Demand Forecasting and Allocation for High-speed Rail
 Express Network Development

doi:10.16097/j.cnki.1009-6744.2025.05.020

Abstract

Abstract: With the rapid development of China’s express delivery industry and the strategic integration of high-speed rail freight, accurately forecasting high-speed rail express transport demand and optimizing its spatial allocation have become critical. This study uses a comprehensive approach integrating network clustering, hybrid forecasting, and the gravity model for the demand forecast and allocation. Considering regional differences in economic and demographic indicators, this paper established a hierarchical high-speed rail express transport network through cluster analysis of 50 major cities. A self-adaptive weight allocation algorithm, evaluated using the root mean square error (RMSE) metric, is designed to integrate grey prediction, ARIMA, and multiple regression models for forecasting high-speed rail express transport volumes. To enhance prediction accuracy, spatial proximity is incorporated to adjust model weights. Furthermore, an improved Logit model is developed to quantify the market share of high-speed rail express across different transport distances. By comprehensively considering impedance factors such as Gross Domestic Product (GDP), total retail sales of consumer goods, and network distance, this paper develops a doubly constrained gravity model, incorporating a mixed-effects model to analyze the impact of regional economic heterogeneity on networked express volume. This approach enables the Origin-Destination (OD) express shipment matrix within the high-speed rail express transport network to better reflect real-world conditions, providing a reliable reference for high-speed rail express transport network planning.

Key words: railway transportation, OD allocation, hybrid prediction, transport network, regional heterogeneity

摘要： 随着中国快递业的快速发展和高铁货运的战略性整合，准确预测高铁快递运输需求并优化其空间分配已成为亟需解决的关键问题。本文综合运用网络聚类、混合预测和重力模型解决该问题。考虑经济和人口指标的地区差异，通过对50个主要城市的聚类分析，构建高铁快递分层运输网络，选用均方根误差作为评价指标设计自适应权重分配算法混合灰色预测、ARIMA(自回归积分滑动平均模型)和多元回归模型，对高铁快递网络化运量进行预测，为提高预测精度，根据空间邻近性对权重进行调整；设计改进的Logit模型量化不同运输距离高铁快运的市场份额，综合考虑GDP(国内生产总值)、社会消费品零售总额和网络距离等阻抗因素，建立双约束重力模型并引入混合效应模型，着重分析经济因素的区域异质性对网络化快递量的影响，使高铁快递运输网络下的OD(交通出行量)快递运量矩阵更贴合实际，为高铁快递运输网络规划提供可靠参考。

关键词: 铁路运输, OD分配, 混合预测, 运输网络, 区域异质性

CLC Number:

YANG Juhua, TANG Jia, TIAN Zhiqiang, SONG Qi. Demand Forecasting and Allocation for High-speed Rail Express Network Development[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 226-235.

杨菊花, 唐嘉, 田志强, 宋琦. 高铁快运网络化需求预测与分配[J]. 交通运输系统工程与信息, 2025, 25(5): 226-235.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/10.16097/j.cnki.1009-6744.2025.05.020

http://www.tseit.org.cn/EN/Y2025/V25/I5/226

References

[1] 王保华,何世伟.综合运输体系下快捷货物运输网络资源配置优化模型及算法[J].铁道学报,2017,39(2):10-16. [WANG B H, HE S W. Resource planning optimization model and algorithm for multi-modal express shipment network[J]. Journal of the China Railway Society, 2017,39(2):10-16.]

[2] 陈星瀚,周培宇,郎茂祥,等.需求变动下高铁快运货流分配与组织模式优化[J].交通运输系统工程与信息,2022,22(5):174-186. [CHEN X H, ZHOU P Y, LANG M X, et al. High-speed railway express cargo flow allocation and operation organization optimization under varying demand[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(5):174-186.]

[3] MINCKAI BI A, SHIWEI HE A, WANGTU ATO XU B. Express delivery with high-speed railway: Definitely feasible or just a publicity stunt[J]. Transportation Research Part A: Policy and Practice, 2019, 120:165-187.

[4] ZHEN L, GAO J, ZHANG N, et al. A decision model for high-speed railway express systems[J]. Computers & Industrial Engineering, 2023, 177:109087-109095.

[5] TANG S Y, DENG G M. Based on the theory of grey system to forecast China's business volume of express services[J]. Modern Economy, 2015, 6(2):283-288.

[6] 陈华友,盛昭瀚.一类基于IOWGA算子的组合预测新方法[J].管理工程学报,2005(4):39-42. [CHEN H Y, SHENG Z H. A new class of combinatorial forecasting methods based on IOWGA operators[J]. Journal of Industrial Engineering/Engineering Management, 2005 (4):39-42.]

[7] 周晓晔,成佳慧,戴思聪.基于Holt-Winters和PSO-SVR的快递业务量最优加权组合预测[J].数学的实践与认识,2023,53(7):51-60. [ZHOU X Y, CHENG J H, DAI S C. Optimal weighted combination prediction based on Holt-Winters and PSO-SVR express delivery volume[J]. Mathematics In Practice and Theory, 2023, 53 (7):51-60.]

[8] 许可,王孝坤.基于标准差法组合预测模型的区域快递需求量预测研究:以大连市为例[J].数学的实践与认识,2022,52(9):18-27. [XU K, WANG X K. A study on regional express demand forecasting based on the criterion difference method and the combination of forecasting models: A case study of Dalian city[J]. Mathematics In Practice and Theory, 2022, 52(9):18-27.]

[9] NAN Y, WEI X. Research on regional logistics demand forecast based on improved support vector machine: A case study of Qingdao city under the new free trade zone strategy[J]. Quality Control, Transactions, 2020, 8:9551-9564.

[10] HUANG W, YIN Y, LI H, et al. High-speed railway express delivery volume forecast based on data-driven ensemble forecast approaches: The China case[J]. Expert Systems with Application, 2024, 258(9):125196-125219.

[11] 白杰.铁路货运产品市场分担率的研究[J].铁道货运, 2018,36(2):10-14. [BAI J. A study of the market share of rail freight products[J]. Railway Freight Transport, 2018,36(2):10-14.]

[12] 周国华, 陈德捷,周芳汀,等.高速铁路与公路客运竞争的市场分担率模型研究[J].铁道学报,2020,42(1):1-8. [ZHOU G H, CHEN D J, ZHOU F T, et al. Research on market share rate models of passenger transport competition between high-speed rail and road[J]. Journal of the China Railway Society, 2020,42(1):1-8.]

[13] 张晓玲.基于Logit模型的高铁快递市场分担率预测研究[J].铁道运输与经济, 2018,40(12):93-97,116. [ZHANG X L. Study on the market share rate prediction of high-speed railway express based on Logit model[J]. Railway Transport and Economy, 2018,40(12):93-97,116.]

[14] 张发东,谢荣惠,张文畅,等.空铁联运背景下主要城市间快递量预测[J].物流技术, 2019,38(8):59-63. [ZHANG F D, XIE R H, ZHANG W C, et al. Forecast of express delivery volume between major cities in context of air-rail intermodal transport[J]. Logistics Technology, 2019,38(8):59-63.]

[1]	JING Yun, WANG Qi, WANG Siyuan, WU Mingze. Optimization of High-speed Rail Seat Allocation Considering Multi-dimensional Travel Demand of Passengers [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 193-204.
[2]	CHEN Xichun, YANG Yang, TIAN Xiaopeng. Collaborative Optimization of Train Timetabling and Stop Planning for Intercity and Suburban Railways in Cross-line Operations [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 241-253.
[3]	ZHU Qinyue, LI Jiyuan, LI Hongyi, QIAN Shuyang, ZHAO Yahui. Real-time Robust Optimization of Target Speed Profiles for Urban Rail Trains Considering Load Uncertainty [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 254-264.
[4]	LI Jiawei, TIAN Daxin, WU Sifan. A Stable Control Method for Virtual Coupling Trains with Asymmetric Variable Delay [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 265-274.
[5]	GAO Pengfei, ZHENG Wei, WANG Hongwei, LI Ye. Multi-layer Network Weighted Projection Approach to Identify Critical Track Sections in Railway Station [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 275-286.
[6]	ZHOU Wenliang, ZHU Huihong, GUANG Kexin, GUO Yiwei. Optimization of Train Timetables for High-speed Rail Based on Priority Sorting [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 287-296.
[7]	DU Jian, QIN Kexuan, LIN Shan, ZHANG Ran, LI Yang, YANG Zhongjie. Joint Optimization for Operation Plan and Train Diagram of China-Europe Railway Express Considering Assembly Mode [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(3): 61-72.
[8]	TIAN Zhiqiang, LIU Lei, SUN Guofeng, ZHANG Junfeng, LIANG Hui. Optimization of Train Operation Diagram Considering Maintenance Windows on Railway Lines with Long and Steep Gradients [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(3): 288-298.
[9]	SHUAI Bin, LIU Yijiang, XU Minhao, XIE Anhao, SUN Zongsheng, FA Huiyan. Method of Adding High-speed Express Trains to Existing Train Timetable [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(3): 276-287.
[10]	SU Huanyin, MO Shanglin, DAI Huizi. Quasi-dynamic Stochastic User Equilibrium Assignment Method for Urban Rail Transit [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 273-281.
[11]	GONG Shuaiyu, XU Xingfang, LU Yu. Optimization of Train Scheme for Provincial Railway Network [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 282-292.
[12]	FENG Fenling, FANG Yuan, ZHANG Ze, DONG Kaiyun. Resilience Assessment of China Railway Express Transport Network from Perspective of Risk Disturbances [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 338-351.
[13]	LIN Junting, LI Maolin, QIU Xiaohui. AJoint Optimization Method of Train Speed Curves and Dynamic Scheduling Under Delay Scenarios [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 173-187.
[14]	WU Gang, YANG Feng, JIANG Shan, GUO Qian. Optimal Subsidy Value for China Railway Express Based on Hotelling Model [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 289-297.
[15]	XU Minhao, XUE Kaizhao, SHUAI Bin, WANG Yu, YANG Qiaoli, ZUO Jing, ZHANG Yanpeng. Network Districting Plan Optimization for Comprehensive Inspection Trains [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 319-330.

Demand Forecasting and Allocation for High-speed Rail Express Network Development

高铁快运网络化需求预测与分配

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics