IoT-Enabled Adaptive Traffic Management: A Multiagent Framework for Urban Mobility Optimisation

Area of Science:

• Urban Planning & Transportation Engineering
• Computer Science & Artificial Intelligence
• Environmental Science

Background:

• Urban congestion and environmental impact are major challenges in densely populated cities.
• Conventional traffic management systems often rely on static or reactive strategies, proving insufficient for dynamic urban environments.

Purpose of the Study:

• To evaluate the effectiveness of IoT-enabled adaptive traffic management systems in mitigating urban congestion and environmental impact.
• To develop and assess advanced traffic management strategies using a multiagent simulation framework.

Main Methods:

• Developed a multiagent simulation framework integrating real-time IoT sensor data with predictive analytics.
• Modeled diverse traffic actors (vehicles, buses, cyclists, emergency services) as dynamic agents.
• Assessed adaptive signal control and dynamic rerouting strategies under various traffic scenarios.

Main Results:

• Achieved a 30% reduction in average travel times.
• Reduced congestion at major intersections by 50%.
• Decreased carbon dioxide (CO2) emissions by 28%.

Conclusions:

• IoT-enabled adaptive traffic management systems offer transformative potential for sustainable urban mobility.
• The proposed framework provides a realistic and scalable evaluation of smart city transportation strategies.
• Findings offer actionable insights for urban planning and transportation policy, emphasizing scalability, equity, and multimodal inclusivity.