Smart city Traffic Management using Edge Computing and AI Models

Smart city Traffic Management using Edge Computing and AI Models

Baran Rahmati1

1) Smart city Traffic Management using Edge Computing and AI Models

IOI Code : AAGF-AAGFKE
Publication : 9th International Conference on Applied Researches in Science & Engineering (carseconf.com/9th)
Abstract :
    Traffic congestion remains one of the major challenges in modern urban environments, significantly affecting mobility, safety, and sustainability. The emergence of Smart Cities (SCs) has created opportunities to integrate advanced technologies for intelligent traffic management. Traditional cloud-based approaches often suffer from high latency and bandwidth limitations, which restrict their efficiency in real-time decision-making. To overcome these issues, Edge Computing (EC) has been introduced, enabling data processing closer to the source through Internet of Things (IoT) devices and local edge nodes. Meanwhile, Artificial Intelligence (AI) models, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, provide powerful tools for traffic flow prediction, anomaly detection, and adaptive signal control. This paper proposes an integrated framework combining EC and AI to enhance traffic management in SCs. The framework leverages IoT sensors for real-time data acquisition, EC for low-latency processing, and AI models for predictive and prescriptive analytics. Simulation results demonstrate that the proposed approach reduces network latency, improves traffic flow accuracy, and supports scalable urban mobility solutions. The findings highlight the potential of EC-driven AI systems to serve as a backbone for future SC traffic management applications.

Keywords : smart city edge computing artificial intelligence internet of things traffic prediction intelligent transportation systems