Xin Liu
ABSTRACT
In1 this paper, multi-objective optimization problem of train operation is discussed. The optimization model of train operation is established subject to security, stop position, passenger comfort level with energy consumption and running time regarded as the optimization indexes. Incorporated with leader selection strategy, basic cuckoo search algorithm is expanded to solve optimization problem with multiple objectives. On the basis of line information and management condition, the multiple objective cuckoo search algorithm is applied to calculate the train optimization model, and a set of balanced running control strategies is obtained after calculation. The simulation result shows that by applying the balanced strategy to train operation optimization problem, energy consumption is reduced by 10.1%-30.4% while guaranteeing running time is less than scheduled time, stop position and comfort level also achieve satisfied result. Then it's verified that improved algorithm can handle running situation with speed limit in section.
- Mao BH, and He TJ. 2000. A general-purposed simulation system on train movement. Journal of The China Railway Society, 22, 1--6.Google Scholar
- He HY, and Zhu JL. 2000. Design of Software for Traction Calculation and Operation Schematic Diagram of Trains. Journal of Southwest Jiaotong University, 22, 1--6.Google Scholar
- YU J, Zheng HY, and Qian QQ. 2010. Study on Multi-objective Train Control Based on Hybrid Particle Swarm Optimization. Journal of The China Railway Society, 32, 38--42.Google Scholar
- Tang T, and Xun J. 2016. Research on energy-efficient driving strategy in Beijing Yizhuang line. Journal of Beijing Jiaotong University, 40, 19--24.Google Scholar
- Lin C, Fang XQ, Zhao X, Zhang Q, and Liu X. 2017. Study on energy-saving optimization of train coasting control based on multi-population Genetic Algorithm. 2017 3rd International Conference on Control, Automation and Robotics(ICCAR), Nagoya, 627--632.Google Scholar
- Lu S, Yang J, Xue F, Ting TO, and Zhu H. 2017. Partial speed trajectory optimization for urban rail vehicles with considerations on motor efficiency. 2017 IEEE 20th International Conference on Intelligent Transportation Systems(ITSC), Yokohama, 1--6.Google Scholar
- YU J, Zheng HY, and Qian QQ. 2009. Study on Multi-objective Particle Swarm Optimization Algorithm Based on Preference. Control and Decision, 24, 66--70.Google Scholar
- Yang X S, and Deb S. 2010. Cuckoo Search via Levy Flights. Mathematics. 210--214.Google Scholar
- FU Q, GE HW, and SU SZ. 2016. Particle swarm optimization algorithm with firefly behavior and Levy flight. Journal of Computer Applications, 36, 3298--3302.Google Scholar
- Zitzler E, and Thiele L. 1999. Multi-objective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Transactions on Evolutionary Computation, 3, 257--271. Google ScholarDigital Library
Index Terms
- Optimization of Train Control Strategy for Energy Saving and Time Precision Using Multi-Objective Cuckoo Search Algorithm
Recommendations
Multi-objective optimization using BFO algorithm
ICIC'11: Proceedings of the 7th international conference on Intelligent Computing: bio-inspired computing and applicationsThis paper describes a novel bacterial foraging optimization (BFO) approach to multi-objective optimization, called Multi-objective Bacterial Foraging Optimization (MBFO). The search for Pareto optimal set of multi-objective optimization problems is ...
On-line Optimization of Energy-saving Train Control using Bacteria Foraging Algorithm
ICACS '18: Proceedings of the 2nd International Conference on Algorithms, Computing and SystemsReducing the energy consumption has been a significant issue in urban transit operations. Considering the prior constraint from the operational schedule, the online optimization of the speed curve between successive stations is capable of improving the ...
MOGOA algorithm for constrained and unconstrained multi-objective optimization problems
Grasshopper Optimization Algorithm (GOA) was modified in this paper, to optimize multi-objective problems, and the modified version is called Multi-Objective Grasshopper Optimization Algorithm (MOGOA). An external archive is integrated with the GOA for ...
Comments