In urban environments, traffic congestion leads to increased travel time, fuel consumption, and pollution. Traditional traffic signal control systems often struggle to adapt to dynamic traffic flows, resulting in inefficiencies. This study proposes innovative solutions for enhancing traffic signal control using decentralized, multi-agent systems inspired by swarm intelligence principles.
The first method, the split and offset control system, uses a spring model where each traffic light agent adjusts its signals based on real-time data from itself and neighboring agents. This method reduces waiting times and prevents jams by dynamically adapting to traffic conditions. The second method, the wide-area offset control system, facilitates a coordinated green wave by enabling neighboring agents to collaborate and synchronize their signals. This approach promotes continuous flow across extended areas, minimizing stop-and-go movements and improving traffic efficiency.
To address the challenge of sensor installation at every intersection, an Ant Colony Optimization (ACO) algorithm is introduced as a supplementary method. This algorithm estimates and predicts traffic patterns in environments with sparse sensor deployment, using swarm behavior principles to interpolate traffic data.
Simulations and real-world data analyses demonstrate that these decentralized control systems significantly improve traffic flow and reduce congestion. The findings suggest that integrating swarm intelligence into traffic signal control provides a robust, scalable solution to urban traffic management challenges.
Decentralized Multi-agent Traffic Light Control Using Swarm Intelligence for Improved Urban Traffic Flow
Communic.Comp.Inf.Science
International Conference on Science, Engineering Management and Information Technology ; 2024 ; Ankara, Türkiye September 12, 2024 - September 13, 2024
12.08.2025
17 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Swarm Intelligence Inspired Adaptive Traffic Control for Traffic Networks
Springer Verlag | 2018
|Semi-Decentralized Traffic-Responsive Urban Control
Springer Verlag | 2022
|