Real time eco-driving of high speed trains by simulation-based dynamic multi-objective optimization

Abstract Eco-driving is a traffic operation measure that may lead to important energy savings in high speed railway systems. Eco-driving optimization has been applied offline in the design of commercial services. However, the benefits of the efficient driving can also be applied on-line in the regulation stage to recover train delays or in general, to adapt the driving to the changing conditions in the line. In this paper the train regulation problem is stated as a dynamic multi-objective optimization model to take advantage in real time of accurate results provided by detailed train simulation. If the simulation model is realistic, the railway operator will be confident on the fulfillment of punctuality requirements. The aim of the optimization model is to find the Pareto front of the possible speed profiles and update it during the train travel. It continuously calculates a set of optimal speed profiles and, when necessary, one of them is used to substitute the nominal driving. The new speed profile is energy efficient under the changing conditions of the problem. The dynamic multi-objective optimization algorithms DNSGA-II and DMOPSO combined with a detailed simulation model are applied to solve this problem. The performance of the dynamic algorithms has been analyzed in a case study using real data from a Spanish high speed line. The results show that dynamic algorithms are faster tracking the Pareto front changes than their static versions. In addition, the chosen algorithms have been compared with the typical delay recovery strategy of drivers showing that DMOPSO provides 7.8% of energy savings.

[1]  Chun-Liang Lin,et al.  Optimisation of train energy-efficient operation for mass rapid transit systems , 2012 .

[2]  C. S. Chang,et al.  Differential evolution based tuning of fuzzy automatic train operation for mass rapid transit system , 2000 .

[3]  Hong Kam Lo,et al.  An energy-efficient scheduling and speed control approach for metro rail operations , 2014 .

[4]  Maximino Salazar Lechuga,et al.  Multi-objective optimisation using sharing in swarm optimisation algorithms , 2009 .

[5]  Tin Kin Ho,et al.  A review of simulation models for railway systems , 1998 .

[6]  Ting Xie,et al.  Optimization of Train Energy-Efficient Operation Using Simulated Annealing Algorithm , 2012 .

[7]  R. R. Pecharromán,et al.  Energy Savings in Metropolitan Railway Substations Through Regenerative Energy Recovery and Optimal Design of ATO Speed Profiles , 2012, IEEE Transactions on Automation Science and Engineering.

[8]  Antonio Fernández-Cardador,et al.  Optimal design of energy-efficient ATO CBTC driving for metro lines based on NSGA-II with fuzzy parameters , 2014, Eng. Appl. Artif. Intell..

[9]  Bin Xu,et al.  A Review Study on Traction Energy Saving of Rail Transport , 2013 .

[10]  Xuesong Feng,et al.  Evaluating target speeds of passenger trains in China for energy saving in the effect of different formation scales and traction capacities , 2012 .

[11]  Phil Howlett,et al.  Optimal strategies for the control of a train , 1996, Autom..

[12]  Xuesong Feng,et al.  Rational Formations of a Metro Train Improve Its Efficiencies of Both Traction Energy Utilization and Passenger Transport , 2013 .

[13]  Andrew M. Tobias,et al.  Reduction of train and net energy consumption using genetic algorithms for Trajectory Optimisation , 2010 .

[14]  Tae Won Park,et al.  Operating speed pattern optimization of railway vehicles with differential evolution algorithm , 2013 .

[15]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[16]  Moshe Givoni,et al.  Environmental Benefits from Mode Substitution: Comparison of the Environmental Impact from Aircraft and High-Speed Train Operations , 2007 .

[17]  Bernardo Almada-Lobo,et al.  Hybrid simulation-optimization methods: A taxonomy and discussion , 2014, Simul. Model. Pract. Theory.

[18]  B. Schutter,et al.  Optimal trajectory planning for trains – A pseudospectral method and a mixed integer linear programming approach , 2013 .

[19]  Hong Kam Lo,et al.  Energy minimization in dynamic train scheduling and control for metro rail operations , 2014 .

[20]  Tang Bing,et al.  Energy Saving Train Control for Urban Railway Train with Multi-population Genetic Algorithm , 2009, 2009 International Forum on Information Technology and Applications.

[21]  Li-Min Jia,et al.  Distributed intelligent railway traffic control: A fuzzy-decisionmaking-based approach , 1994 .

[22]  Antonio Fernández-Cardador,et al.  Real time regulation of efficient driving of high speed trains based on a genetic algorithm and a fuzzy model of manual driving , 2014, Eng. Appl. Artif. Intell..

[23]  Antonio Fernández-Cardador,et al.  Fuzzy train tracking algorithm for the energy efficient operation of CBTC equipped metro lines , 2016, Eng. Appl. Artif. Intell..

[24]  Hoay Beng Gooi,et al.  Increasing the Regenerative Braking Energy for Railway Vehicles , 2014, IEEE Transactions on Intelligent Transportation Systems.

[25]  Xiang Li,et al.  Optimizing trains movement on a railway network , 2012 .

[26]  Bart De Schutter,et al.  A survey on optimal trajectory planning for train operations , 2011, Proceedings of 2011 IEEE International Conference on Service Operations, Logistics and Informatics.

[27]  Xiao Ma,et al.  Optimization of Train Operation in Multiple Interstations with Multi-Population Genetic Algorithm , 2015 .

[28]  Regina Lamedica,et al.  Energy management in metro-transit systems: An innovative proposal toward an integrated and sustaina , 2011 .

[29]  Tao Tang,et al.  Efficient Real-Time Train Operation Algorithms With Uncertain Passenger Demands , 2016, IEEE Transactions on Intelligent Transportation Systems.

[30]  Erfan Hassannayebi,et al.  Variable and adaptive neighbourhood search algorithms for rail rapid transit timetabling problem , 2017, Comput. Oper. Res..

[31]  Mehmet Turan Soylemez,et al.  Coasting point optimisation for mass rail transit lines using artificial neural networks and genetic algorithms , 2008 .

[32]  Andries Petrus Engelbrecht,et al.  Population-based metaheuristics for continuous boundary-constrained dynamic multi-objective optimisation problems , 2014, Swarm Evol. Comput..

[33]  Phil Howlett,et al.  Energy-efficient train control , 1994 .

[34]  Antonio Fernández-Cardador,et al.  Fuzzy optimal schedule of high speed train operation to minimize energy consumption with uncertain delays and driver's behavioral response , 2012, Eng. Appl. Artif. Intell..

[35]  Piotr Lukaszewicz,et al.  Modeling and optimizing energy‐efficient manual driving on high‐speed lines , 2012 .

[36]  Carlos A. Coello Coello,et al.  Handling multiple objectives with particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[37]  Tad Gonsalves,et al.  Design of Robust and Energy-Efficient ATO Speed Profiles of Metropolitan Lines Considering Train Load Variations and Delays , 2015, IEEE Transactions on Intelligent Transportation Systems.

[38]  Maite Pena-Alcaraz,et al.  Optimal underground timetable design based on power flow for maximizing the use of regenerative-braking energy , 2012 .

[39]  Hee-Soo Hwang,et al.  Control strategy for optimal compromise between trip time and energy consumption in a high-speed railway , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[40]  Thomas Albrecht,et al.  Dealing with operational constraints in energy efficient driving , 2010 .

[41]  Hui Yang,et al.  Online Regulation of High Speed Train Trajectory Control Based on T-S Fuzzy Bilinear Model , 2016, IEEE Transactions on Intelligent Transportation Systems.

[42]  Jih-Wen Sheu,et al.  Automatic train regulation with energy saving using dual heuristic programming , 2011 .

[43]  Zhongsheng Hou,et al.  Adaptive Iterative Learning Control for High-Speed Trains With Unknown Speed Delays and Input Saturations , 2016, IEEE Transactions on Automation Science and Engineering.

[44]  Wei-Song Lin,et al.  Optimization of Train Regulation and Energy Usage of Metro Lines Using an Adaptive-Optimal-Control Algorithm , 2011, IEEE Transactions on Automation Science and Engineering.

[45]  Felix Schmid,et al.  An assessment of available measures to reduce traction energy use in railway networks , 2015 .

[46]  Tad Gonsalves,et al.  Multi objective particle swarm optimization algorithm for the design of efficient ATO speed profiles in metro lines , 2014, Eng. Appl. Artif. Intell..

[47]  Yi Liu,et al.  Ensuring a Reasonable Passenger Capacity Utilization Rate of a Train for Its Sustainably Efficient Transport , 2014 .

[48]  Ziyou Gao,et al.  An improved equation model for the train movement , 2007, Simul. Model. Pract. Theory.

[49]  Eugene Khmelnitsky,et al.  On an optimal control problem of train operation , 2000, IEEE Trans. Autom. Control..

[50]  Rongfang Rachel Liu,et al.  Energy-efficient operation of rail vehicles , 2003 .

[51]  Alexander Fay,et al.  A fuzzy knowledge-based system for railway traffic control , 2000 .

[52]  Wei-Song Lin,et al.  Energy-Saving Automatic Train Regulation Using Dual Heuristic Programming , 2012, IEEE Transactions on Vehicular Technology.

[53]  Phil Howlett,et al.  Coasting boards vs optimalcontrol , 2010 .

[54]  Kalyanmoy Deb,et al.  Dynamic Multi-objective Optimization and Decision-Making Using Modified NSGA-II: A Case Study on Hydro-thermal Power Scheduling , 2007, EMO.

[55]  Chang Han Bae.  A simulation study of installation locations and capacity of regenerative absorption inverters in DC 1500 V electric railways system , 2009, Simul. Model. Pract. Theory.

[56]  Limin Jia,et al.  A Fuzzy Optimization Model for High-Speed Railway Timetable Rescheduling , 2012 .

[57]  Clive Roberts,et al.  Single-Train Trajectory Optimization , 2013, IEEE Transactions on Intelligent Transportation Systems.

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

[59]  Fernando Jiménez,et al.  A Multi-Objective Evolutionary Approach for Fuzzy Optimization in Production Planning , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[60]  Felix Schmid,et al.  Standardised approach to energy consumption calculations for high-speed rail , 2016 .

[61]  Paola Pellegrini,et al.  Energy saving in railway timetabling: A bi-objective evolutionary approach for computing alternative running times , 2013 .

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

[63]  Chao-Shun Chen,et al.  Design of Optimal Coasting Speed for MRT Systems Using ANN Models , 2009 .

[64]  Prospero C. Naval,et al.  An effective use of crowding distance in multiobjective particle swarm optimization , 2005, GECCO '05.

[65]  Piotr Lukaszewicz,et al.  Optimal design of metro automatic train operation speed profiles for reducing energy consumption , 2011 .

[66]  Xiang Li,et al.  A Survey on Energy-Efficient Train Operation for Urban Rail Transit , 2016, IEEE Transactions on Intelligent Transportation Systems.

[67]  H. B. Quek,et al.  Pareto-optimal set based multiobjective tuning of fuzzy automatic train operation for mass transit system , 1999 .

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

[69]  Miguel A. Salido,et al.  Distributed search in railway scheduling problems , 2008, Eng. Appl. Artif. Intell..

[70]  Masafumi Miyatake,et al.  Optimization of Train Speed Profile for Minimum Energy Consumption , 2010 .

[71]  Martin Kozek,et al.  Simulation-based multi-objective system optimization of train traction systems , 2017, Simul. Model. Pract. Theory.