Digital Twin Architecture for Smart Traffic Systems in the Cloud

Kante, Bharadwaj (2025) Digital Twin Architecture for Smart Traffic Systems in the Cloud. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The modern city transport networks rely more on low latency, data-driven control mechanisms that are not easily fulfilled by the traditional supervisory systems. To address this challenge, this study designs, implements, and evaluates a cloud-native Digital Twin (DT) architecture that integrates real-time MQTT telemetry, semantic twin modelling, and micro-service analytics to enhance intersection performance. Based on Microsoft Azure IoT Hub, Event Hub, Digital Twins, the prototype maintains a median sensor-to-twin latency of 230 ms and provides an RMSE of 6.3 vehicles per minute using a lightweight rolling-window predictor, and also reaches throughputs in excess of 2000 messages per second using only a single vCPU. Cost analysis indicates that the solution can work comfortably within the average student cloud-credit allocation and thus affirms its cost-effectiveness in case of small-scale research implementation. The experimental results fill critical gaps addressed by recent literature, i.e. real-time synchronisation and elastic scaling of traffic DTs, and provide a replicable template that smart-city authorities can use to deploy at relatively low cost and within a short time frame. Future efforts will add sophisticated predictive models, reinforcement-learning controllers, and twin federation to transform the platform into a full-service smart-city operating layer.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heeney, Sean UNSPECIFIED
Uncontrolled Keywords:	Digital Twin; Smart City; Traffic Optimisation; MQTT; Azure Digital Twins; Realtime Analytics; Cloud Computing
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 13:36
Last Modified:	26 Mar 2026 14:32
URI:	https://norma.ncirl.ie/id/eprint/9224

Actions (login required)

View Item