Edge-Enabled IoT-Based Dynamic Traffic Management System

Abstract

This paper presents an edge-enabled IoT framework for dynamic urban traffic management that computes and enforces context-aware speed recommendations in real time. Vehicles supply on-board diagnostics (OBD-II) data to an embedded edge device (Raspberry Pi), which performs local pre-processing to extract speed and density indicators and publishes compact messages via MQTT secured with TLS to a cloud service. The cloud executes a lightweight control model that estimates an optimal speed v<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">opt</inf> as a function of traffic density, congestion index, road priority, and weather, and disseminates the result to roadside Variable Speed Limit Signs (VSLS). The pipeline operates with periodic updates and event-triggered refresh. Experiments in simulated urban scenarios, complemented by short field tests, show improved throughput (+30%), reduced speed variability (−57%), higher average travel speed (+16%), and lower fuel consumption (−17%), with an estimated 15–20% reduction in NOx emissions. End-to-end decision latency averages 320ms, with under 100ms at the edge. These results indicate that combining in-vehicle edge processing with secure cloud coordination yields timely, scalable traffic harmonization while limiting bandwidth and energy costs on constrained devices.