Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

Design and Evaluation of a New Machine Learning Toolbox for Optimal Traffic Light Control with SUMO and Tensorflow

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2021
Reda Mali, Mohammed Bousmah

Reda Mali and Mohammed Bousmah. Design and Evaluation of a New Machine Learning Toolbox for Optimal Traffic Light Control with SUMO and Tensorflow. International Journal of Computer Applications 183(27):10-18, September 2021. BibTeX

	author = {Reda Mali and Mohammed Bousmah},
	title = {Design and Evaluation of a New Machine Learning Toolbox for Optimal Traffic Light Control with SUMO and Tensorflow},
	journal = {International Journal of Computer Applications},
	issue_date = {September 2021},
	volume = {183},
	number = {27},
	month = {Sep},
	year = {2021},
	issn = {0975-8887},
	pages = {10-18},
	numpages = {9},
	url = {},
	doi = {10.5120/ijca2021921653},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


Today, all the major metropolises of the world suffer from serious problems of congestion and saturation of road infrastructures. Within this context, one of the main challenges is the creation of appropriate Machine Learning algorithms for the optimization of the traffic lights systems. The objective is to minimize the total journey time of the vehicles that are present in a certain part of a city. In this article, we propose a new toolbox and a framework that brings Tensorflow features to Simulation of Urban Mobility (SUMO). Our work aims to facilitate the use of the SUMO simulator with Tensorflow, for road traffic management. With this tool, researchers will be able to easily test their different models quickly. Instead of spending several days studying the SUMO API, and setting up data mapping procedures, researchers will be able to get results in minutes with our tool. A Web generator let researchers set simulation scenarios, and they can implement their model with the toolbox, based on neural networks and Deep Q Learning. The toolbox exports many metrics, and can compare multiple policies, and different hyper parameters to optimize models. The experimental results obtained show that such an approach makes it possible to obtain significant gains.


  1. Lijun Wei, Heshan Du, Quratul-ain Mahesar, Kareem Al Ammari, Derek R. Magee, Barry Clarke, Vania Dimitrova, David Gunn, David Entwisle, Helen Reeves, Anthony G. Cohn,“A decision support system for urban infrastructure inter-asset management employing domain ontologies and qualitative uncertainty-based reasoning”, Expert Systems with Applications, Volume 158, 2020, 113461,ISSN0957-4174.
  2. Talha Oktay, Erdenay Yoğurtçuoğlu, Ramazan Nejdet Sarıkaya, Ali Recep Karaca, Mehmet Fırat Kömürcü, Ahmet Sayar,“Multimodel anomaly detection on spatio-temporal logistic datastream with open anomaly detection architecture “, Expert Systems with Applications,2021,115755,ISSN0957-4174,
  3. Jang Seung-Ju, “Design of Traffic Flow Simulation System to Minimize Intersection Waiting Time” International Journal of Advanced Computer Science and Applications(IJACSA), 9(5), 2018
  4. Qi Chen, Wei Wang, Kaizhu Huang, Suparna De, Frans Coenen, “Multi-modal generative adversarial networks for traffic event detection in smart cities”, Expert Systems with Applications, Volume 177, 2021,114939, ISSN0957-4174,
  5. Jafar Alzubi, Nayyar Anand, Kumar Akshi, “Machine Learning from Theory to Algorithms: An Overview,” 2018 J. Phys.: Conf. Ser. 1142 012012.
  6. Johanna Ylipulli, Aale Luusua, “Smart cities with a Nordic twist? Public sector digitalization in Finnish data-rich cities”, Telematics and Informatics,Volume 55, 2020,101457,ISSN0736-5853,
  7. Schmidhuber J., "Deep Learning in Neural Networks: An Overview". Neural Networks. 61: 85–117(2015). arXiv:1404.7828. doi:10.1016/j.neunet.2014.09.003. PMID 25462637. S2CID 11715509.
  8. Bengio Yoshua, LeCun, Yann, Hinton Geoffrey (2015). "Deep Learning". Nature. 521 (7553): 436–444. Bibcode:2015Natur.521..436L. doi:10.1038/nature14539. PMID 26017442. S2CID 3074096.
  9. Nosratabadi, S., Mosavi, A., Keivani, R., Ardabili, S., & Aram, F. “State of the art survey of deep learning and machine learning models for smart cities and urban sustainability”. In International Conference on Global Research and Education (pp. 228-238), 2019, September, Springer, Cham.
  10. Jie Xie, Kai Hu, Guofa Li, Ya Guo, “CNN-based driving maneuver classification using multi-sliding window fusion,” Expert Systems with Applications, Volume 169,2021,114442, ISSN 0957-4174,
  11. Liang, X.; Du, X.; Wang, G.; Han, Z. “A Deep Reinforcement Learning Network for Traffic Light Cycle Control.”, IEEE Trans. Veh. Technol.2019,68, 1243–1253.
  12. Shabestary, S.M.A.; Abdulhai, B. “Deep Learning vs. Discrete Reinforcement Learning for Adaptive TrafficSignal Control”. In Proceedings of the 2018 21st International Conference on Intelligent TransportationSystems (ITSC), Maui, HI, USA, 4–7 November 2018; pp. 286–293.
  13. Jianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang, “A Theoretical Analysis of Deep Q-Learning”, 2019
  14. Bouktif, Salah, Abderraouf Cheniki, and Ali Ouni. 2021. "Traffic Signal Control Using Hybrid Action Space Deep Reinforcement Learning" Sensors 21, no. 7: 2302.
  15. P. A. Lopez et al., "Microscopic Traffic Simulation using SUMO," 2018 21st International Conference on Intelligent Transportation Systems (ITSC), 2018, pp. 2575-2582 [H]
  16. Lucas Rivoirard, Martine Wahl, Patrick Sondi, Marion Berbineau, Dominique Gruyer. “Using Real-World Car Traffic Dataset in Vehicular Ad Hoc Network Performance Evaluation”. International journal of advanced computer science and applications (IJACSA), The Science and Information Organization,2016, 7 (12), p390-398.
  17. Van der Pol, E., & Oliehoek, F. A. “Coordinated deep reinforcement learners for traffic light control. Proceedings of Learning, Inference and Control of Multi-Agent Systems” (at NIPS 2016).
  18. Mannion, P., Duggan, J., & Howley, E. (2016). “An experimental review of reinforcement learning algorithms for adaptive traffic signal control”. Autonomic road transport support systems, 47-66
  19. Tilkov, S., & Vinoski, S. (2010). “Node. js: Using JavaScript to build high-performance network programs”. IEEE Internet Computing, 14(6), 8083.


Traffic Light Control; Machine Learning; Simulation Tool; Deep Q Learning.