Using Genetic Algorithms to Optimize Stopping Patterns for Passenger Rail Transportation
Using Genetic Algorithms to Optimize Stopping Patterns for Passenger Rail Transportation
复制标题
DOI：
10.1111/mice.12020
复制
发表时间：
2014-04-01
影响因子：
9.6
通讯作者：
Ku, Yu-Hsiung
中科院分区：
文献类型：
--
作者：
Lin, Dung-Ying;Ku, Yu-Hsiung
在客运铁路系统中，停车模式优化问题确定列车停车策略，考虑多个列车类别，车站类型和客户的起讫点（OD）的需求，以最大限度地提高铁路公司的利润。传统上，停车模式是由经验法则决定的，这种方法有很大的改进空间。在这篇文章中，我们提出了一个整数规划这个问题，并提供了一个系统的方法来确定最佳列车停车模式的铁路公司。通常使用的商业优化软件包不能有效地解决这个复杂的问题，特别是当需要解决实际规模的问题时。因此，我们开发了两种遗传算法，即二进制编码的遗传算法（BGA）和整数编码的遗传算法（伊加）。在过去的许多进化规划研究中，染色体使用二进制字母表进行编码，如BGA。BGA的编码和遗传算子是直接的，并且相对容易实现。然而，我们发现，这是困难的BGA收敛到可行的解决方案的停止模式优化问题，由于复杂的解决方案空间。因此，我们提出了一种新的编码机制和遗传算子的伊加。数值结果表明，建议的伊加可以解决现实世界中的问题，是超出了常用的优化包。
In a passenger railroad system, the stopping pattern optimization problem determines the train stopping strategy, taking into consideration multiple train classes, station types, and customer origin-destination (OD) demand, to maximize the profit made by a rail company. The stopping pattern is traditionally decided by rule of thumb, an approach that leaves much room for improvement. In this article, we propose an integer program for this problem and provide a systematic approach to determining the optimal train stopping pattern for a rail company. Commonly used commercial optimization packages cannot solve this complex problem efficiently, especially when problems of realistic size need to be solved. Therefore, we develop two genetic algorithms, namely binary-coded genetic algorithm (BGA) and integer-coded genetic algorithm (IGA). In many of the past evolutionary programming studies, the chromosome was coded using the binary alphabet as BGA. The encoding and genetic operators of BGA are straightforward and relatively easy to implement. However, we show that it is difficult for the BGA to converge to feasible solutions for the stopping pattern optimization problem due to the complex solution space. Therefore, we propose an IGA with new encoding mechanism and genetic operators. Numerical results show that the proposed IGA can solve real-world problems that are beyond the reach of commonly used optimization packages.