基于系统关联性的高速公路大中型货车到达量多尺度预测

doi:10.16088/j.issn.1001-6600.2021020301

摘要/Abstract

摘要： 近年来,交通流中大中型货车流量占比逐渐增大,对城市交通的影响日愈增加,准确、及时的大中型货车到达量预测对精确的城市交通管控具有重要意义。针对该问题,本文提出了考虑系统关联性的高速公路大中型货车到达量多尺度预测方法:考虑高速公路网的系统关联性,对高速公路收费站进、出口大中型货车流量的时空关联性进行分析,构建神经网络模型学习空间权重与时间权重;每一时间步将输入与空间权重、时间权重融合,并设置偏置项修正后得到该时间步预测结果;各时间步预测结果对应求和得到最终预测结果。实验结果表明:所用方法在15、30、60 min的时间尺度下预测精度分别达到90.92%、92.48%、94.33%,优于其他对比模型,实用性和有效性均得到了保证。

关键词: 交通流预测, 系统关联性, 神经网络, 高速公路, 大中型货车流量

Abstract: In recent years, the proportion of large and medium-sized trucks in the traffic flow has gradually increased, and the impact on urban traffic is increasing day by day. Accurate and timely prediction of the arrival of large and medium-sized trucks is of great significance to accurate urban traffic control. To solve this problem, a multi-scale prediction method for the arrival volume of large and medium-sized trucks on expressway based on the system correlation is proposed: the spatio-temporal correlation of the flow of large and medium-sized trucks at the entrance and exit of expressway toll stations is analyzed, and a neural network model is constructed to learn the spatial weight and time weight. In each step of time, the input is fused with spatial weight and time weight, and the offset term is set to obtain the prediction result of the time step after correction.The final prediction result is obtained by summing the prediction results of each step of time. The experimental results show that the prediction accuracy of the method is 90.92%, 92.48% and 94.33% respectively at the time scales of 15, 30 and 60 mins, which is better than other models, and the practicability and effectiveness are guaranteed.

Key words: traffic flow prediction, system relevance, neural networks, expressways, large and medium-sized trucks volume

中图分类号:

U491

林培群, 何伙华, 林旭坤. 基于系统关联性的高速公路大中型货车到达量多尺度预测[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 15-26.

LIN Peiqun, HE Huohua, LIN Xukun. Multi-scale Prediction of Expressways' Arrival Volume of Large and Medium-sized Trucks Based on System Relevance[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(2): 15-26.

参考文献

[1] 美国交通研究委员会. 道路通行能力手册[M]. 任福田, 刘小明, 荣建, 等译. 北京: 人民交通出版社, 2007: 56-150.
[2] 刘欣, 王洪涛, 林洋. 交通量预测研究方法评述[J]. 吉林建筑工程学院学报, 2009, 26(4): 35-38. DOI: 10.3969/j.issn.1009-0185.2009.04.010.
[3] 唐秋生,王川. 基于云遗传算法优化BP神经网络的轨道客流预测[J]. 桂林理工大学学报,2021,41(2):403-408.
[4] 刘铭, 鱼昕. 基于改进LSTM算法的短时交通流量预测[J]. 桂林理工大学学报, 2021, 41(2):409-414.
[5] 林培群, 陈丽甜, 雷永巍. 基于K近邻模式匹配的地铁客流量短时预测[J]. 华南理工大学学报(自然科学版), 2018, 46(1): 50-57. DOI: 103969/jissn1000-565X201801007.
[6] ZHENG Z D, SU D C. Short-term traffic volume forecasting: A k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm[J]. Transportation Research Part C: Emerging Technologies, 2014, 43(Part 1): 143-157. DOI: 10.1016/j.trc.2014.02.009.
[7] CHENG S F, LU F, PENG P, et al. Short-term traffic forecasting: An adaptive ST-KNN model that considers spatial heterogeneity[J]. Computers, Environment and Urban Systems, 2018, 71: 186-198. DOI: 10.1016/j.compenvurbsys.2018.05.009.
[8] HABTEMICHAEL F G, CETIN M. Short-term traffic flow rate forecasting based on identifying similar traffic patterns[J]. Transportation Research Part C: Emerging Technologies, 2016, 66: 61-78. DOI: 10.1016/j.trc.2015.08.017.
[9] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results[J]. Journal of Transportation Engineering, 2003, 129(6):664-672. DOI: 10.1061/(ASCE)0733-947X(2003)129: 6(664).
[10] VAN DER VOORT M, DOUGHERTY M, WATSON S. Combining Kohonen maps with ARIMA time series models to forecast traffic flow[J]. Transportation Research Part C: Emerging Technologies, 1996, 4(5): 307-318. DOI: 10.1016/S0968-090X(97)82903-8.
[11] SMITH B L, WILLIAMS B M, OSWALD R K. Comparison of parametric and nonparametric models for traffic flow forecasting[J]. Transportation Research Part C: Emerging Technologies, 2002, 10(4): 303-321. DOI: 10.1016/S0968-090X(02)00009-8.
[12] JEONG Y S, BYON Y J, CASTRO-NETO M M, et al. Supervised weighting-online learning algorithm for short-term traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(4): 1700-1707. DOI: 10.1109/TITS.2013.2267735.
[13] 徐永俊. 基于混沌和SVR的短时交通流预测方法研究[D]. 成都: 西南交通大学, 2011.
[14] 刘剑, 刘丽华, 赵悦. 基于KPCA与SVM的混合核交通流数据检测[J]. 沈阳建筑大学学报(自然科学版), 2018, 34(5): 921-928. DOI: 10.11717/j.issn:2095-1922.2018.05.19.
[15] 谈苗苗. 基于LSTM和灰色模型集成的短期交通流预测[D]. 南京: 南京邮电大学, 2017.
[16] 王嘉琪. 基于CNN和LSTM的城市区域交通流量预测[D]. 大连: 大连理工大学, 2019.
[17] ZHANG D, KABULA M R. Combining weather condition data to predict traffic flow: a GRU-based deep learning approach[J]. IET Intelligent Transport Systems, 2018, 12(7): 578-585. DOI: 10.1049/iet-its.2017.0313.
[18] 于德新, 邱实, 周户星, 等. 基于GRU-RNN模型的交叉口短时交通流预测研究[J]. 公路工程, 2020, 45(4): 109-114. DOI: 10.19782/j.cnki.1674-0610.2020.04.018.
[19] 李朝阳, 李琳, 陶晓辉. 面向动态交通流预测的双流图卷积网络[EB/OL]. (2020-11-06)[2021-03-23]. http://kns.cnki.net/kcms/detail/11.5602.TP.20201105.1009.008.html.
[20] LV M Q, HONG Z X, CHEN L, et al. Temporal multi-graph convolutional network for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3337-3348. DOI: 10.1109/TITS.2020.2983763.
[21] GUO K, HU Y L, QIAN Z, et al. Dynamic graph convolution network for traffic forecasting based on latent network of Laplace matrix estimation[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(2): 1009-1018. DOI: 10.1109/TITS.2020.3019497.
[22] 黄子敬. 基于时空注意力机制的高速公路多收费站多时段出口流量预测方法研究[D]. 广州: 华南理工大学, 2020.
[23] COHEN J, COHEN P, WEST S G, et al. Applied multiple regression/correlation analysis for the behavioral sciences[M]. 3rd ed. London: Routledge, 2013: 52-138.
[24] 扬波尔斯基 A P. 双曲函数[M]. 邢富冲, 译. 北京: 中央民族学院出版社, 1987: 23-96.
[25] NAIR V, HINTON G E. Rectified linear units improve restricted Boltzmann machines[C]// Proceedings of the 27th International Conference on Machine Learning. NY, New York: Association for Computing Machinery, 2010: 807-814.
[26] ANDERSEN L N, LARSEN J, HANSEN L K, et al. Adaptive regularization of neural classifiers[C]// Neural Netwrorks for Signal Processing VII: Proceedings of the 1997 IEEE Signal Processing Society Workshop. Piscataway, NJ: IEEE, 1997: 24-33. DOI: 10.1109/NNSP.1997.622380.
[27] 袁华, 陈泽濠. 基于时间卷积神经网络的短时交通流预测算法[J]. 华南理工大学学报(自然科学版), 2020, 48(11): 107-113, 122.
[28] 贾俊平, 何晓群, 金勇进. 统计学[M]. 4版. 北京: 中国人民大学出版社, 2009: 1-165.
[29] YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 3634-3640. DOI: 10.24963/ijcai.2018/505.
[30] BAI L, YAO L N, LI C, et al. Adaptive graph convolutional recurrent network for traffic forecasting[EB/OL]. (2020-07-06)[2021-03-23]. https://arxiv.org/pdf/2007.02842v1.pdf.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed