Journal of Ubiquitous Computing and Communication Technologies
IRO Journals
Volume 7 — Issue 1 — March 2025

Optimized Traffic Routing System for Urban Congestion Management

https://doi.org/10.36548/jucct.2025.1.002
Rajkumar S.
Assistant Professor, Information Technology, Velammal Engineering College, Chennai, TamilNadu, India
Sandhiya S.
Information Technology, Velammal Engineering College, Chennai, TamilNadu, India
Manjusri A.
Information Technology, Velammal Engineering College, Chennai, TamilNadu, India
PDF
PDF

How to Cite

S., Rajkumar, Sandhiya S., and Manjusri A. 2025. “Optimized Traffic Routing System for Urban Congestion Management”. Journal of Ubiquitous Computing and Communication Technologies 7 (1): 19-35. https://doi.org/10.36548/jucct.2025.1.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Traffic Optimization
— Q-learning
— Genetic Algorithm
— Search-Based Techniques
— Traffic Simulation
— Reinforcement Learning
— Adaptive Traffic Control
Published: 10-03-2025

Abstract

Traffic congestion is a major challenge in modern urban areas, leading to increased travel time, fuel consumption, and environmental pollution. Traditional traffic control systems often rely on fixed signal timing, which lacks adaptability to dynamic traffic conditions. To overcome these limitations, the study proposes an Optimized Traffic Routing System for Urban Congestion Management that integrates multiple algorithms, including Fixed Cycle, Longest Queue First, Q-learning, and Search-Based Techniques which combines Genetic Algorithms and A Search where Genetic Algorithm optimizes traffic signal timing through evolutionary methods, while A search dynamically reroutes vehicles to minimize congestion by finding the shortest and least crowded paths. The approach utilizes reinforcement learning, heuristic optimization, and real-time simulations to dynamically optimize traffic signals and improve vehicle throughput while reducing the waiting time of vehicles. The approach was implemented using Python, and SUMO (Simulation of Urban Mobility), the system adapts to fluctuating traffic patterns and provides an efficient solution for urban traffic management.

References

  1. Tang, Keshuang, Manfred Boltze, Hideki Nakamura, and Zong Tian. Global practices on road traffic signal control: Fixed-time control at isolated intersections. Elsevier, 2019.
  2. Hassan, Muhammad Ahmed, Mourad Elhadef, and Muhammad Usman Ghani Khan. "Collaborative traffic signal automation using deep Q-learning." IEEE Access 11 (2023): 136015-136032.
  3. Zeng, Jinghong, Jianming Hu, and Yi Zhang. "Adaptive traffic signal control with deep recurrent Q-learning." In 2018 IEEE intelligent vehicles symposium (IV), IEEE, 2018. 1215-1220.
  4. Lee, Sangmin, Younghoon Kim, Hyungu Kahng, Soon-Kyo Lee, Seokhyun Chung, Taesu Cheong, Keeyong Shin, Jeehyuk Park, and Seoung Bum Kim. "Intelligent traffic control for autonomous vehicle systems based on machine learning." Expert Systems with Applications 144 (2020): 113074.
  5. Sandberg, Oscar. "Pathfinding Algorithm Comparison In Dynamic Congested Environment." (2024).
  6. Reza, Selim, Marta Campos Ferreira, J. J. M. Machado, and João Manuel RS Tavares. "A citywide TD‐learning based intelligent traffic signal control for autonomous vehicles: Performance evaluation using SUMO." Expert Systems 42, no. 1 (2025): e13301.
  7. Celtek, Seyit Alperen, Akif Durdu, and Muzamil Eltejani Mohammed Ali. "Evaluating action durations for adaptive traffic signal control based on deep Q-learning." International journal of intelligent transportation systems research 19, no. 3 (2021): 557-571.
  8. Shi, S., and F. Chen. "Deep recurrent Q-learning method for area traffic coordination control." Journal of Advances in Mathematics and Computer Science 27, no. 3 (2018): 1-11.
  9. Abu-Lebdeh, Ghassan, and Rahim F. Benekohal. "Genetic algorithms for traffic signal control and queue management of oversaturated two-way arterials." Transportation Research Record 1727, no. 1 (2000): 61-67.
  10. Tan, Tian, Feng Bao, Yue Deng, Alex Jin, Qionghai Dai, and Jie Wang. "Cooperative deep reinforcement learning for large-scale traffic grid signal control." IEEE transactions on cybernetics 50, no. 6 (2019): 2687-2700.
  11. Deepika, and Gitanjali Pandove. "Optimizing traffic flow with Q-learning and genetic algorithm for congestion control." Evolutionary Intelligence 17, no. 5 (2024): 4179-4197.
  12. .Abdoos, Monireh, Nasser Mozayani, and Ana LC Bazzan. "Hierarchical control of traffic signals using Q-learning with tile coding." Applied intelligence 40 (2014): 201-213.
  13. Benmessaoud, Youssef, Loubna Cherrat, and Mostafa Ezziyyani. "Real-time self-adaptive traffic management system for optimal vehicular navigation in modern cities." Computers 12, no. 4 (2023): 80.
  14. Wang, Zheng, Jinlong Liu, and Jingling Zhang. "Hyper-heuristic algorithm for traffic flow-based vehicle routing problem with simultaneous delivery and pickup." Journal of Computational Design and Engineering 10, no. 6 (2023): 2271-2287.
  15. Peeta, Srinivas, and T-H. Yang. "Stability issues for dynamic traffic assignment." Automatica 39, no. 1 (2003): 21-34.