Optimization of Train Regulation and Energy Usage of Metro Lines Using an Adaptive-Optimal-Control Algorithm

Automatic train regulation (ATR) dominates the service quality, transport capacity, and energy usage of a metro-line operation. The train regulator aims to maximize the schedule/headway adherence while minimizing the energy consumption. This paper presents a traffic-energy model to characterize the complicated dynamics with regard to the traffic and the energy consumption of a metro line, and devises an adaptive-optimal-control (AOC) algorithm to optimize the train regulator through reinforcement learning. The updating rules for reinforcement learning are deduced from the discrete minimum principle. Testing with field traffic data, the AOC algorithm succeeds in the optimization of the train regulator; no matter the system is disturbed by passenger-flow fluctuations or by frequently minor delays. The results also show that better train regulation with less energy consumption is attainable through the running-time and dwell-time controls.

[1]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[2]  Wei-Song Lin,et al.  Energy management of a fuel cell/ultracapacitor hybrid power system using an adaptive optimal-contro , 2011 .

[3]  Georges Bastin,et al.  Traffic modeling and state feedback control for metro lines , 1991 .

[4]  Clive Roberts,et al.  Optimal driving strategy for traction energy saving on DC suburban railways , 2007 .

[5]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Chung-Fu Chang,et al.  Optimising train movements through coast control using genetic algorithms , 1997 .

[7]  Donald A. Sofge,et al.  Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches , 1992 .

[8]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[9]  Felix Schmid,et al.  A review of methods to measure and calculate train resistances , 2000 .

[10]  C. J. Goodman,et al.  Metro traffic regulation from the passenger perspective , 2001 .

[11]  George Stephanopoulos,et al.  A Stronger Version of the Discrete Minimum Principle , 1974 .

[12]  M. Steiner,et al.  Energy storage system with ultracaps on board of railway vehicles , 2007, 2007 European Conference on Power Electronics and Applications.

[13]  Jaeho Choi,et al.  Line voltage regulation of urban transit systems using supercapacitors , 2009, 2009 IEEE 6th International Power Electronics and Motion Control Conference.

[14]  Bernard Widrow,et al.  Punish/Reward: Learning with a Critic in Adaptive Threshold Systems , 1973, IEEE Trans. Syst. Man Cybern..

[15]  Yu-Chi Chung,et al.  From timetabling to train regulation - a new train operation model , 2005, Inf. Softw. Technol..

[16]  Jennie Si,et al.  ADP: Goals, Opportunities and Principles , 2004 .

[17]  Warren B. Powell,et al.  GUIDANCE IN THE USE OF ADAPTIVE CRITICS FOR CONTROL , 2007 .

[18]  W-S Lin,et al.  Automatic train regulation for metro lines using dual heuristic dynamic programming , 2010 .

[19]  Benjamin C. Kuo,et al.  Digital Control Systems , 1977 .

[20]  M. Mendes,et al.  A methodology for generation of optimal schedules for an underground railway system , 1979, 1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[21]  Felix Schmid,et al.  Electric railway systems in common use , 2005 .

[22]  G. McFadden.  Sustainability and carbon reduction on electrified railways , 2009 .

[23]  Paul J. Werbos,et al.  Approximate dynamic programming for real-time control and neural modeling , 1992 .

[24]  Victor M. Becerra,et al.  Optimal control , 2008, Scholarpedia.

[25]  Tin Kin Ho,et al.  Coast control for mass rapid transit railways with searching methods , 2004 .

[26]  B Vitoriano,et al.  Predictive Traffic Regulation for Metro Loop Lines Based on Quadratic Programming , 2006 .

[27]  C. S. Chang,et al.  Online rescheduling of mass rapid transit systems: fuzzy expert system approach , 1996 .

[28]  Wei-Song Lin,et al.  Optimality and convergence of adaptive optimal control by reinforcement synthesis , 2011, Autom..