Research on Forecast of Passenger Flow of High Speed Railway in Competitive Market Based on XGBoost Model

Author(s):  
HAN Huiting ◽  
ZHANG Junfeng ◽  
MENG Ge ◽  
WANG Hongye ◽  
SHAN Xinghua
2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Zhengyu Xie ◽  
Limin Jia ◽  
Yong Qin ◽  
Li Wang

With the rapid development of high-speed railway in China, high-speed railway transport hub (HRTH) has become the high-density distribution center of passenger flow. In order to accurately detect potential safety hazard hidden in passenger flow, it is necessary to forecast the status of passenger flow. In this paper, we proposed a hybrid temporal-spatio forecasting approach to obtain the passenger flow status in HRTH. The approach combined temporal forecasting based on radial basis function neural network (RBF NN) and spatio forecasting based on spatial correlation degree. Computational experiments on actual passenger flow status from a specific bottleneck position and its correlation points in HRTH showed that the proposed approach is effective to forecast the passenger flow status with high precision.


Author(s):  
L. Nie ◽  
D. B. Fei ◽  
S. D. Zhou ◽  
H. L. Fu ◽  
L. Tong

The Beijing-Shanghai High speed railway line (Hereinafter referred to as “Jing-Hu HSL”) is one of the most important railway lines in the Chinese rapid passenger transportation network and will be put into operation at the end of 2011. Train line planning directly reflects the quality and competition ability of train services. The characteristics of operational conditions and passenger flow of this corridor HSL bring about a few new issues on train line planning like night train operation, train OD sets, cyclic operation, and train stop schedule. For the first issue, a large amount of long distance travel demand put forward the demand for night services, which causes great conflict with the time-window for maintenance work. The confliction can be solved by harmoniously utilizing the parallel lines. For the second one, in view of the differences of technical and economic factors between HSL and conventional railways, high frequency and medium-long distance train will dominate HSL’s train service plan rather than low frequency and long distance trains on conventional railways. Thus, part of long-distance passenger flow has to transfer at some stations. Considering the whole possible ODs over Jing-Hu HSL and the transfer condition of related stations, the optimal OD sets and corresponding transfer plan is suggested. High frequency makes HSL possible to operate trains cyclically to improve service quality. However, with too many train ODs and some special trains, e.g. night train, an incomplete cyclic train operation mode is more practical. The ODs which can provide cyclic service for Jing-Hu HSL need to be identified. For the last issue, although non-stop long-distance train is a very popular kind of service in China, it should be reconsidered for Jing-Hu HSL line because of massive intercity travel demand and regular stops required. Each of the above issues is very complex. What is more, they have close relationship between each other. Due to limited space, the methods used to solve these issues are given in conceptual way rather than detailed description of mathematical model. The research paves the way for future integration study to design an efficient, economic, convenient, and regular train service plan for Jing-Hu HSL.


2013 ◽  
Vol 409-410 ◽  
pp. 1071-1074
Author(s):  
Xiu Shan Jiang ◽  
Rui Feng Zhang ◽  
Liang Pan

Take Wuhan-Guangzhou high-speed railway for example. By adopting the empirical mode decomposition (EMD) attempt to analyze mode from the perspective of volatility of high speed railway passenger flow fluctuation signal. Constructed the ensemble empirical mode decomposition-gray support vector machine (EEMD-GSVM) short-term forecasting model which fuse the gray generation and support vector machine with the ensemble empirical mode decomposition (EEMD). Finally, by the accuracy of predicted results, explains the EEMD-GSVM model has the better adaptability.


2014 ◽  
Vol 505-506 ◽  
pp. 471-476
Author(s):  
Qing Jie Zheng ◽  
Bao Ming Han ◽  
Hua Li

Based on the relationship between passenger flow and demand of electric multiple units (EMU), a new methodology to calculate the EMU demand and allocate the EMU is proposed, which can meet the demand of passenger as well as avoid the waste of transport capacity. An offline allocation plan of EMU is designed by analyzing the fluctuation in passenger flow, passenger average haul distance, passenger load factor and so on. Using the methodology, the EMU allocation problem is solved through program, which is used in Beijing-Shanghai High-speed Railway to obtain the EMU allocation plan.


2012 ◽  
Vol 569 ◽  
pp. 246-250 ◽  
Author(s):  
Xue Dong Du ◽  
Na Ren

Under the regional economic conditions, a passenger flow prediction model is proposed in the paper. It can predict high-speed railway passenger flow volume under the conditions of multi-mode, and guide the reasonable operation of high-speed railway effectively. According to the data analysis of Beijing and Tianjin railway stations, we can know that the reasonable ticket price plays an important role in high-speed railway operation benefit under regional economic conditions.


2014 ◽  
Vol 505-506 ◽  
pp. 632-636 ◽  
Author(s):  
Peng Fei Zhou ◽  
Bao Ming Han ◽  
Qi Zhang

The development of high-speed railway has been very fast, while there are still existing many problems to be further studied and discussed, especially the design of high-speed railway Train stops program. The research of classification of high-speed passenger railway nodes has a vital significance for forecast of high-speed railway passenger flow, passenger train operation plan, evaluation and optimization and so on, especially for highspeed railway stopping schedule .This paper analyzes the significance and methods of high-speed passenger railway nodes classification, and designs high-speed rail train line stops program based on the classification. Finally, analyzing the case on the basis of Beijing-Guangzhou high-speed railway, a train stops program will be made bases on the classification of Beijing-Guangzhou high-speed railway passenger transport nodes to verify the feasibility of this study.


Sign in / Sign up

Export Citation Format

Share Document