融合多因素的短时交通流预测研究

doi:10.3778/j.issn.1002-8331.2105-0421

摘要/Abstract

摘要： 交通流预测一直是交通领域的研究热点，针对现有交通流预测研究大多为常态下的预测，而未考虑天气、节假日等外部因素的影响，提出了一种融合多因素的短时交通流预测模型。通过长短时记忆网络（long short-term memory，LSTM）捕捉时间序列的长期依赖关系，引入注意力机制，利用注意力机制自适应地选择相应的驱动序列，实现短时交通流的预测。实验分别与传统模型、未引入注意力机制的CLA-ATTN模型及未融合多因素的CLA-MFACTOR模型进行对比分析，结果证明所提出的CLA模型具有较高的预测准确度，是一种较好的预测方法。

关键词: 多因素, 短时交通流预测, 长短时记忆网络（LSTM）, 注意力机制

Abstract: Traffic flow prediction has always been a hot research topic in the field of transportation. In view of the fact that most of the existing traffic flow prediction researches are under normal conditions without considering the influence of weather, holidays and other external factors, this paper proposes a short-term traffic flow prediction model integrating multiple factors. Long short-term memory（LSTM） is used to capture the long-term dependence of time series, and then the attention mechanism is introduced to adaptively select the corresponding driving sequence to realize short-term traffic flow prediction. By comparing with the traditional model, the CLA-ATTN model without attention mechanism and the CLA-MFACTOR model without the introduction of multi-factors, the results show that the CLA model has higher prediction accuracy and is a better prediction method.

Key words: multi-factors, short-term traffic flow prediction, long short-term memory（LSTM）, attention mechanism

王庆荣, 田可可, 朱昌锋, 魏怡萌. 融合多因素的短时交通流预测研究[J]. 计算机工程与应用, 2022, 58(21): 309-316.

WANG Qingrong, TIAN Keke, ZHU Changfeng, WEI Yimeng. Short Term Traffic Flow Prediction Based on Multi-Factors[J]. Computer Engineering and Applications, 2022, 58(21): 309-316.

参考文献

[1] LUO X L，LI D Y，YANG Y，et al.Spatiotemporal traffic flow prediction with KNN and LSTM[J].Journal of Advanced Transportation，2019（1）：537-546.
[2] 邱敦国，兰时勇，杨红雨.基于时空特性的短时交通流预测模型[J].华南理工大学学报（自然科学版），2014，42（7）：49-54.
QIU D G，LAN S Y，YANG H Y.Short-term traffic flow forecast model based on temporal-spatial characteristics[J].Journal of South China University of Technology（Natural Science Edition），2014，42（7）：49-54.
[3] 邴其春，龚勃文，林赐云，等.基于粒子群优化投影寻踪回归模型的短时交通流预测[J].中南大学学报（自然科学版），2016，47（12）：4277-4282.
BING Q C，GONG B W，LIN C Y，et al.Short-term traffic flow prediction method based on particle swarm optimization projection pursuit re-gression model[J].Journal of Central South University（Science and Technology），2016，47（12）：4277-4282.
[4] 罗文慧，董宝田，王泽胜.基于CNN-SVR混合深度学习模型的短时交通流预测[J].交通运输系统工程与信息，2017，17（5）：68-74.
LUO W H，DONG B T，WANG Z S.Short-term traffic flow prediction based on CNN-SVR hybrid deep learning model[J].Journal of Transportation Systems Engineering and Information Technology，2017，17（5）：68-74.
[5] ZHANG G S，WANG W L，SHEN Q，et al.A novel learning method for multi-intersections aware traffic flow forecasting[J].Neurocomputing，2020，398：477-484.
[6] 白伟华，张传斌，张塽旖，等.基于异常值识别卡尔曼滤波器的短期交通流预测[J].计算机应用研究，2021，38（3）：817-821.
BAI W H，ZHANG C B，ZHANG S Y，et al.Outlier-identified Kalman filter for short-term traffic flow forecasting[J].Application Research of Computers，2021，38（3）：817-821.
[7] QIAN Y S，ZENG J W，ZHANG S F，et al.Short-term traffic prediction based on genetic algorithm improved neural network[J].Tehni?ki Vjesnik，2020，27（4）：1270-1276.
[8] LU S Q，ZHANG Q Y，CHEN G S，et al.A combined method for short-term traffic flow prediction based on recurrent neural network[J].Alexandria Engineering Journal，2021，60（1）：87-94.
[9] 李彤伟，王庆荣.路网交通流在时空分析背景下的预测研究[J].计算机工程与应用，2020，56（17）：258-265.
LI T W，WANG Q R.Prediction research on road network traffic flow in background of time and space analysis[J].Computer Engineering and Applications，2020，56（17）：258-265.
[10] ZHAO J L，QU H，ZHAO J H，et al.Towards traffic matrix prediction with LSTM recurrent neural networks[J].Electronics Letters，2018，54（9）：566-568.
[11] WANG J，HU F，LI L，et al.Deep bi-directional long short-term memory model for short-term trafficflow predictio[C]//Proceedings of the International Conference on Neural Information Processing，2017：306-316.
[12] 吕鲜，戚湧，张伟斌.基于长短期记忆模型的交通拥堵预测方法[J].南京理工大学学报，2020，44（1）：26-32.
LV X，QI Y，ZHANG W B.Traffic congestion prediction method based on long short-term memory model[J].Journal of Nanjing University of Science and Technology，2020，44（1）：26-32.
[13] 桂智明，李壮壮，郭黎敏.基于ACGRU模型的短时交通流预测[J].计算机工程与应用，2020，56（21）：260-265.
GUI Z M，LI Z Z，GUO L M.Short-term traffic flow prediction based on ACGRU model[J].Computer Engineering and Applications，2020，56（21）：260-265.
[14] QIAO Y H，WANG Y，MA C X，et al.Short-term traffic flow prediction based on 1DCNN-LSTM neural network structure[J].Modern Physics Letters B，2021，35（2）：2150042.
[15] 王庆荣，李彤伟，朱昌锋.基于小波去噪和LSTM模型的短时交通流预测[J].测试科学与仪器（英文版），2021（2）：195-207.
WANG Q R，LI T W，ZHU C F.Short-time prediction for traffic flow based on wavelet de-noising and LSTM model[J].Journal of Measurement Science and Instrumentation，2021（2）：195-207.
[16] SUN B，SUN T，ZHANG Y J，et al.Urban traffic flow online prediction based on multi-component attention mechanism[J].IET Intelligent Transport Systems，2020，14（10）：1249-1258.
[17] LI M，WANG Y W，WANG Z W，et al.A deep learning method based on an attention mechanism for wireless network traffic prediction[J].Ad Hoc Networks，2020，107：102258.