Adaptive and dynamic smart traffic light system for efficient management of regular and emergency vehicles at city intersection

• Published in: IET smart cities 2024-12, Vol.6 (4), p.387-421
• Main Authors: Zerroug, Rafik, Aliouat, Zibouda, Aliouat, Makhlouf, Alti, Adel
• Format: Article
• Language: English
• Subjects: smart cities; transport control
• ISSN: 2631-7680; 2631-7680
• DOI: 10.1049/smc2.12090

Smart Traffic Light Systems play an important role in urban traffic management. They often rely on cameras and sensors to collect traffic data. However, these methods are limited in terms of vehicle occupancy and queuing. Effective traffic management remains a challenge in urban areas owing to traffic congestion and emergencies. A new system called ADSTLS (Adaptive and Dynamic Smart Traffic Light System) is proposed, which handles traffic management at an intersection and effectively solves the cumbersome problem of traffic congestion while ensuring priority for emergency vehicles. ADSTLS provides fault tolerance to its components and works reliably in most failure situations. Therefore, traffic data is collected from cameras, and useful traffic information is extracted using computer vision and image processing. The proposed system also uses the Weight Chicken Swarm Optimisation algorithm for decision‐making to reduce congestion and average vehicle waiting time significantly. ADSTLS was applied to a real case study of EL‐Hidhab Setif city intersection. The approach's effectiveness was confirmed by thorough experiments, resulting in a noteworthy decrease in the average vehicle waiting time (31 s) and queue occupation rate (33.82%) across all simulated traffic scenarios. Furthermore, compared to other car types, emergency vehicles usually had much shorter wait times. The authors propose a new Adaptive and Dynamic Smart Traffic Light System that handles traffic management at an intersection and effectively solves the problem of traffic congestion while ensuring priority for emergency vehicles. Fault tolerance is supported in its components and works reliably in most failure situations. Therefore, traffic data is collected from cameras, and useful traffic information is extracted using computer vision and image processing. The proposed system uses the Weight Chicken Swarm Optimisation algorithm for decision‐making to reduce congestion and average vehicle waiting time.