基于深度学习的短时交通流预测研究综述

doi:10.3778/j.issn.1002-8331.2407-0410

摘要/Abstract

摘要： 交通流预测是智能交通系统的重要组成部分，旨在准确估计未来特定时间间隔内特定区域的交通流量。随着车辆的增长和路网中不同区域之间的复杂时空关系，传统的交通预测方法难以准确描述交通数据的特征，而深度学习的预测方法能够更好地处理复杂的特征结构，因此，深度学习的方法已成为短时交通流预测的研究热点。总结了传统交通流预测方法和深度学习交通流预测方法的研究现状，详细介绍了深度学习架构卷积神经网络、自编码器、循环神经网络、图卷积神经网络、注意力机制与Transformer以及深度学习混合神经网络，并且对深度学习的交通流预测文献、深度学习的超参数和场景进行了总结分析。总结了现有文献中常用的国内外公共数据集。根据前人的模型实验对交通预测模型的性能进行了对比分析。最后，讨论了基于深度学习的交通预测领域的未来研究方向。

关键词: 交通流预测, 深度学习, 短时交通流, 交通数据集, 时空特征

Abstract: Traffic flow prediction is an important part of intelligent transportation system, which aims to accurately estimate the traffic flow of a specific area in a specific time interval in the future. With the increase of vehicles and the complex space-time relationship between different regions in the road network, traditional traffic prediction methods are difficult to accurately describe the characteristics of traffic data, while deep learning prediction methods can better deal with complex feature structures. Therefore, deep learning has become a research hotspot in short-term traffic flow prediction. Firstly, the research status of traditional traffic flow prediction methods and deep learning traffic flow prediction methods is summarized, and the deep learning architecture of convolutional neural network, autoencoder, recurrent neural network, graph convolutional neural network, attention mechanism and Transformer as well as deep learning hybrid neural network is introduced in detail. And the deep learning traffic flow prediction literature, deep learning hyperparameters and scenarios are summarized and analyzed. Secondly, the paper summarizes the common domestic and foreign public data sets in the existing literature. Then, the performance of traffic prediction models is compared and analyzed according to previous model experiments. Finally, the future research direction of traffic prediction based on deep learning is discussed.

Key words: traffic flow prediction, deep learning, short time traffic flow, traffic data set, spatio-temporal characteristics

熊章友, 李卫军, 朱晓娟, 杨国梁, 马馨瑜. 基于深度学习的短时交通流预测研究综述[J]. 计算机工程与应用, 2025, 61(11): 67-82.

XIONG Zhangyou, LI Weijun, ZHU Xiaojuan, YANG Guoliang, MA Xinyu. Short-Term Traffic Flow Prediction Based on Deep Learning[J]. Computer Engineering and Applications, 2025, 61(11): 67-82.

参考文献

[1] KARAMI Z, KASHEF R. Smart transportation planning: data, models, and algorithms[J]. Transportation Engineering, 2020, 2: 100013.
[2] QI Y, ISHAK S. A hidden Markov model for short term prediction of traffic conditions on freeways[J]. Transportation Research Part C: Emerging Technologies, 2014, 43: 95-111.
[3] SUN Y X, LENG B, GUAN W. A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system[J]. Neurocomputing, 2015, 166: 109-121.
[4] DAVIS G A, NIHAN N L. Nonparametric regression and short-term freeway traffic forecasting[J]. Journal of Transportation Engineering, 1991, 117(2): 178-188.
[5] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computer, 2006, 18(7): 1527-1554.
[6] BOUKERCHE A, WANG J. Machine learning-based traffic prediction models for intelligent transportation systems[J]. Computer Networks, 2020, 181: 107530.
[7] TEDJOPURNOMO D A, BAO Z F, ZHENG B H, et al. A survey on modern deep neural network for traffic prediction: trends, methods and challenges[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(4): 1544-1561.
[8] JIANG W W, LUO J Y. Graph neural network for traffic forecasting: a survey[J]. Expert Systems with Applications, 2022, 207: 117921.
[9] OKUTANI I, STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory[J]. Transportation Research Part B: Methodological, 1984, 18(1): 1-11.
[10] CHOROWSKI J, BAHDANAU D, SERDYUK D, et al. Attention-based models for speech recognition[J]. arXiv:1506.07503, 2015.
[11] 刘静, 关伟. 交通流预测方法综述[J]. 公路交通科技, 2004, 21(3): 82-85.
LIU J, GUAN W. A summary of traffic flow forecasting methods[J]. Journal of Highway and Transportation Research and Development, 2004, 21(3): 82-85.
[12] 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.
[13] KUMAR S V. Traffic flow prediction using Kalman filtering technique[J]. Procedia Engineering, 2017, 187: 582-587.
[14] DONG H H, JIA L M, SUN X L, et al. Road traffic flow prediction with a time-oriented ARIMA model[C]//Proceedings of the 5th International Joint Conference on INC, IMS and IDC, 2009: 1649-1652.
[15] 傅贵, 韩国强, 逯峰, 等. 基于支持向量机回归的短时交通流预测模型[J]. 华南理工大学学报(自然科学版), 2013, 41(9): 71-76.
FU G, HAN G Q, LU F, et al. Short-term traffic flow forecasting model based on support vector machine regression[J]. Journal of South China University of Technology (Natural Science Edition), 2013, 41(9): 71-76.
[16] SUN T T, HUANG Z F, ZHU H D, et al. Congestion pattern prediction for a busy traffic zone based on the hidden Markov model[J]. IEEE Access, 2021, 9: 2390-2400.
[17] CAI P L, WANG Y P, LU G Q, et al. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting[J]. Transportation Research Part C: Emerging Technologies, 2016, 62: 21-34.
[18] MOREIRA-MATIAS L, GAMA J, FERREIRA M, et al. Predicting taxi-passenger demand using streaming data[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(3): 1393-1402.
[19] TU Y, LIN S K, QIAO J Z, et al. Deep traffic congestion prediction model based on road segment grouping[J]. Applied Intelligence, 2021, 51(11): 8519-8541.
[20] ZHENG H F, LIN F, FENG X X, et al. A hybrid deep learning model with attention-based conv-LSTM networks for short-term traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 6910-6920.
[21] CHEN K, CHEN F, LAI B S, et al. Dynamic spatio-temporal graph-based CNNs for traffic flow prediction[J]. IEEE Access, 2020, 8: 185136-185145.
[22] YANG D, LI S J, PENG Z, et al. MF-CNN: traffic flow prediction using convolutional neural network and multi-features fusion[J]. IEICE Transactions on Information and Systems, 2019, 102(8): 1526-1536.
[23] BOGAERTS T, MASEGOSA A D, ANGARITA-ZAPATA J S, et al. A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2020, 112: 62-77.
[24] ZANG D, LING J W, WEI Z H, et al. Long-term traffic speed prediction based on multiscale spatio-temporal feature learning network[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3700-3709.
[25] PALM R B. Prediction as a candidate for learning deep hierarchical models of data[D]. Lyngby: Technical University of Denmark, 2012.
[26] DUAN Y J, LYU Y S, WANG F Y. Performance evaluation of the deep learning approach for traffic flow prediction at different times[C]//Proceedings of the IEEE International Conference on Service Operations and Logistics, and Informatics, 2016: 223-227.
[27] YANG H F, DILLON T S, CHEN Y P. Optimized structure of the traffic flow forecasting model with a deep learning approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2371-2381.
[28] ESSIEN A, PETROUNIAS I, SAMPAIO P, et al. A deep-learning model for urban traffic flow prediction with traffic events mined from twitter[J]. World Wide Web, 2021, 24(4): 1345-1368.
[29] TIAN Y, WEI C C, XU D W. Traffic flow prediction based on stack AutoEncoder and long short-term memory network[C]//Proceedings of the IEEE 3rd International Conference on Automation, Electronics and Electrical Engineering, 2020: 385-388.
[30] KASHYAP A A, RAVIRAJ S, DEVARAKONDA A, et al. Traffic flow prediction models-a review of deep learning techniques[J]. Cogent Engineering, 2022, 9(1): 2010510.
[31] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[32] YANG B L, SUN S L, LI J Y, et al. Traffic flow prediction using LSTM with feature enhancement[J]. Neurocomputing, 2019, 332: 320-327.
[33] ZHAO Z, CHEN W H, WU X M, et al. LSTM network: a deep learning approach for short-term traffic forecast[J]. IET Intelligent Transport Systems, 2017, 11(2): 68-75.
[34] MA X, YU H, WANG Y, et al. Large-scale transportation network congestion evolution prediction using deep learning theory[J]. PLoS One, 2015, 10(3): 0119044.
[35] LYU Z, XU J, ZHENG K, et al. LC-RNN: a deep learning model for traffic speed prediction[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018: 3470-3476.
[36] LIAO B B, ZHANG J Q, WU C, et al. Deep sequence learning with auxiliary information for traffic prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 537-546.
[37] ZHANG Z C, LI M, LIN X, et al. Multistep speed prediction on traffic networks: a graph convolutional sequence-to-sequence learning approach with attention mechanism[J]. arXiv:1810.10237, 2018.
[38] YE J C, SUN L L, DU B W, et al. Co-prediction of multiple transportation demands based on deep spatio-temporal neural network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 305-313.
[39] CHUNG J, GULCEHRE C, CHO K, et al. Gated feedback recurrent neural networks[C]//Proceedings of the 32nd International Conference on Machine Learning, 2015: 2067-2075.
[40] SUN P, BOUKERCHE A, TAO Y J. SSGRU: a novel hybrid stacked GRU-based traffic volume prediction approach in a road network[J]. Computer Communications, 2020, 160: 502-511.
[41] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[42] BAI J D, ZHU J W, SONG Y J, et al. A3T-GCN: attention temporal graph convolutional network for traffic forecasting[J]. ISPRS International Journal of Geo-Information, 2021, 10(7): 485.
[43] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[44] ALI A, ZHU Y M, ZAKARYA M. Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction[J]. Neural Networks, 2022, 145: 233-247.
[45] LI Y G, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[J]. arXiv:1707.01926, 2017.
[46] JIANG R H, WANG Z N, YONG J W, et al. Spatio-temporal meta-graph learning for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2023: 8078-8086.
[47] WANG Y, ZHENG J, DU Y Q, et al. Traffic-GGNN: predicting traffic flow via attentional spatial-temporal gated graph neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18423-18432.
[48] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[49] LIU D, TANG L, SHEN G, et al. Traffic speed prediction: an attention-based method[J]. Sensors (Basel), 2019, 19(18): 3836.
[50] ZHENG C P, FAN X L, WANG C, et al. GMAN: a graph multi-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 1234-1241.
[51] ZHANG L, WU J Q, SHEN J, et al. SATP-GAN: self-attention based generative adversarial network for traffic flow prediction[J]. Transportmetrica B: Transport Dynamics, 2021, 9(1): 552-568.
[52] ASHISH V. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[53] CAI L, JANOWICZ K, MAI G C, et al. Traffic transformer: capturing the continuity and periodicity of time series for traffic forecasting[J]. Transactions in GIS, 2020, 24(3): 736-755.
[54] CHEN C, LIU Y, CHEN L, et al. Bidirectional spatial-temporal adaptive transformer for urban traffic flow forecasting[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(10): 6913-6925.
[55] HUO G Y, ZHANG Y, WANG B Y, et al. Hierarchical spatio-temporal graph convolutional networks and transformer network for traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(4): 3855-3867.
[56] XU M X, DAI W R, LIU C M, et al. Spatial-temporal transformer networks for traffic flow forecasting[J]. arXiv:2001. 02908, 2020.
[57] MA J, ZHAO J, HOU Y. Spatial-temporal transformer networks for traffic flow forecasting using a pre-trained language model[J]. Sensors (Basel), 2024, 24(17): 5502.
[58] LIU Y P, ZHENG H F, FENG X X, et al. Short-term traffic flow prediction with Conv-LSTM[C]//Proceedings of the 9th International Conference on Wireless Communications and Signal Processing, 2017: 1-6.
[59] RANJAN N, BHANDARI S, ZHAO H P, et al. City-wide traffic congestion prediction based on CNN, LSTM and transpose CNN[J]. IEEE Access, 2020, 8: 81606-81620.
[60] ZHENG H L, LI X, LI Y F, et al. GCN-GAN: integrating graph convolutional network and generative adversarial network for traffic flow prediction[J]. IEEE Access, 2022, 10: 94051-94062.
[61] YIN L S, LIU P, WU Y Y, et al. ST-VGBiGRU: a hybrid model for traffic flow prediction with spatio-temporal multimodality[J]. IEEE Access, 2023, 11: 54968-54985.
[62] DU S D, LI T R, GONG X, et al. A hybrid method for traffic flow forecasting using multimodal deep learning[J]. International Journal of Computational Intelligence Systems, 2020, 13(1): 85-97.
[63] HOFFER E, HUBARA I, SOUDRY D. Train longer, generalize better: closing the generalization gap in large batch training of neural networks[J]. arXiv:1705.08741, 2017.
[64] CHEN L, BEI L L, AN Y, et al. A hyperparameters automatic optimization method of time graph convolution network model for traffic prediction[J]. Wireless Networks, 2021, 27(7): 4411-4419.
[65] TSAI C W, FANG Z Y. An effective hyperparameter optimization algorithm for DNN to predict passengers at a metro station[J]. ACM Transactions on Internet Technology, 2021, 21(2): 1-24.
[66] QI X D, YAO J F, WANG P, et al. Combining weather factors to predict traffic flow: a spatial-temporal fusion graph convolutional network-based deep learning approach[J]. IET Intelligent Transport Systems, 2024, 18(3): 528-539.
[67] XIA T, LIN J J, LI Y, et al. 3DGCN: 3-dimensional dynamic graph convolutional network for citywide crowd flow prediction[J]. ACM Transactions on Knowledge Discovery from Data, 2021, 15(6): 1-21.
[68] BAI L, YAO L, LI C, et al. Adaptive graph convolutional recurrent network for traffic forecasting[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020: 17804-17815.
[69] KONG W Y, GUO Z Y, LIU Y B. Spatio-temporal pivotal graph neural networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2024: 8627-8635.
[70] JI J H, WANG J Y, HUANG C, et al. Spatio-temporal self-supervised learning for traffic flow prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2023: 4356-4364.
[71] ZHANG J B, ZHENG Y, QI D K, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018, 259: 147-166.
[72] LAN S, MA Y, HUANG W, et al. DSTAGNN: dynamic spatial-temporal aware graph neural network for traffic flow forecasting[C]//Proceedings of the International Conference on Machine Learning, 2022: 11906-11917.
[73] GUO S N, LIN Y F, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 922-929.
[74] SONG C, LIN Y F, GUO S N, et al. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 914-921.
[75] SUTSKEVER I. Sequence to sequence learning with neural networks[J]. arXiv:1409.3215, 2014.
[76] YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[J]. arXiv:1709.04875, 2017.
[77] ZHANG Q, CHANG W, YIN C, et al. Attention-based spatial-temporal convolution gated recurrent unit for traffic flow forecasting[J]. Entropy (Basel), 2023, 25(6): 938.
[78] WU Z H, PAN S R, LONG G D, et al. Graph WaveNet for deep spatial-temporal graph modeling[J]. arXiv:1906.00121, 2019.
[79] YAO H X, LIU Y D, WEI Y, et al. Learning from multiple cities: a meta-learning approach for spatial-temporal prediction[C]//Proceedings of the World Wide Web Conference, 2019: 2181-2191.
[80] WEI Y, ZHENG Y, YANG Q. Transfer knowledge between cities[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 1905-1914.
[81] CHEN L, SHAO W, LYU M Q, et al. AARGNN: an attentive attributed recurrent graph neural network for traffic flow prediction considering multiple dynamic factors[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 17201-17211.
[82] WU Q, HE K W, CHEN X, et al. Deep transfer learning across cities for mobile traffic prediction[J]. ACM Transactions on Networking, 2022, 30(3): 1255-1267.
[83] TAN J Y, QIU Q Q, GUO W W, et al. Research on the construction of a knowledge graph and knowledge reasoning model in the field of urban traffic[J]. Sustainability, 2021, 13(6): 3191.
[84] WANG S, LYU Y M, PENG Y, et al. Metro traffic flow prediction via knowledge graph and spatiotemporal graph neural network[J]. Journal of Advanced Transportation, 2022, 2022: 2348375.
[85] MANIBARDO E L, LANA I, LOBO J L, et al. New perspectives on the use of online learning for congestion level prediction over traffic data[C]//Proceedings of the 2020 International Joint Conference on Neural Networks, 2020: 1-8.
[86] PENG H, DU B W, LIU M S, et al. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning[J]. Information Sciences, 2021, 578: 401-416.
[87] QU L C, LI W, LI W J, et al. Daily long-term traffic flow forecasting based on a deep neural network[J]. Expert Systems with Applications, 2019, 121: 304-312.