IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v17y2025i8p3383-d1632094.html
   My bibliography  Save this article

Dynamic Traffic Flow Optimization Using Reinforcement Learning and Predictive Analytics: A Sustainable Approach to Improving Urban Mobility in the City of Belgrade

Author

Listed:
  • Volodymyr N. Skoropad

    (Faculty of Business and Law, University Milija Babović—MB, 11000 Belgrade, Serbia)

  • Stevica Deđanski

    (Faculty for Social Sciences, University Business Academy, 21107 Novi Sad, Serbia)

  • Vladan Pantović

    (Faculty of Information Technology and Engineering, University Union–Nikola Tesla, 11158 Belgrade, Serbia)

  • Zoran Injac

    (Faculty for Traffic Engineering, Pan Apeiron University, 78102 Banja Luka, Bosnia and Herzegovina)

  • Slađana Vujičić

    (Faculty of Business Economics and Entrepreneurship, 11158 Belgrade, Serbia)

  • Marina Jovanović-Milenković

    (Project Management College, Educons University, 11158 Belgrade, Serbia)

  • Boris Jevtić

    (Computing Faculty (Racunarski Fakultet—RAF), University Union Belgrade, 11000 Belgrade, Serbia)

  • Violeta Lukić-Vujadinović

    (Department for Industrial Engineering, Faculty of Engineering Management and Economics, University Business Academy Novi Sad, 21000 Novi Sad, Serbia)

  • Dejan Vidojević

    (Department for Criminalistics, University of Criminal Investigation and Police Studies, 11158 Belgrade, Serbia)

  • Ištvan Bodolo

    (Department for Industrial Engineering, Faculty of Engineering Management and Economics, University Business Academy Novi Sad, 21000 Novi Sad, Serbia)

Abstract

Efficient traffic management in urban areas represents a key challenge for modern cities, particularly in the context of sustainable development and reducing negative environmental impacts. This paper explores the application of artificial intelligence (AI) in optimizing urban traffic through a combination of reinforcement learning (RL) and predictive analytics. The focus is on simulating the traffic network in Belgrade (Serbia, Europe), where RL algorithms, such as Deep Q-Learning and Proximal Policy Optimization, are used for dynamic traffic signal control. The model optimized traffic signal operations at intersections with high traffic volumes using real-time data from IoT sensors, computer vision-enabled cameras, third-party mobile usage data and connected vehicles. In addition, implemented predictive analytics leverage time series models (LSTM, ARIMA) and graph neural networks (GNNs) to anticipate traffic congestion and bottlenecks, enabling initiative-taking decision-making. Special attention is given to challenges such as data transmission delays, system scalability, and ethical implications, with proposed solutions including edge computing and distributed RL models. Results of the simulation demonstrate significant advantages of AI application in 370 traffic signal control devices installed in fixed timing systems and adaptive timing signal systems, including an average reduction in waiting times by 33%, resulting in a 16% decrease in greenhouse gas emissions and improved safety in intersections (measured by an average reduction in the number of traffic accidents). A limitation of this paper is that it does not offer a simulation of the system’s adaptability to temporary traffic surges during mass events or severe weather conditions. The key finding is that integrating AI into an urban traffic network that consists of fixed-timing traffic lights represents a sustainable approach to improving urban quality of life in large cities like Belgrade and achieving smart city objectives.

Suggested Citation

  • Volodymyr N. Skoropad & Stevica Deđanski & Vladan Pantović & Zoran Injac & Slađana Vujičić & Marina Jovanović-Milenković & Boris Jevtić & Violeta Lukić-Vujadinović & Dejan Vidojević & Ištvan Bodolo, 2025. "Dynamic Traffic Flow Optimization Using Reinforcement Learning and Predictive Analytics: A Sustainable Approach to Improving Urban Mobility in the City of Belgrade," Sustainability, MDPI, vol. 17(8), pages 1-31, April.
  • Handle: RePEc:gam:jsusta:v:17:y:2025:i:8:p:3383-:d:1632094
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/17/8/3383/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/17/8/3383/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Marina Jovanovic-Milenkovic & Filip Petrovic, 2023. "The Impact of Digitization on the Formation of a New Model for Geospatial Data," Sustainability, MDPI, vol. 15(22), pages 1-24, November.
    2. Rusul Abduljabbar & Hussein Dia & Sohani Liyanage & Saeed Asadi Bagloee, 2019. "Applications of Artificial Intelligence in Transport: An Overview," Sustainability, MDPI, vol. 11(1), pages 1-24, January.
    3. Jesús Vegas & César Llamas, 2024. "Opportunities and Challenges of Artificial Intelligence Applied to Identity and Access Management in Industrial Environments," Future Internet, MDPI, vol. 16(12), pages 1-20, December.
    4. Elżbieta Macioszek & Anna Granà & Paulo Fernandes & Margarida C. Coelho, 2022. "New Perspectives and Challenges in Traffic and Transportation Engineering Supporting Energy Saving in Smart Cities—A Multidisciplinary Approach to a Global Problem," Energies, MDPI, vol. 15(12), pages 1-8, June.
    5. Thiago Poleto & Thyago Celso Cavalcante Nepomuceno & Victor Diogho Heuer de Carvalho & Ligiane Cristina Braga de Oliveira Friaes & Rodrigo Cleiton Paiva de Oliveira & Ciro José Jardim Figueiredo, 2023. "Information Security Applications in Smart Cities: A Bibliometric Analysis of Emerging Research," Future Internet, MDPI, vol. 15(12), pages 1-36, December.
    6. Violeta Lukic Vujadinovic & Aleksandar Damnjanovic & Aleksandar Cakic & Dragan R. Petkovic & Marijana Prelevic & Vladan Pantovic & Mirjana Stojanovic & Dejan Vidojevic & Djordje Vranjes & Istvan Bodol, 2024. "AI-Driven Approach for Enhancing Sustainability in Urban Public Transportation," Sustainability, MDPI, vol. 16(17), pages 1-18, September.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tan Yigitcanlar & Kevin C. Desouza & Luke Butler & Farnoosh Roozkhosh, 2020. "Contributions and Risks of Artificial Intelligence (AI) in Building Smarter Cities: Insights from a Systematic Review of the Literature," Energies, MDPI, vol. 13(6), pages 1-38, March.
    2. Yuting Wang & Zhaocheng He & Wangyong Xing & Chengchuang Lin, 2025. "Understanding Congestion Risk and Emissions of Various Travel Behavior Patterns Based on License Plate Recognition Data," Sustainability, MDPI, vol. 17(2), pages 1-22, January.
    3. Ioana Popescu & Camelia Teau & Cristian Moisescu-Ciocan & Constantin Florescu & Relu Adam & Albert Titus Constantin, 2024. "Evaluating the Sustainability of Longtime Operating Infrastructure for Romanian Flood Risk Protection," Sustainability, MDPI, vol. 16(23), pages 1-19, December.
    4. Catarina N. S. Silva & Justas Dainys & Sean Simmons & Vincentas Vienožinskis & Asta Audzijonyte, 2022. "A Scalable Open-Source Framework for Machine Learning-Based Image Collection, Annotation and Classification: A Case Study for Automatic Fish Species Identification," Sustainability, MDPI, vol. 14(21), pages 1-13, November.
    5. Ghasri, Milad & Ardeshiri, Ali & Zhang, Xiang & Waller, S. Travis, 2024. "Analysing preferences for integrated micromobility and public transport systems: A hierarchical latent class approach considering taste heterogeneity and attribute non-attendance," Transportation Research Part A: Policy and Practice, Elsevier, vol. 181(C).
    6. Wu, Min & Wang, Nanxi & Yuen, Kum Fai, 2023. "Can autonomy level and anthropomorphic characteristics affect public acceptance and trust towards shared autonomous vehicles?," Technological Forecasting and Social Change, Elsevier, vol. 189(C).
    7. Mochen Liao & Kai Lan & Yuan Yao, 2022. "Sustainability implications of artificial intelligence in the chemical industry: A conceptual framework," Journal of Industrial Ecology, Yale University, vol. 26(1), pages 164-182, February.
    8. Milan Dedík & Martin Kendra & Matúš Senci & Daniel Pribula & Martin Vojtek, 2024. "Progressive Methods of the Harmfulness Evaluation of Transport in Terms of Emission Production," Sustainability, MDPI, vol. 16(23), pages 1-24, November.
    9. Muhammad Adeel & Biao Wang & Ji Ke & Israel Muaka Mvitu, 2024. "The Nonlinear Dynamics of CO 2 Emissions in Pakistan: A Comprehensive Analysis of Transportation, Electricity Consumption, and Foreign Direct Investment," Sustainability, MDPI, vol. 17(1), pages 1-26, December.
    10. Zulamir Hassani, Afdhal & Yusoff, Fazirah & Wan Zain, Wan Nor Aisyah, 2021. "Fair and Responsible in Logistics IR 4.0," MPRA Paper 108432, University Library of Munich, Germany.
    11. Marya Butt & Ander de Keijzer, 2022. "Using Transfer Learning to Train a Binary Classifier for Lorrca Ektacytometery Microscopic Images of Sickle Cells and Healthy Red Blood Cells," Data, MDPI, vol. 7(9), pages 1-21, September.
    12. Hang Nguyen Thi Bich & Thuc Le Dinh, 2024. "Overcoming Barriers to Sustainable Green Transportation in Ho Chi Minh City: A Pathway Toward Achieving SDGs 11 and 13," Sustainability, MDPI, vol. 16(23), pages 1-20, December.
    13. Bander Fahad Alkrides, 2025. "Promoting Sustainable Urban Walkability: A Modified Delphi Study on Key Indicators for Urban Walkability in Gulf Cooperation Council Urban Streets," Sustainability, MDPI, vol. 17(3), pages 1-34, February.
    14. Sohani Liyanage & Hussein Dia & Rusul Abduljabbar & Saeed Asadi Bagloee, 2019. "Flexible Mobility On-Demand: An Environmental Scan," Sustainability, MDPI, vol. 11(5), pages 1-39, February.
    15. Pamucar, Dragan & Deveci, Muhammet & Gokasar, Ilgin & Tavana, Madjid & Köppen, Mario, 2022. "A metaverse assessment model for sustainable transportation using ordinal priority approach and Aczel-Alsina norms," Technological Forecasting and Social Change, Elsevier, vol. 182(C).
    16. Jae-joon Chung & Hyun-Jung Kim, 2020. "An Automobile Environment Detection System Based on Deep Neural Network and its Implementation Using IoT-Enabled In-Vehicle Air Quality Sensors," Sustainability, MDPI, vol. 12(6), pages 1-17, March.
    17. Yeran Huang & Jian Gao & Lin Wang & Jierui Zhu & Wanjun Li, 2025. "A Framework of Life-Cycle Infrastructure Digitalization for Highway Asset Management," Sustainability, MDPI, vol. 17(3), pages 1-30, January.
    18. Sayeda Jahangir & Ruhe Xie & Amir Iqbal & Muttahir Hussain, 2025. "The Influence of Sustainable Human Resource Management Practices on Logistics Agility: The Mediating Role of Artificial Intelligence," Sustainability, MDPI, vol. 17(7), pages 1-25, March.
    19. Jin, Hui & Liu, Yue & Wu, Telan & Zhang, Yanpei, 2022. "Site-specific optimization of bus stop locations and designs over a corridor," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 599(C).
    20. Tahmineh Ladi & Shaghayegh Jabalameli & Ayyoob Sharifi, 2022. "Applications of machine learning and deep learning methods for climate change mitigation and adaptation," Environment and Planning B, , vol. 49(4), pages 1314-1330, May.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:17:y:2025:i:8:p:3383-:d:1632094. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.