Application of Firefly algorithm to train operation

Increasing demand for energy and environmental concerns have increased importance of energy-efficient transportation. In this manuscript, an energy-efficient train operation based on finding optimal speed profile is studied. As a nature-inspired metaheuristic approach, Firefly algorithm is employed to find optimal switching points of the train control signal. In problem formulation, energy consumption is taken as major part of objective function and travel time is being included as penalty factor. In order to verify the obtained results, a simulation is performed. Besides firefly algorithm, genetic algorithm is also used to compare results. Two algorithms are simulated on test track with various grade profiles for several times. Both of them considered four phases (maximum acceleration, cruising, coasting and braking) of train motion. Furthermore with the help of relaxing boundary conditions, algorithms are able to organize motion phases excluding cruising phase. Simulation results demonstrated that, compared to the GA, FA provides more accurate and persistent solutions. In addition, it can be converged to solution in small iterations, so it is compatible for using in real time problem solving.

[1]  Phil Howlett,et al.  Application of critical velocities to the minimisation of fuel consumption in the control of trains , 1992, Autom..

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

[3]  Zoran Miljkovic,et al.  Bio-inspired approach to learning robot motion trajectories and visual control commands , 2015, Expert Syst. Appl..

[4]  Krzysztof Tesch,et al.  Arterial cannula shape optimization by means of the rotational firefly algorithm , 2016 .

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

[6]  Phil Howlett,et al.  The Optimal Control of a Train , 2000, Ann. Oper. Res..

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

[8]  M. Meyer,et al.  An algorithm for the optimal control of the driving of trains , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[9]  J. Kwiecień,et al.  Firefly algorithm in optimization of queueing systems , 2012 .

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

[11]  K. Ichikawa.  Application of Optimization Theory for Bounded State Variable Problems to the Operation of Train , 1968 .

[12]  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..

[13]  Michael P. Polis,et al.  Reducing energy consumption through trajectory optimization for a metro network , 1975 .

[14]  Kemal Keskin,et al.  A hybrid optimization algorithm for energy efficient train operation , 2015, 2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA).

[15]  P. Howlett.  An optimal strategy for the control of a train , 1990, The Journal of the Australian Mathematical Society. Series B. Applied Mathematics.

[16]  Xin-She Yang,et al.  Firefly Algorithm, Lévy Flights and Global Optimization , 2010, SGAI Conf..

[17]  Stacy Cagle Davis,et al.  Transportation energy data book , 2008 .

[18]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

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

[20]  P. Howlett,et al.  A note on the calculation of optimal strategies for the minimization of fuel consumption in the control of trains , 1993, IEEE Trans. Autom. Control..