بهینه‌سازی سیستم‌های حمل‌ونقل ریلی شهری: رویکردی یکپارچه برای ارتقای هم‌زمان بهره‌وری انرژی و زمان سفر در شرایط عدم قطعیت

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکدۀ مهندسی انرژی و منابع پایدار، دانشکدگان علوم و فناوری‌های میان‌رشته‌ای، دانشگاه تهران، تهران، ایران

2 استاد، دانشکدۀ مهندسی انرژی و منابع پایدار، دانشکدگان علوم و فناوری‌های میان‌رشته‌ای، دانشگاه تهران، تهران، ایران

10.22059/ses.2026.413703.1235

چکیده

سیستم‌های ریلی شهری با چالش مصرف بالای انرژی و عدم تطابق برنامه‌های ثابت با تغییرات لحظه‌ای تقاضا (به‌ویژه در شرایط متغیر جوی) مواجه‌اند. این پژوهش چارچوبی یکپارچه شامل مدل پیش‌بینی تقاضا و یک موتور بهینه‌سازی چندهدفه برای تدوین راهبردهای عملیاتی کم‌مصرف ارائه می‌دهد. مدل تقاضا بر رگرسیون جنگل تصادفی مبتنی است و با ترکیب الگوهای زمانی، داده‌های هواشناسی و آمار واقعی مسافران، سناریوهای واقع‌گرایانه تولید می‌کند. موتور بهینه‌سازی مبتنی بر الگوریتم تکامل تفاضلی نیز زمان‌بندی حرکت قطارها و پروفیل‌های سرعت را برای کاهش مصرف انرژی و حفظ کیفیت خدمت (یکنواختی فاصلۀ حرکت) تنظیم می‌کند. پیاده‌سازی این چارچوب در یک روز با شرایط نامساعد جوی نشان داد مصرف انرژی روزانه 46/11 درصد و انتشار  CO2به میزان 45/13 تُن کاهش یافت. هم‌زمان، میانگین زمان سفر مسافران 51/12 درصد کاهش یافت که بر چالش تقابل کارایی انرژی و سرعت خدمت غلبه می‌کند. تحلیل حساسیت نشان داد زمان (ساعت) و میزان بارش برف بیشترین تأثیر را بر بار مسافر دارند. این رویکرد سناریومحور به‌ طور هم‌زمان عملکرد زیست‌محیطی و کیفیت خدمت را بهبود می‌بخشد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Optimization of Urban Railway Transit Systems: An Integrated Approach for Simultaneous Enhancement of Energy Efficiency and Travel Time under Uncertainty

نویسندگان [English]

  • Hadi Alinia 1
  • Hossein Yousefi 2
  • Younes Noorollahi 2
1 School of Energy Engineering and Sustainable Resources, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran
2 Professor, School of Energy Engineering and Sustainable Resources, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran
چکیده [English]

Urban rail systems face the challenge of high energy consumption and the inability of fixed schedules to adapt to real-time demand changes (especially under variable weather conditions). This study presents an integrated framework comprising a demand prediction model and a multi-objective optimization engine to develop energy-efficient operational strategies. The demand model, based on Random Forest regression, generates realistic scenarios by combining temporal patterns, meteorological data, and real passenger statistics. The optimization engine, based on the Differential Evolution algorithm, adjusts train schedules and speed profiles to reduce energy consumption and maintain service quality (headway evenness). Implementing this framework on a day with severe weather conditions showed that daily energy consumption was reduced by 11.46%, and CO2​emissions decreased by 13.45 tons. Simultaneously, the average passenger travel time decreased by 12.51%, overcoming the trade-off between energy efficiency and service speed. Sensitivity analysis revealed that time (hour) and snowfall have the greatest impact on passenger load. This scenario-based approach simultaneously improves environmental performance and service quality.

کلیدواژه‌ها [English]

  • Urban railway transit
  • Energy consumption optimization
  • Passenger demand forecasting
  • Random forest
  • ‎Differential evolution algorithm

مراجع

[1]        X. Gao and X. Shi, "Analysis of the Abnormality of Traction Energy Consumption in Urban Rail Transit System," Mathematical Problems in Engineering, vol. 2023, no. 1, p. 1039287, 2023.
[2]        B. Qin et al., "Integrated Development of Urban Rail Transit and Energy Systems Supported by Underground Space," Strategic Study of Chinese Academy of Engineering, vol. 25, no. 1, pp. 45-59, 2023.
[3]        R. Xu, J. Meng, D. Li, and X. Chen, "Energy-Efficient Optimization Method of Urban Rail Train Based on Following Consistency," Energies, vol. 16, no. 4, p. 2050, 2023.
[4]        P. Sun, C. Zhang, B. Jin, Q. Wang, and H. Geng, "Timetable optimization for maximization of regenerative braking energy utilization in traction network of urban rail transit," Computers & Industrial Engineering, vol. 183, p. 109448, 2023/09/01/ 2023, doi: https://doi.org/10.1016/j.cie.2023.109448.
[5]        Y. Pang, J. Chen, and Y. Liu, "Energy Saving Optimization Scheme Design of Multi Train Cooperative Control in Urban Rail Transit," in International Conference of Artificial Intelligence, Medical Engineering, Education, 2022: Springer, pp. 277-291.
[6]        H. Geng and M. Miyatake, "Investigation and Optimisation of Urban Rail Transit Lifecycle Energy Saving in Coordinating Section Running Time and Slope," in 2023 IEEE International Conference on Electrical Systems for Aircraft, Railway, Ship Propulsion and Road Vehicles & International Transportation Electrification Conference (ESARS-ITEC), 2023: IEEE, pp. 1-6.
[7]        J. Ning, Y. Zhou, F. Long, and X. Tao, "A synergistic energy-efficient planning approach for urban rail transit operations," Energy, vol. 151, pp. 854-863, 2018/05/15/ 2018, doi: https://doi.org/10.1016/j.energy.2018.03.111.
[8]        J. Zhang, Y. Li, and H. Xie, "Evaluation of Energy Consumption Level of Urban Rail Train Operation Plans: A Case Study," in Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019, Singapore, B. Liu, L. Jia, Y. Qin, Z. Liu, L. Diao, and M. An, Eds., 2020// 2020: Springer Singapore, pp. 625-635.
[9]        C. Wu, B. Han, S. Lu, F. Xue, and F. Zhong, "Carbon-reducing Train Rescheduling Method for Urban Railway Systems considering the Grid with Wind Power Supply," in 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), 8-12 Oct. 2022 2022, pp. 164-169, doi: 10.1109/ITSC55140.2022.9922470.
[10]      W. Kampeerawat and T. Koseki, "Integrated design of smart train scheduling, use of onboard energy storage, and traction power management for energy-saving urban railway operation," IEEJ Journal of Industry Applications, vol. 8, no. 6, pp. 893-903, 2019, doi: https://doi.org/10.1541/ieejjia.8.893.
[11]      W. Kampeerawar, T. Koseki, and F. Zhou, "Efficient Urban Railway Design integrating Train Scheduling, Onboard Energy Storage, and Traction Power Management," in 2018 International Power Electronics Conference (IPEC-Niigata 2018 -ECCE Asia), 20-24 May 2018 2018, pp. 3257-3264, doi: 10.23919/IPEC.2018.8507499.
[12]      W. Kampeerawat and T. Koseki, "A strategy for utilization of regenerative energy in urban railway system by application of smart train scheduling and wayside energy storage system," Energy Procedia, vol. 138, pp. 795-800, 2017/10/01/ 2017, doi: https://doi.org/10.1016/j.egypro.2017.10.070.
[13]      W. Kampeerawat and T. Koseki, "Efficient urban railway design integrating train scheduling, wayside energy storage, and traction power management," IEEJ Journal of Industry Applications, vol. 8, no. 6, pp. 915-925, 2019.
[14]      D. Wang, J. Wu, Y. Wei, X. Chang, and H. Yin, "Energy-saving operation in urban rail transit: A deep reinforcement learning approach with speed optimization," Travel Behaviour and Society, vol. 36, p. 100796, 2024/07/01/ 2024, doi: https://doi.org/10.1016/j.tbs.2024.100796.
[15]      Z. Yang, F. Zhu, and F. Lin, "Deep-Reinforcement-Learning-Based Energy Management Strategy for Supercapacitor Energy Storage Systems in Urban Rail Transit," IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp. 1150-1160, 2021, doi: 10.1109/TITS.2019.2963785.
[16]      G. Yikwanga and P. Sun, "Optimizing the Urban Rail Transit System for Minimal Passenger Waiting Time and Reduced Traction Energy Consumption," in Future Directions in Energy Engineering: Challenges, Opportunities, and Sustainability, X. Wang Ed. Cham: Springer Nature Switzerland, 2024, pp. 79-87.
[17]      M. Zhang, "Parallel Calculation and Simulation of Urban Rail Transport Train Operation Based on GA," in 2023 International Conference on Power, Electrical Engineering, Electronics and Control (PEEEC), 25-27 Sept. 2023 2023, pp. 582-586, doi: 10.1109/PEEEC60561.2023.00119.
[18]      H. Li, J. Yin, T. Tang, A. D’Ariano, and M. You, "Energy-Efficient Operation of Train Platoons in Urban Rail Transit Systems: An MIP Approach," in 2024 43rd Chinese Control Conference (CCC), 28-31 July 2024 2024, pp. 6543-6549, doi: 10.23919/CCC63176.2024.10662116.
[19]      W. Zhou, Y. Huang, L. Deng, and J. Qin, "Collaborative optimization of energy-efficient train schedule and train circulation plan for urban rail," Energy, vol. 263, p. 125599, 2023/01/15/ 2023, doi: https://doi.org/10.1016/j.energy.2022.125599.
[20]      X. Yang, M. Wang, T. Q. Zheng, and X. Sun, "Modelling and Simulation of Stray Current in Urban Rail Transit—A Review," Urban Rail Transit, vol. 10, no. 3, pp. 189-199, 2024/09/01 2024, doi: 10.1007/s40864-024-00227-3.
[21]      H. Zhang, "Analysis of the Low‐Carbon, Environmental‐Friendly, Energy‐Saving, and Emission‐Reduction Evaluation Model of Urban Rail Transit Based on the Spatiotemporal Distribution of Passenger Flow," Scientific Programming, vol. 2022, no. 1, p. 8995448, 2022, doi: https://doi.org/10.1155/2022/8995448.
[22]      C. Jia, X. Wang, C. Qian, Z. Cao, L. Zhao, and L. Lin, "Quantitative Assessment of the Environmental Impact of Urban Rail Transits through Carbon Emission Reduction—A Case Study of Beijing Municipality," 2024.
[23]      Z. Han, E. Christofa, E. Gonzales, S. Donaghy, and J. Oke, "Long Short-Term Memory Energy Forecasting Framework for Sustainable Operations Planning in Urban Rail Transit Systems," Available at SSRN 4978818, doi: http://dx.doi.org/10.2139/ssrn.4978818.
[24]      L. Deng, L. Cai, G. Zhang, and S. Tang, "Energy consumption analysis of urban rail fast and slow train modes based on train running curve optimization," Energy Reports, vol. 11, pp. 412-422, 2024/06/01/ 2024, doi: https://doi.org/10.1016/j.egyr.2023.12.014.
[25]      F. Rowe, M. Mahony, and S. Tao, "Assessing Machine Learning Algorithms for Near-Real Time Bus Ridership Prediction During Extreme Weather," arXiv preprint arXiv:2204.09792, 2022.
[26]      P. Lin, J. Weng, D. K. Brands, H. Qian, and B. Yin, "Analysing the relationship between weather, built environment, and public transport ridership," IET Intelligent Transport Systems, vol. 14, no. 14, pp. 1946-1954, 2020/12/01 2020, doi: https://doi.org/10.1049/iet-its.2020.0469.
[27]      B. Li, S. Li, Z. Ye, S. Liu, Q. Zou, and X. Wang, "Exploring the Lagged Effect of Rainfall on Urban Rail Transit Passenger Flow: A Case Study of Guangzhou," Eng, vol. 7, no. 1, p. 47doi: 10.3390/eng7010047.
[28]      Y. Lai et al., "Short-term passenger flow prediction of urban rail transit integrating multiple features: A hybrid model with two-stage feature selection," Journal of Transportation Engineering, Part A: Systems, vol. 152, no. 6, p. 04026027, 2026.
[29]      Renewables.ninja. "Renewables.ninja." https://www.renewables.ninja (accessed.
[30]      L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5-32, 2001/10/01 2001, doi: 10.1023/A:1010933404324.
[31]      R. Storn and K. Price, "Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces," Journal of Global Optimization, vol. 11, no. 4, pp. 341-359, 1997/12/01 1997, doi: 10.1023/A:1008202821328.
فصلنامه سیستم های انرژی پایدار
دوره 5، شماره 3
تیر 1405
صفحه 429-446

فایل ها

هم رسانی

ارجاع به این مقاله

آمار