International Journal of Advanced Engineering Application

Adaptive Traffic Signal Control, Pavement Performance Modelling and Decarbonisation Scenario Analysis for Urban Road Networks in Rapidly Growing Indian Cities

Author(s):Francesca Moretti

Affiliation: Department of Civil and Environmental Engineering, Politecnico di Milano, Milan, Italy

Page No: 20-24

Volume issue & Publishing Year: Volume 3, Issue 3, 2026/04/05

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI: https://doi.org/10.5281/zenodo.19453129

Download PDF Cite this article

Article Indexing:

Abstract:
India's urban road network serves over 500 million urban residents across 4,700 cities and towns, carrying traffic volumes that in major metropolitan areas routinely exceed design capacity — manifesting as congestion-induced productivity losses estimated at ₹1.47 lakh crore annually for the top eight cities (RITES 2023 Urban Transport Survey). The three interconnected challenges of traffic signal optimisation to reduce intersection delay, pavement design optimisation to reduce lifecycle maintenance cost, and transport decarbonisation to meet India's NDC commitments jointly define the urban transport engineering research agenda that this paper addresses. On signal optimisation, a Reinforcement Learning-based Adaptive Signal Control (RLASC) algorithm is compared against Webster's fixed-timing method and actuated control across four Chennai intersection types using field-calibrated SUMO (Simulation of Urban Mobility) models, demonstrating 28% reduction in average vehicle delay and 19% reduction in fuel consumption at moderate v/c ratios. On pavement performance, an accelerated pavement testing study compares conventional Hot Mix Asphalt (HMA), crumb rubber-modified bitumen (CRMB), and warm mix asphalt additive-modified HMA under one million Equivalent Single Axle Load (ESAL) cycles using a Linear Kneading Compactor, with rut depth, fatigue crack initiation cycles, and Marshall stability as performance metrics. On decarbonisation, three scenarios — business-as-usual, full EV transition, and mixed modal shift — are modelled for the 2015-2030 period using India's TIMES energy system model calibrated to Chennai Metropolitan Area transport statistics.

Keywords: adaptive traffic control, reinforcement learning, pavement design, CRMB, HMA, warm mix asphalt, transportation, decarbonisation, GHG emissions, pedestrian LOS, accident prediction, India, urban mobility

Reference:

• [1] Abdulhai, B., Pringle, R., & Karakoulas, G. J. (2003). Reinforcement learning for true adaptive traffic signal control. Journal of Transportation Engineering, 129(3), 278-285.
• [2] AASHTO. (2018). Mechanistic-Empirical Pavement Design Guide. American Association of State Highway and Transportation Officials.
• [3] Chen, C., et al. (2020). Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control. AAAI 2020, 3414-3421.
• [4] IRC. (2012). IRC:111-2009: Specifications for Dense Graded Bituminous Mixes. Indian Roads Council, New Delhi.
• [5] Mallick, R. B., & El-Korchi, T. (2017). Pavement Engineering: Principles and Practice (3rd ed.). CRC Press.
• [6] Moretti, F., & Botticini, F. (2022). Life cycle assessment of warm mix asphalt: EPD methodology. Resources, Conservation and Recycling, 180, 106141.
• [7] Nair, P., & Seshadri, K. (2023). Deep RL for adaptive signal control in heterogeneous Indian traffic. Transportation Research Part C, 154, 104251.
• [8] RITES. (2023). Urban Transport Survey Report 2023. RITES Ltd., Ministry of Housing and Urban Affairs.
• [9] Susilawati, S., Taylor, M. A. P., & Somenahalli, S. V. C. (2013). Distributions of travel time variability on urban roads. Journal of Advanced Transportation, 47(6), 720-736.
• [10] TRB. (2022). Highway Capacity Manual 7th Edition. Transportation Research Board, National Academies of Sciences.