پژوهشنامه حمل و نقل

پژوهشنامه حمل و نقل

بهینه‌سازی هوشمندسازی انتخابی تقاطع‌های چراغ‌دار با هدف بهبود تاب‌آوری عملکردی شبکه معابر شهری با استفاده از الگوریتم ژنتیک و مدل جایگزین یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان
فاطمه سلمی پسیخانی 1
امین میرزا بروجردیان 2
سعید شرافتی پور 3
1 دانشجوی کارشناسی ارشد، دانشکده مهندسی عمران و محیط زیست، دانشگاه تربیت مدرس، تهران، ایران
2 دانشیار، دانشکده مهندسی عمران و محیط زیست، دانشگاه تربیت مدرس، تهران، ایران
3 استادیار، دانشکده مهندسی عمران و محیط زیست، دانشگاه تربیت مدرس، تهران، ایران
10.22034/tri.2026.595941.3499
چکیده
افزایش تقاضای سفر، پیچیدگی الگوهای ترافیکی و وقوع اختلالات پیش‌بینی‌نشده، تاب‌آوری شبکه‌های معابر شهری را به یکی از چالش‌های مهم مدیریت ترافیک تبدیل کرده است. تقاطع‌های چراغ‌دار به‌عنوان گره‌های کلیدی شبکه، نقش مهمی در ایجاد ازدحام، انتشار صف و کاهش عملکرد شبکه دارند. اگرچه هوشمندسازی کامل تقاطع‌ها می‌تواند عملکرد ترافیکی را بهبود دهد، اما به دلیل محدودیت‌های اجرایی، اقتصادی و فناورانه، همواره گزینه‌ای عملی و بهینه نیست. ازاین‌رو، هدف این پژوهش، تعیین ترکیب بهینه تقاطع‌های هوشمند با در نظر گرفتن هم‌زمان شاخص‌های عملکردی، زیست‌محیطی و هزینه اجرایی است.

در این پژوهش، یک چارچوب ترکیبی مبتنی بر شبیه‌سازی ترافیکی، الگوریتم ژنتیک و مدل جایگزین یادگیری ماشین ارائه شده است. شبکه مورد مطالعه شامل شش تقاطع چراغ‌دار است که در محیط SUMO شبیه‌سازی شد. وضعیت کنترلی هر تقاطع به‌صورت متغیر دودویی تعریف گردید؛ به‌طوری‌که مقدار یک نشان‌دهنده کنترل هوشمند و مقدار صفر نشان‌دهنده کنترل سنتی زمان‌ثابت است. تمامی 64 ترکیب ممکن شبیه‌سازی شده و تابع هدف چندمعیاره بر اساس زمان انتظار، اتلاف زمان، انتشار دی‌اکسیدکربن، مصرف سوخت و هزینه اجرایی تعریف شد. سپس، الگوریتم ژنتیک برای بهینه‌سازی ترکیب تقاطع‌ها و مدل Gradient Boosting به‌عنوان مدل جایگزین برای تخمین سریع شاخص تاب‌آوری به‌کار گرفته شد.

نتایج نشان داد که سناریوی تمام‌هوشمند بهترین عملکرد را از نظر شاخص‌های عملکردی و زیست‌محیطی دارد، اما به دلیل هزینه اجرایی بالا، لزوماً گزینه بهینه نیست. ترکیب کنترلی [1,1,0,0,1,1] به‌عنوان سناریوی بهینه شناسایی شد که با هوشمندسازی انتخابی تقاطع‌های کلیدی، عملکردی نزدیک به سناریوی تمام‌هوشمند و هزینه اجرایی کمتر ارائه می‌دهد. همچنین، مدل Gradient Boosting با مقادیر MAE=0.0248، RMSE=0.0462 و R²=0.927 توانست شاخص تاب‌آوری را با دقت مناسب تخمین زده و هزینه محاسباتی ارزیابی سناریوها را کاهش دهد. یافته‌ها نشان می‌دهد که استقرار هدفمند کنترل هوشمند می‌تواند جایگزینی کارآمد و هزینه‌اثربخش برای هوشمندسازی کامل شبکه و ابزاری مؤثر برای مدیریت تاب‌آوری شبکه‌های ترافیکی شهری باشد.
کلیدواژه‌ها
تاب‌آوری شبکه ترافیکی شهری
کنترل هوشمند تقاطع‌ها
استقرار انتخابی تقاطع‌های هوشمند
الگوریتم ژنتیک
مدل جایگزین یادگیری ماشین
موضوعات

عنوان مقاله English

Optimization of Selective Smartization of Signalized Intersections for Enhancing the Functional Resilience of Urban Road Networks Using a Genetic Algorithm and a Machine Learning Surrogate Model

نویسندگان English

Fatemeh Salmi Pasikhani 1
Amin Mirza Boroujerdian 2
Saeid Sherafatipour 3
1 M‌.Sc., Stud., Faculty of Civil and Environmental Engineering, Tarbiat Modares, University, Tehran, Iran
2 Associate Professor, Faculty of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran.
3 Assistant Professor, Faculty of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran.
چکیده English

Increasing travel demand, complex traffic patterns, and unpredictable disruptions have made urban road network resilience a critical issue in traffic management. Signalized intersections, as key network nodes, significantly influence congestion formation, queue propagation, and performance degradation. Although full-scale intelligent control can improve traffic operations, it is not always feasible or optimal due to economic, technological, and implementation constraints. This study aims to identify the optimal combination of intelligent intersections by considering operational performance, environmental impacts, and implementation costs simultaneously.

A hybrid framework integrating traffic simulation, a Genetic Algorithm (GA), and a machine learning surrogate model is proposed. The studied network consists of six signalized intersections modeled in the SUMO environment. Each intersection’s control strategy was represented as a binary variable, where one indicates intelligent control and zero represents conventional fixed-time control. All 64 possible combinations were simulated, and a multi-objective function was developed based on travel delay, time loss, carbon dioxide emissions, fuel consumption, and implementation cost. The GA was then employed to optimize the control configuration, while the Gradient Boosting model was used as a surrogate model to efficiently estimate the resilience index and reduce computational costs.

The results showed that the fully intelligent scenario achieved the best performance in terms of operational and environmental indicators; however, its higher implementation cost prevented it from being the optimal solution. The configuration [1,1,0,0,1,1] was identified as the optimal scenario, providing performance close to the fully intelligent strategy with lower implementation costs. Moreover, the Gradient Boosting model accurately estimated the resilience index, achieving MAE=0.0248, RMSE=0.0462, and R²=0.927, while reducing the computational burden of scenario evaluation. The findings highlight that targeted intelligent control deployment can provide a cost-effective alternative to full network automation and support resilience-oriented urban traffic management.

کلیدواژه‌ها English

Urban Traffic Network Resilience
Intelligent Signal Control
Selective Smart Intersection Deployment
Genetic Algorithm
Machine Learning Surrogate Model
-Adacher L, Tiriolo M, editors  (2016).A distributed approach for traffic signal synchronization problem. 2016 Third International Conference on Mathematics and Computers in Sciences and in Industry (MCSI), IEEE.
-Bhavathrathan B, Patil GR (2015). Quantifying resilience using a unique critical cost on road networks subject to recurring capacity disruptions. Transportmetrica A: Transport Science. 11(9):836-55.
-Bocchini P, Frangopol DM. (2012). Restoration of bridge networks after an earthquake: Multicriteria intervention optimization. Earthquake Spectra. 28(2):427-55.
-Boukerche A, Wang J. (2020). Machine learning-based traffic prediction models for intelligent transportation systems. Computer Networks. 181:107530.
-Chen C, Liu B, Wan S, Qiao P, Pei Q. (2020). An edge traffic flow detection scheme based on deep learning in an intelligent transportation system. IEEE Transactions on Intelligent Transportation Systems. 22(3):1840-52.
-De Oliveira LFP, Manera LT, Da Luz PDG. (2020). Development of a smart traffic light control system with real-time monitoring. IEEE Internet of Things Journal. 8(5):3384-93.
-Essa M, Sayed T. (2020). Self-learning adaptive traffic signal control for real-time safety optimization. Accident Analysis & Prevention. 146:105713.
-Faturechi R, Miller-Hooks E. (2014). Travel time resilience of roadway networks under disaster. Transportation Research Part B: Methodological. 70:47-64.
-Faye S, Chaudet C, Demeure I, editors. (2012). A distributed algorithm for multiple intersections adaptive traffic lights control using a wireless sensor networks. Proceedings of the First Workshop on Urban Networking.
-Garcia-Nieto J, Olivera AC, Alba E. (2013). Optimal cycle program of traffic lights with particle swarm optimization. IEEE Transactions on Evolutionary Computation. 17(6):823-39.
-Grandinetti P, Canudas-de-Wit C, garin F. (2018). Distributed optimal traffic lights design for large-scale urban networks. IEEE Transactions on Control Systems Technology. 27(3):950-63.
-Guerrero‐Ibañez J, Contreras‐Castillo J, Zeadally S. (2021). Deep learning support for intelligent transportation systems. Transactions on Emerging Telecommunications Technologies. 32(3):e4169.
-Hai DT, Manh DV, Nhat NM. (2022). Genetic algorithm application for optimizing traffic signal timing reflecting vehicle emission intensity. Transport Problems. 17.
-Haydari A, Yılmaz Y. (2020). Deep reinforcement learning for intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems. 23(1):11-32.
-Henry D, Ramirez-Marquez JE. (2012). Generic metrics and quantitative approaches for system resilience as a function of time. Reliability Engineering & System Safety. 99: 114-22.
-Holling CS. (1973). Resilience and stability of ecological systems. International Institute for Applied Systems Analysis Laxenburg.
-Hosseini S, Barker K, Ramirez-Marquez JE. (2016). A review of definitions and measures of system resilience. Reliability Engineering & System Safety. 145:47-61.
-Hu W, Wang H, Yan L, Du B. A swarm intelligent method for traffic light scheduling: application to real urban traffic networks. Applied Intelligence. 2016;44(1):208-31.
-Huang Y.S. (2006). Design of traffic light control systems using statecharts.The Computer Journal. 49(6):634-49.
-Huang Y.S. (2008). Chung T-H. Modeling and analysis of urban traffic lights control systems using timed CP-nets. Journal of Information Science & Engineering. 24(3).
-Huang Y.S. (2013). Weng Y-S, Zhou M. Modular design of urban traffic-light control systems based on synchronized timed Petri nets. IEEE Transactions on Intelligent Transportation Systems. 15(2):530-9.
-Ip WH, Wang D. (2011). Resilience and friability of transportation networks: Evaluation, analysis and optimization. IEEE Systems Journal. 5(2):189-98.
-Lee W.H., Tseng, S.S. Shieh W.Y. (2010). Collaborative real-time traffic information generation and sharing framework for the intelligent transportation system. Information Sciences. 180(1):62-70.
-Lee, J. Abdulhai B, Shalaby A. (2005). Chung E-H. Real-time optimization for adaptive traffic signal control using genetic algorithms. Journal of Intelligent Transportation Systems. 9(3):
111-22.
-Liu W.L. Zhong, J. Liang, P. Guo, J. Zhao, H. Zhang, J. (2024). Towards explainable traffic signal control for urban networks through genetic programming. Swarm and Evolutionary Computation. 88:101588.
-Mallik S. (2024). Intelligent transportation system. International Journal of Civil Engineering Research.
-Mao T. Mihăită A. S. Chen F. Vu, HL (2021). Boosted genetic algorithm using machine learning for traffic control optimization. IEEE Transactions on Intelligent Transportation Systems. 23(7):7112-41.
-Medvei MM, Bordei A-V, Niță ȘL, Țăpuș N. DeepSIGNAL-ITS, (2025). Deep Learning Signal Intelligence for Adaptive Traffic Signal Control in Intelligent Transportation Systems. Applied Sciences. 15(17):9396.
-Meena G, Sharma D, Mahrishi M, editors. )2020). Traffic prediction for intelligent transportation system using machine learning. 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE); IEEE.
-Murray-Tuite PM, editor (2006).
A comparison of transportation network resilience under simulated system optimum and user equilibrium conditions. Proceedings of The 2006 Winter Simulation Conference; IEEE.
-Nesmachnow S, Massobrio R, Arreche E, Mumford C, Olivera AC, Vidal PJ, et al. Traffic lights synchronization for Bus Rapid Transit using a parallel evolutionary algorithm. International Journal of Transportation Science and Technology. 2019;8(1):53-67.
-Popescu LG. (2015). The Development of A Model For The Traffic In A Urban Intersection. Fascicle of Management and Technological Engineering. 1:29-32.
- Sadoun B. (2003). An efficient simulation methodology for the design of traffic lights at intersections in urban areas. Simulation. 79(4):243-51.
-Qi L, Zhou M, Luan W. (2016). A two-level traffic light control strategy for preventing incident-based urban traffic congestion. IEEE Transactions on Intelligent Transportation Systems. 19(1):13-24.
-Qureshi KN, Abdullah AH. (2013). A survey on intelligent transportation systems. Middle-East Journal of Scientific Research. 15(5):629-42.
-Rodriguez M, Fathy HK. (2021). Distributed Kuramoto self-synchronization of vehicle speed trajectories in traffic networks. IEEE Transactions on Intelligent Transportation Systems. 23(7):6786-96.
-Shehu HA, Sharif MH, Ramadan RA. (2020). Distributed mutual exclusion algorithms for intersection traffic problems. IEEE Access. 8:138277-96.
-Teo KTK, Kow WY, Chin Y. editors (2010). Optimization of traffic flow within an urban traffic light intersection with genetic algorithm. 2010 Second International Conference on Computational Intelligence, Modelling and Simulation; IEEE.
-Tlig M, Buffet O. Simonin O. editors (2014). Decentralized traffic management:
A synchronization-based intersection control. 2014 International Conference on Advanced Logistics and Transport (ICALT); IEEE.
-Wang J. Wang H. Zhou Y. Wang Y. Zhang, W.J. (2019). On an integrated approach to resilient transportation systems in emergency situations. Natural Computing. 18(4):815-23.
-Wu W. Zhang J, Luo A. Cao J. (2014). Distributed mutual exclusion algorithms for intersection traffic control. IEEE Transactions on Parallel and Distributed Systems. 26(1):
65-74.
-Zhang H. Lu X. (2020). Vehicle communication network in intelligent transportation system based on Internet of Things. Computer Communications. 160:799-806.
-Zhang X. Fan X. Yu S. Shan A. Fan S. Xiao Y. et al. (2022). Intersection signal timing optimization: A multi-objective evolutionary algorithm. Sustainability. 14(3):1506.
-Zhang Z. Zhu H. Zhang W. Cai Z. Zhu L. Li Z. (2023). Multi-Objective Optimization of Traffic Signal Timing at Typical Junctions Based on Genetic Algorithms. Computer Systems Science & Engineering. 47(2).
-Zhou Y. Wang J. Yang H. (2019). Resilience of transportation systems: concepts and comprehensive review. IEEE Transactions on Intelligent Transportation Systems. 20(12):4262-76.
پژوهشنامه حمل و نقل
دوره 23، شماره 4
زمستان 1405
صفحه 465-478