By: Yamini N. Deshvena
Assistant Professor, Department of Civil Engineering, Shri Shivaji Institute of Engineering & Management Studies, Parbhani, Maharashtra, India
Abstract
Urban traffic congestion is one of the most pressing challenges in modern cities, leading to
substantial economic losses, environmental degradation, and reduced quality of life. Traditional
fixed-time traffic signal systems are often inadequate in addressing fluctuating traffic demands,
contributing significantly to this congestion. This paper explores the optimization of traffic signal
timing using a genetic algorithm (GA) integrated with real-time traffic data to improve urban
mobility. A case study was conducted at three highly congested intersections in downtown Vancouver,
Canada, focusing on reducing vehicle delays, fuel consumption, and emissions through dynamic
green time allocation based on traffic volumes. The study employed traffic simulation software
(VISSIM) to model and evaluate the proposed optimization strategy. Results indicate that the
optimized traffic signal system reduced vehicle delays by 25%, increased intersection throughput by
18%, and lowered fuel consumption and emissions by 12%. Additionally, these improvements
contribute to overall sustainability in urban transportation. While the study provides a strong case for
the effectiveness of adaptive signal control systems, scaling this optimization to larger urban areas
presents challenges, particularly in terms of infrastructure requirements and integration with
emerging technologies, such as autonomous and connected vehicles. This paper also discusses the
implications for future urban mobility solutions and emphasizes the importance of scalable, adaptable
traffic signal systems.
Keywords: Traffic signal optimization, urban mobility, genetic algorithm, adaptive traffic control,
green time allocation, VISSIM simulation, traffic congestion, sustainable transportation
Citation:
Refrences:
- Reno C Costa, Samara S Leal, Paulo EM Almeida and Eduardo G Carrano. Fixed-time traffic signal optimization using a multi-objective evolutionary algorithm and microsimulation of urban networks. Transactions of the Institute of Measurement and Control1–10ÓThe Author(s) 2016Reprints and permissions:sagepub.co.uk/journalsPermissions.navDOI: 10.1177/014
sagepub.com - Brown J, Patel R. Vehicle-actuated traffic signals: A review of current technologies. Journal of Transport Research. 2019;18(4):227–239.
- Chen D, Lee Y. Adaptive traffic signal control systems and their application in smart cities. Transportation Engineering and Systems. 2021;25(1):45–58.
- Gupta P, Sharma V, et al. Traffic signal optimization using genetic algorithms and machine learning approaches. International Journal of Transportation Systems. 2022;17(2):89–105.
- Jones A, Smith P, et al. Smart traffic management in mega cities: A case study of Singapore and New York. Global Transport Innovations. 2022;10(1):75–89.
- Zhang X, Zhang Y. Coordinated traffic signal control using genetic algorithms. IEEE Transactions on Intelligent Transportation Systems. 2020;21(3):1123–1134.
- Huang J, Zhou L, et al. A review of traffic signal optimization using heuristic algorithms. Applied Transportation Research. 2021;15(4):203–215.
- Miller S. Evolution of traffic signal control: From fixed-time systems to adaptive technologies. Journal of Traffic Engineering and Management. 2018;13(2):178–190.
- Torres G, Hernández R. The impact of genetic algorithm-based traffic signal optimization on fuel consumption. Mexican Journal of Transport Engineering. 2021;19(3):215–225.
- Wang Y, Liu H, et al. Adaptive traffic signal control in Beijing: A study of impact on traffic delays. International Journal of Urban Transport. 2019;14(2):95–104.
- Yuan X, Chen Y, et al. Machine learning approaches in traffic signal optimization: A comprehensive review. Transport Science and Technology. 2020;21(2):80–96.
- Kumar S, Singh T. Integration of autonomous vehicle technology with adaptive signal systems. Smart Transportation Innovations. 2023;9(1):65–78.
