Artificial Intelligence-Based Traffic Signal Optimization for Improving Urban Intersection Performance: A Case Study of Rohtak, Haryana

Author

Narender Kumar, Mr. Satish Kumar

Abstract

 Rapid urbanization and the continuous growth in vehicle ownership have significantly increased traffic congestion at signalized intersections, resulting in longer travel times, excessive fuel consumption, and higher environmental emissions. Conventional fixed-time traffic signal systems are often unable to accommodate fluctuating traffic demand, leading to inefficient traffic operations during peak periods. This study proposes an Artificial Intelligence (AI)-based traffic signal optimization framework to improve the operational performance of urban intersections in Rohtak, Haryana. Traffic data, including traffic volume, queue length, vehicle delay, average waiting time, and existing signal timings, were collected through field surveys at selected signalized intersections. The collected data were processed and integrated with a Reinforcement Learning-based optimization model developed using Python and evaluated through a microscopic traffic simulation environment. The performance of the proposed AI model was assessed by comparing it with the existing fixed-time traffic signal system using key traffic engineering indicators. The results demonstrated that the AI-based optimization model reduced the average signal cycle length from 120 seconds to approximately 100 seconds while improving green time allocation according to real-time traffic demand. The optimized model increased intersection capacity by approximately 15%, reduced queue length by about 35%, and decreased vehicle delay and average waiting time by nearly 38%. Furthermore, smoother traffic flow resulted in a 12% reduction in fuel consumption and a 14% reduction in carbon dioxide (CO₂) emissions. These findings indicate that AI-driven adaptive traffic signal control can substantially enhance urban traffic efficiency while supporting sustainable transportation objectives. The proposed framework provides a practical approach for transportation agencies to improve traffic management in medium-sized cities and may be extended to larger urban networks as part of future Intelligent Transport Systems and smart city initiatives.

Keywords

Artificial Intelligence, Traffic Signal Optimization, Urban Traffic Management, Intelligent Transport Systems, Reinforcement Learning, Rohtak, Sustainable Transportation

Full Text:

Download Paper PDF

References

1. Bishop, C. M. (2021). Pattern recognition and machine learning. Springer.
2. Federal Highway Administration. (2023). Traffic signal timing manual(2nd ed.). U.S. Department of Transportation.
3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
4. Indian Roads Congress. (2019). IRC:106-2019 Guidelines for capacity of urban roads in plain areas. Indian Roads Congress.
5. Institute of Transportation Engineers. (2022). Traffic engineering handbook(8th ed.). Wiley.
6. Li, L., Lv, Y., & Wang, F. Y. (2016). Traffic signal timing via deep reinforcement learning. IEEE/CAA Journal of Automatica Sinica, 3(3), 247–254.
7. Lopez, P. A., Behrisch, M., Bieker-Walz, L., Erdmann, J., Flötteröd, Y., Hilbrich, R., ... & Wießner, E. (2018). Microscopic traffic simulation using SUMO. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC)(pp. 2575–2582). IEEE.
8. Noaeen, M., Naik, A., Goodman, L., Abrar, T., Boukerche, A., & Pei, Y. (2022). Reinforcement learning in urban network traffic signal control: A survey. ACM Computing Surveys, 55(10), 1–35.
9. Russell, S., & Norvig, P. (2021). Artificial intelligence: A modern approach(4th ed.). Pearson.
10. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction(2nd ed.). MIT Press.
11. Transportation Research Board. (2020). Highway capacity manual(7th ed.). National Academies Press.
12. Wang, X., Li, Y., & Chen, Z. (2023). Neural network-based adaptive traffic signal optimization for urban intersections. IEEE Transactions on Intelligent Transportation Systems, 24(6), 5621–5635.
13. Wei, H., Zheng, G., Yao, H., & Li, Z. (2019). IntelliLight: A reinforcement learning approach for intelligent traffic light control. In Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining(pp. 2496–2505).
14. Yau, K. L. A., Qadir, J., Khoo, H. L., Ling, M. H., & Komisarczuk, P. (2017). A survey on reinforcement learning models and algorithms for traffic signal control. ACM Computing Surveys, 50(3), 1–38.
15. Zhang, Y., Wang, X., Li, L., & Wang, S. (2021). Deep learning for intelligent traffic management: A review. IEEE Transactions on Intelligent Transportation Systems, 22(10), 6136–6155.
16. Zheng, G., Xu, K., Liu, H., & Li, Z. (2022). Multi-agent reinforcement learning for coordinated traffic signal control in urban road networks. IEEE Transactions on Intelligent Transportation Systems, 23(9), 15672–15686.
17. Zhou, X., Taylor, J., & Wang, Y. (2021). Artificial intelligence applications in urban transportation management: A systematic review. Sustainable Cities and Society, 72, 103042.