Multi-timescale Optimization for Reversible Converter in DC Traction Power System Based on Model Predictive Control

Abstract

In urban rail flexible traction power supply system (FTPSS), conventional energy-saving strategies for reversible converter (RC) predominantly rely on offline optimization with fixed parameters. However, inherent uncertainties in train operations, such as timetable deviations and stochastic load fluctuations, result in energy consumption volatility, rendering traditional approaches suboptimal. To address this, we propose a multi-timescale model predictive control (MPC) framework that integrates day-ahead scheduling and intraday rolling optimization. Second, we propose a novel data processing method for neural network training in the intraday to construct a neural network-based load prediction model, which is used as the model prediction control (MPC) input for rolling optimization. Validated on Qingdao Metro Line 11 datasets, the prediction model achieves a correlation coefficient (R²) value of 95.2%, and the mean squared error (MSE) is 0.078, outperforming conventional prediction methods. By integrating MPC-based rolling optimization with day-ahead scheduling, the proposed strategy improves the energy-saving rate by 2.00% over traditional offline optimization methods. Demonstrating robustness against timetable perturbations and load uncertainties.

Keywords

Urban rail transit / Reversible converter / Deep learning / Model predictive control / Energy management

References

[1] Deng L, Chen M, Duan K, Li O, Shi F. Integrated energy-efficient optimization for urban rail transit timetable. IET Intell Transp Syst, 2023, 17(9): 1819-1834.

[2] Huang Y, Yang L, Tang T, Cao F, Gao Z. Saving energy and improving service quality: bicriteria train scheduling in urban rail transit systems. IEEE Trans Intell Transp Syst, 2016, 17(12): 3364-3379.

[3] Liu H, Zheng Z, Xu Z. Architecture of urban rail transit power supply based on PET braking energy feedback. J Eng, 2019, 2019(16): 2758-2763.

[4] Meishner F, Sauer DU. Wayside energy recovery systems in DC urban railway grids. eTransportation, 2019, 1: 100001.

[5] Khodaparastan M, Mohamed AA, Brandauer W. Recuperation of regenerative braking energy in electric rail transit systems. IEEE Trans Intell Transp Syst, 2019, 20(8): 2831-2847.

[6] Xu Q. et al.. Bi-level optimal design for DC traction power supply system with reversible substations. IEEE Trans Transp Electrif, 2024, 10(3): 7488-7500.

[7] Wang R, Zhang G, Gao M, Yu H, Qiu R. Parameter identification and load prediction of train models for power flow dynamic deduction in urban rail traction power supply systems. IEEE Trans Transp Electrif, 2024, 10(4): 8110-8121.

[8] Zhang J, Liu W, Tian Z, Zhang H, Zeng J, Qi H. Modelling, simulating, and parameter designing for traction power system with bidirectional converter devices. IET Gener Transm Distrib, 2022, 16(1): 110-122.

[9] Dan S. Comparative study on design schemes of bidirectional converters in subway power supply systems. Urban Rapid Rail Transit, 2022, 35(2): 6

[10] Wei L, Zeng J, Ma Q. Calculation of cooperative power flow of urban rail traction power supply system with bidirectional converter device. J Southwest Jiaotong Univ, 2023, 58(5): 1145-1153

[11] Zhang G, Tian Z, Tricoli P, Hillmansen S, Wang Y, Liu Z. Inverter operating characteristics optimization for DC traction power supply systems. IEEE Trans on Veh Technol, 2019, 68(4): 3400-3410.

[12] Sun P, Zhang C, Jin B, Wang Q, Geng H. Timetable optimization for maximization of regenerative braking energy utilization in traction network of urban rail transit. Computers Ind Eng, 2023, 183. 109448

[13] Zhang J, Liu W, Tian Z, Qi H, Zeng J, Yang Y. Urban rail substation parameter optimization by energy audit and modified salp swarm algorithm. IEEE Trans Power Del, 2022, 37(6): 4968-4978.

[14] Xu Q. et al.. System efficient energy regulation and control for reversible substations in urban rail system. IEEE Trans Transp Electrif, 2025, 11(2): 6916-6928.

[15] Yu H, Zhang G, Wang R, Xiong W. A real-time adaptive energy optimization method for urban rail flexible traction power supply system. IEEE Trans Intell Transp Syst, 2023, 24(9): 10155-10164.

[16] Yu H, Zhang G, Wang R, Yang J, Xiong W, Wei W. An online energy optimization method for urban rail flexible traction power supply system based on spatiotemporal matching of train power. IEEE Trans on Transp Electrific, 2024, 10(4): 8656-8670.

[17] Li Z, Li X, Wei Y, Lu C, Bai X. Fast quasi-optimal power flow of flexible DC traction power systems. IEEE Trans Power Syst, 2024, 39(1): 1555-1567.

[18] Yin J, Tang T, Yang L, Gao Z, Ran B. Energy-efficient metro train rescheduling with uncertain time-variant passenger demands: an approximate dynamic programming approach. Transp Res Part B: Methodol, 2016, 91: 178-210.

[19] Zhu L, Shen C, Wang X, Liang H, Wang H, Tang T. A learning based intelligent train regulation method with dynamic prediction for the metro passenger flow. IEEE Trans. Intell. Transp. Syst., 2023, 24(4): 3935-3948.

[20] Qin SJ, Badgwell TA. A survey of industrial model predictive control technology. Control Eng Pract, 2003, 11: 733-764.

[21] Aasi E, Cai M, Vasile C-I, Belta C. A two-level control algorithm for autonomous driving in urban environments. IEEE Trans Intell Transp Syst, 2025, 26(1): 410-424.

[22] Bian Y. et al.. Distributed model predictive control of connected and automated vehicles with Markov packet loss. IEEE Trans Transp Electrific, 2025, 11(no. 2): 6368-6379.

[23] Dong H, Tian Z, Liao K, Yang J, Spencer JW. Three-stage energy management of urban rail transit-based microgrid and EV charging station with V2T technology. IEEE Trans Transp Electrif, 2025, 15(4): 2500-2515

[24] Engel J, Schmitt T, Rodemann T, Adamy J. Hierarchical economic model predictive control approach for a building energy management system with scenario-driven EV charging. IEEE Trans Smart Grid, 2022, 13(4): 3082-3093.

[25] Liu B, Nowotarski J, Hong T, Weron R. Probabilistic load forecasting via quantile regression averaging on sister forecasts. IEEE Trans Smart Grid, 2017, 8(2): 730-737

[26] Tan D, Tang Z, Zhou F, Xie Y. A novel hybrid model based on EMD-improved TCN-improved TST for short-term railway traction load forecasting. IEEE Trans Transp Electrific, 2025, 11(2): 6418-6427.

[27] Alhussein M, Aurangzeb K, Haider SI. Hybrid CNN-LSTM model for short-term individual household load forecasting. IEEE Access, 2020, 8: 180544-180557.

[28] Zhou Y, Wang M. Empower pre-trained large language models for building-level load forecasting. IEEE Trans Power Syst, 2025.

[29] de Magalhães CL, Gonzalez-Fernandez RA, Da Silva AM, Da Rosa MA, Miranda V. Simplified cross-entropy based approach for generating capacity reliability assessment. IEEE Trans Power Syst, 2012, 28(2): 1609-16

[30] Wei X. et al.. Reduce the noise of transient electromagnetic signal based on the method of SMA-VMD-WTD. IEEE Sens J, 2022, 22(15): 14959-14969.

Funding

National Natural Science Foundation of China(52477125)

RIGHTS & PERMISSIONS

The Author(s)

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.