Integrating LoRaWAN and Edge Computing for Dynamic Intelligent Traffic Signals

Abstract: Traffic congestion is a significant urban challenge, exacerbated by increasing populations and vehicle usage, leading to delays and increased carbon emissions. Connected Autonomous Vehicles (CAVs), equipped with an array of advanced sensors and smart technologies, present a promising solution to mitigate congestion issues and reduce carbon emissions. This study explores the integration of LoRaWAN (Long Range Wide Area Network) and edge computing to create a dynamic and intelligent traffic signal system. LoRaWAN's long-range, low-power communication capabilities, combined with edge computing's ability to process data near the source, provide a strong foundation for real-time traffic management. Leveraging LoRaWAN and edge devices, we propose a framework to demonstrate how the combined use of these technologies can optimize traffic flow through dynamic signals, potentially mitigating congestion issues and promoting sustainable urban mobility. The system architecture is designed with integrated traffic sensors, LoRaWAN modules, and edge nodes embedded within traffic lights to create a comprehensive traffic management network. Simulations are conducted under diverse scenarios to evaluate the system's performance, with congestion levels assessed using metrics such as traffic flow rate, density, and Level of Service (LOS). Fixed timing plan methods serve as a baseline for comparison. Our approach demonstrates potential scalability for large urban areas and adaptability to various traffic patterns.