summary
With the rapid development of IoT technology and the arrival of industry 4.0 era, IIoT has begun to enter our production and life [1]. In order to solve the problem that the IIoT devices cannot optimize the model due to its low computing power, a federated learning mechanism based on edge computing and blockchain is designed in this manuscript to enable multiple factory edge servers to upload parameters and distribute them uniformly after cloud training model. Based on the above scheme, this manuscript proposes a secure transmission scheme in the IIoT, which uses the blockchain decentralized architecture to continuously record the transmission data in and out of the node to ensure the security of the data This solution can realize the identity authentication of IIoT devices and the secure transmission of data, creating conditions for data sharing between devices in federated learning and edge computing. The approximate transformed monokernel function can be expressed as: Algorithm 1 Federated Transfer Learning Algorithm for IIoT Devices with Low Computing Power Based on Blockchain and Edge Computin Require: Data generated by each terminal device. 1: for Before the trained model is optimal do 2: Each terminal device transmits data to the edge server; 3: Edge server deduplication; 4: Edge server training model; 5: Each edge server uploads the trained model to the cloud server; 6: The cloud server aggregates the models uploaded by the edge server; 7: The cloud server transmits the aggregated model to the edge server; 8: The edge server transmits the model to the device; 9: return Trained model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
