Application research of passenger flow forecasting method for large railway station based on support vector regression
-
摘要: 准确预测大型客运站发送客流量,是铁路依据旅客出行需求制订开行方案、编制运行图和完成客流输送任务的重要基础。简要介绍支持向量回归的概念和原理;以汉口车站2017年1月—12月日实际发送客流量作为样本数据集,分析大型铁路客运车站客流特点,即年度客流呈现明显周期波动性、长周期内因多次节假日出现客流大幅激增;将样本数据集分为训练集及测试集,利用支持向量回归模型对剔除节假日前后的客流量进行预测,预测误差对比表明:排除节假日突发大客流的影响后,由支持向量回归模型计算得到车站日常发送客流量的预测精度可明显提高。Abstract: Accurate prediction of the number of passengers sent at large train stations is one of the main basis for the compilation of train operation plan and train timetables to complete the task of passenger trasportation based on passenger travel demand. Firstly, this paper gives a brief introduction to the theory and principle of support vector regression. Taking the actual daily passenger flow of Hankou Station from January to December in 2017 as the sample data set, the characteristics of passenger flow of the large railway station are analyzed. And the analysis shows that the annual passenger flow fluctuates in obvious cycles and the passenger flow spikes suddenly due to several holidays in a long period. The sample data set is then divided into one training set and one test set and the numbers of passengers daily sent at the station before and after the elimination of holidays are respectively predicted by using the support vector regression model and the comparison of the errors of the predication results indicates that the accuracy of the number of passengers sent at a station derived by using this model can be enhanced subtantially after eliminating the impact of sudden spikes of holidays' passenger flow.
-
-
表 1 排除节假日前后的汉口站发送客流量预测误差对比
误差指标 包含节假日 剔除节假日 RMSE 8099.46 2721.42 MAE 1918.38 880.31 R2 0.5295 0.8999 -
[1] 李丽辉,朱建生,强丽霞,等. 基于随机森林回归算法的高速铁路短期客流预测研究 [J]. 铁道运输与经济,2017,39(9):12-16. [2] 豆 飞,贾利民,秦 勇,等. 铁路客运专线模糊k近邻客流预测模型 [J]. 中南大学学报(自然科学版),2014(45):4422-4430. [3] 段 然,庞建华,张良钧. 基于SARIMA模型的铁路站点客流量预测研究 [J]. 数学的实践与认识,2019,49(9):1-10. [4] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016. [5] Zhang T. Statistical behavior and consistency of classification methods based on convex risk minimization [J]. Annals of Stats, 2004, 32(1): 56-84.
[6] Vapnik, V.N. Statistical learning theory[M]. New York: Scientific Research, 1998.
[7] Tikhonov A N. On the stability of inverse problems [J]. C. R. (Doklady) Acad. Sci. URSS (N. S.), 1943(39): 176-179.
[8] 贾俊平. 统计学[M]. 7版. 北京: 中国人民大学出版社, 2018. -
期刊类型引用(8)
1. 李永,孟歌,廖凤华,张军锋,周星. 铁路客运车站客流监测与预警系统. 铁路计算机应用. 2023(01): 68-73 . 本站查看
2. 王忻,李晔,张思韬,张凌云. 基于多层卷积长短期记忆神经网络的城轨路网短时客流预测研究. 现代城市轨道交通. 2023(09): 95-99 . 百度学术
3. 王平,吴文波,马毅华,许江,宗智诚. 后疫情时代基于XGBoost的铁路客运站客流量预测研究. 铁路计算机应用. 2022(01): 22-26 . 本站查看
4. 张涛. 基于铁路通勤用户需求的铁路新票制产品设计. 铁路计算机应用. 2022(01): 9-14 . 本站查看
5. 王金锋,孙连英,张天,涂帅. 基于K-LSTM-ecm模型的城市轨道交通短时客流预测. 制造业自动化. 2022(05): 103-107+133 . 百度学术
6. 曹满义,郑鹏,徐颖杰,刘栋梁. 基于长短时记忆网络的磨削在线预测与补调. 组合机床与自动化加工技术. 2022(06): 6-9 . 百度学术
7. 张亚伟,陈瑞凤,刘小燕. 基于门控循环神经网络的客运站客流预测. 铁道运输与经济. 2022(09): 96-102 . 百度学术
8. 唐杰. 西安地铁小寨站运营客流组织优化改造. 工程技术研究. 2021(11): 247-248 . 百度学术
其他类型引用(8)