Digital Twin-Native AI-Driven Service Architecture for Industrial Networks

Duran, Kübra; Broadbent, Matthew; Yurdakul, Gökhan; Canberk, Berk

Abstract

The dramatic increase in the connectivity demand results in an excessive amount of Internet of Things (IoT) sensors. To meet the management needs of these large-scale networks, such as accurate monitoring and learning capabilities , Digital Twin (DT) is the key enabler. However, current attempts regarding DT implementations remain insufficient due to the perpetual connectivity requirements of IoT networks. Furthermore, the sensor data streaming in IoT networks cause higher processing time than traditional methods. In addition to these, the current intelligent mechanisms cannot perform well due to the spatiotemporal changes in the implemented IoT network scenario. To handle these challenges, we propose a DT-native AI-driven service architecture in support of the concept of IoT networks. Within the proposed DT-native architecture, we implement a TCP-based data flow pipeline and a Reinforcement Learning (RL)-based learner model. We apply the proposed architecture to one of the broad concepts of IoT networks, the Internet of Vehicles (IoV). We measure the efficiency of our proposed architecture and note 30% processing time-saving thanks to the TCP-based data flow pipeline. Moreover, we test the performance of the learner model by applying several learning rate combinations for actor and critic networks and highlight the most successive model.

Citation

Duran, K., Broadbent, M., Yurdakul, G., & Canberk, B. (2023, December). Digital Twin-Native AI-Driven Service Architecture for Industrial Networks. Presented at 2023 IEEE Globecom Workshops (GC Wkshps), Kuala Lumpur, Malaysia

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2023 IEEE Globecom Workshops (GC Wkshps)
• Start Date: Dec 4, 2023
• End Date: Dec 8, 2023
• Acceptance Date: Nov 30, 2023
• Online Publication Date: Mar 21, 2024
• Publication Date: 2023
• Deposit Date: Oct 10, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Pages: 1297-1302
• Book Title: 2023 IEEE Globecom Workshops (GC Wkshps)
• ISBN: 9798350370225
• DOI: https://doi.org/10.1109/gcwkshps58843.2023.10464857
• Keywords: Index Terms-digital twin; internet of things; internet of vehicles; reinforcement learning