Short-Term Passenger Flow Prediction Method for Urban Rail Transit Considering Station Classification

doi:10.3778/j.issn.1002-8331.2306-0338

Abstract

Abstract: Accurate and reliable short-term forecasting of passenger flows can ensure the operation of urban rail transport. Considering the differences in the timing characteristics of passenger flows at different stations, a deep learning method for predicting passenger flows at urban stations is developed based on station classification. Firstly, stations are classified by dynamic time warping and the K-means algorithm, and the timing characteristics of the passenger flow of various stations are analyzed. Secondly, the complete ensemble empirical mode decomposition with adaptive noise is used to decompose passenger flow data of various stations to reduce the effects of data noise. Finally, a deep learning prediction method integrating long short-term memory and Transformer model is proposed to predict the passenger flow of different types of stations. The method is verified by using the passenger flow data of Xi’an Metro. The results show that the stations can be classified into four types according to the timing characteristics of passenger flow data on working days and non-working days: occupation-residential balance type, business office type, leisure and entertainment type, and dense residential type. Compared with the other three single models and three combined models, mean absolute error of passenger flow prediction results of the proposed method in different types of stations is reduced by 16.36%~51.02%, root mean square error is reduced by 10.35%~50.76%, and mean absolute percentage error is reduced by 14.71%~48.62%. Compared with the other six models, the prediction results of the station passenger flow data based on the statistics of different time intervals of 15 min, 30 min, 45 min and 60 min, the three indicators are respectively reduced by 12.63%~51.02%, 8.08%~49.12% and 6.83%~47.26%.

Key words: urban rail transit, short-term prediction, station classification, complete ensemble empirical mode decomposition with adaptive noise, long short-term memory network, Transformer

摘要： 精确、可靠的短时客流预测可为城市轨道交通运营提供保障。考虑不同站点的客流时序特征差异，在对站点分类的基础上，建立了一种城市轨道站点客流的深度学习预测方法。以动态时间规整及K-means算法对站点进行分类，分析各类站点的客流时序特征；采用自适应噪声完全集成经验模式分解算法对各类站点客流数据进行分解，以减少数据噪声的影响；提出一种融合长短期记忆网络和Transformer模型的深度学习预测方法，从而预测不同类型站点客流。应用西安市轨道交通客流数据验证该方法，结果表明：根据工作日及非工作日的客流数据时序特征可将站点分为职住均衡型、商务办公型、休闲娱乐型和密集居住型4类，所提出的方法在不同类型站点的客流预测结果相比于其他3种单一模型和3种组合模型，平均绝对误差降低16.36%~51.02%、均方根误差降低10.35%~50.76%，平均绝对百分比误差降低14.71%~48.62%，基于15 min、30 min、45 min及60 min不同时间间隔统计的站点客流数据的预测结果相比于其他6种模型，3种指标分别降低了12.63%~51.02%、8.08%~49.12%和6.83%~47.26%。

关键词: 城市轨道交通, 短时预测, 站点分类, 自适应噪声完全集成经验模式分解算法, 长短期记忆网络, Transformer

WANG Taizhou, XU Jinhua, CHEN Jianghui, LI Yan, REN Lu. Short-Term Passenger Flow Prediction Method for Urban Rail Transit Considering Station Classification[J]. Computer Engineering and Applications, 2024, 60(19): 343-353.

王泰州, 徐金华, 陈姜会, 李岩, 任璐. 考虑站点分类的城市轨道短时客流预测方法[J]. 计算机工程与应用, 2024, 60(19): 343-353.

References

[1] 张金雷, 陈奕洁, Panchamy Krishnakumari, 等. 基于注意力机制的城市轨道交通网络级多步短时客流时空综合预测模型[J]. 地球信息科学学报, 2023, 25(4): 698-713.
ZHANG J L, CHEN Y J, PANCHAMY K, et al. Attention-based multi-step short-term passenger flow spatial-temporal integrated prediction model in URT systems[J]. Journal of Geo-information Science, 2023, 25(4): 698-713.
[2] ZHANG Q, LIU X X, SPURGEON S, et al. A two-layer modelling framework for predicting passenger flow on trains: a case study of London underground trains[J]. Transportation Research, Part A: Policy and Practice, 2021, 151: 119-139.
[3] 张兴锐, 刘畅, 陈哲, 等. 基于时空图卷积网络的机场地铁短时客流预测[J]. 计算机工程与应用, 2023, 59(8): 322-330.
ZHANG X R, LIU C, CHEN Z, et al. Short-term passenger flow prediction of airport subway based on spatio-temporal graph convolutional Network[J]. Computer Engineering and Applications, 2023, 59(8): 322-330.
[4] 赵阳阳, 夏亮, 江欣国. 基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型[J]. 交通运输工程学报, 2020, 20(4): 194-204.
ZHAO Y Y, XIA L, JIANG X G. Short-term metro passenger flow prediction based on EMD-LSTM[J]. Journal of Traffic and Transportation Engineering, 2020, 20(4): 194-204.
[5] 蒋阳升, 俞高赏, 胡路, 等. 基于聚类站点客流公共特征的轨道交通车站精细分类[J]. 交通运输系统工程与信息, 2022, 22(4): 106-112.
JIANG Y S, YU G S, HU L, et al. Refined classification of urban rail transit stations based on clustered station's passenger traffic flow features[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(4): 106-112.
[6] 孙晓黎, 朱才华, 李美妮, 等. 时间序列聚类下的城市轨道交通客流预测研究[J]. 铁道运输与经济, 2023, 45(3):149-157.
SUN X L, ZHU C H, LI M N, et al. Research on passenger flow prediction of urban rail transit based on time sequence clustering[J]. Railway Transport and Economy, 2023, 45(3): 149-157.
[7] KURIHARA K, ISHIOKA F, KAJINISHI S. Spatial and temporal clustering based on the echelon scan technique and software analysis[J]. Japanese Journal of Statistics and Data Science, 2020, 3(1): 313-332.
[8] RUIZ L G B, PEGALAJAR M C, ARCUCCI R, et al. A time-series clustering methodology for knowledge extraction in energy consumption data[J]. Expert Systems with Applications, 2020, 160: 113731.
[9] 李海林, 张丽萍. 时间序列数据挖掘中的聚类研究综述[J]. 电子科技大学学报, 2022, 51(3): 416-424.
LI H L, ZHANG L P. Summary of clustering research in time series data mining[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(3): 416-424.
[10] 李正欣, 张凤鸣, 张晓丰, 等. 多元时间序列相似性搜索研究综述[J]. 控制与决策, 2017, 32(4): 577-583.
LI Z X, ZHANG F M, ZHANG X F, et al. Survey of similarity search for multivariate time series[J]. Control and Decision, 2017, 32(4): 577-583.
[11] 乔美英, 刘宇翔, 陶慧. 一种基于信息熵和DTW的多维时间序列相似性度量算法[J]. 中山大学学报(自然科学版), 2019, 58(2): 1-8.
QIAO M Y, LIU Y X, TAO H. A similarity metric algorithm for multivariate time series based on information entropy and DTW[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2019, 58(2): 1-8.
[12] 朱才华, 孙晓黎, 李培坤, 等. 融合车站分类和数据降噪的城市轨道交通短时客流预测[J]. 铁道科学与工程学报, 2022, 19(8): 2182-2192.
ZHU C H, SUN X L, LI P K, et al. Short-term urban rail transit passenger flow prediction based on incorporating station classification and data noise reduction[J]. Journal of Railway Science and Engineering, 2022, 19(8): 2182-2192.
[13] NI M, HE Q, GAO J. Forecasting the subway passenger flow under event occurrences with social media[J].IEEE Transactions on Intelligent Transportation Systems, 2016, 18(6): 1623-1632.
[14] 申雷霄, 陆宇航, 郭建华. 卡尔曼滤波短时交通流预测普通国省道适应性研究[J]. 交通信息与安全, 2021, 39(5):117-127.
SHEN L X, LU Y H, GUO J H. Adaptability of Kalman filter for short-time traffic flow forecasting on national and provincial highways[J]. Journal of Transport Information and Safety, 2021, 39(5): 117-127.
[15] 郇宁, 谢俏, 叶红霞, 等. 基于改进KNN算法的城轨进站客流实时预测[J]. 交通运输系统工程与信息, 2018, 18(5): 121-128.
HUAN N, XIE Q, YE H X, et al. Real-time forecasting of urban rail transit ridership at the station level based on improved KNN algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 121-128.
[16] 王盛, 杨信丰. 基于EEMD-GWO-LSSVM的公共交通短期客流预测[J]. 计算机工程与应用, 2019, 55(20): 216-221.
WANG S, YANG X F. Short-term passenger flow forecasting of public transport based on EEMD-GWO-LSSVM[J].Computer Engineering and Applications, 2019, 55(20): 216-221.
[17] 温惠英, 张东冉, 陆思园. GA-LSTM模型在高速公路交通流预测中的应用[J]. 哈尔滨工业大学学报, 2019, 51(9): 81-87.
WEN H Y, ZHANG D R, LU S Y. Application of GA-LSTM model in highway traffic flow prediction[J]. Journal of Harbin Institute of Technology, 2019, 51(9): 81-87.
[18] 刘晓磊, 段征宇, 余庆, 等. 基于图卷积循环神经网络的城市轨道客流预测[J]. 华南理工大学学报(自然科学版), 2022, 50(3): 21-27.
LIU X L, DUAN Z Y, YU Q, et al. Passenger flow forecast of urban rail transit based on graph convolution and recurrent neural network[J].Journal of South China University of Technology(Natural Science Edition), 2022, 50(3): 21-27.
[19] 唐继强, 杨璐琦, 杨武. 融合长短期记忆网络和图卷积网络的轨道交通短时客流起讫点预测[J]. 重庆大学学报, 2022, 45(11): 91-99.
TANG J Q, YANG L Q, YANG W. Urban rail transit short-term passenger flow origin-destination forecast based on LSTM and GCN[J]. Journal of Chongqing University, 2022, 45(11): 91-99.
[20] XU J H, LU W B, LI Y R, et al. A multi-directional recurrent graph convolutional network model for reconstructing traffic spatiotemporal diagram[J]. Transportation Letters, 2023: 1-11.
[21] 李文, 陈佳伟, 刘瑞雪, 等. 张量时间序列预测T-Transformer模型[J]. 计算机工程与应用, 2023, 59(11): 57-62.
LI W, CHEN J W, LIU R X, et al. T-Transformer model for predicting tensor time series[J]. Computer Engineering and Applications, 2023, 59(11): 57-62.
[22] 吴翊恺, 胡启洲, 吴啸宇. 车联网背景下的机动车辆轨迹预测模型[J]. 东南大学学报(自然科学版), 2022, 52(6): 1199-1208.
WU Y K, HU Q Z, WU X Y. Vehicle trajectory prediction model in the context of Internet of vehicles[J]. Journal of Southeast University(Natural Science Edition), 2022, 52(6): 1199-1208.
[23] 耿立艳, 鲁荣利, 李新杰. 基于波动聚集性的城际高铁客流量预测[J]. 铁道科学与工程学报, 2019, 16(8): 1890-1896.
GENG L Y, LU R L, LI X J. Predicting intercity high-speed railway passenger flow based on volatility clustering[J]. Journal of Railway Science and Engineering, 2019, 16(8): 1890-1896.
[24] 赵建东, 朱丹, 刘佳欣. 基于时间序列分解与门控循环单元的地铁换乘客流预测[J]. 华南理工大学学报(自然科学版), 2022, 50(5): 22-31.
ZHAO J D, ZHU D, LIU J X. Metro transfer passenger flow prediction based on STL-GRU[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(5): 22-31.
[25] LI Y P, MA C X. Short-time bus route passenger flow prediction based on a secondary decomposition integration method[J]. Journal of Transportation Engineering, Part A: Systems, 2023, 149(2): 04022132.
[26] TANG J J, GAO F, LIU F, et al. A denoising scheme-based traffic flow prediction model: combination of ensemble empirical mode decomposition and fuzzy C-Means neural network[J]. IEEE Access, 2020, 8: 11546-11559.
[27] 田秀娟, 于德新, 邢雪, 等. 交叉口短时流量CEEMDAN-PE-OSELM预测模型[J]. 哈尔滨工业大学学报, 2018, 50(3): 83-89.
TIAN X J, YU D X, XING X, et al. Prediction model of CEEMDAN-PE-OSELM for intersections short-term traffic flow[J]. Journal of Harbin Institute of Technology, 2018, 50(3): 83-89.