IoT-Based Digital Twin Framework for Real-Time Sensor-data Visualization over 5G Vehicular Networks

Abstract

The integration of digital twin (DT) technology with 5G vehicular networks provides a revolutionary approach for real-time monitoring and predictive maintenance in autonomous transportation systems. Keeping high-fidelity virtual replicas, however, requires low-latency and high-reliability data synchronization from a multitude of vehicle sensors. In this paper, we propose an IoT-based Digital Twin framework for real-time sensor-data visualization on 5G networks. We assess the performance of the framework using ns-3 simulation platform under different vehicle densities, focusing on important metrics such as end-to-end uplink delay, packet delivery ratio (PDR), and throughput. The results show that the proposed system with 500 ms sensing interval and load-aware scheduling provides a total end-to-end delay of 42.5 ms and PDR of 0.99, which are manageable even at a density of 100 vehicles.. Comparisons with a FIFO baseline and high-frequency traffic scenarios highlight the framework’s efficiency in mitigating buffer congestion and resource saturation. This work provides a scalable foundation for real-time vehicular state visualization at the network edge.