基于多元时序和模式挖掘的终端区交通流预测  

Traffic Flow Prediction Model Based on Multivariate Time Series and Pattern Mining in Terminal Area

作　　者：祝玮琦 陈海燕[1,3] 刘莉 袁立罡 田文[2] ZHU Weiqi;CHEN Haiyan;LIU Li;YUAN Ligang;TIAN Wen(College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,P.R.China;College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,P.R.China;Collaborative Innovation Center of Novel Software Technology and Industrialization,Nanjing 210023,P.R.China)

机构地区：[1]南京航空航天大学计算机科学与技术学院,中国南京211106 [2]南京航空航天大学民航学院,中国南京211106 [3]软件新技术与产业化协同创新中心,中国南京210023

出　　处：《Transactions of Nanjing University of Aeronautics and Astronautics》2023年第5期595-606,共12页南京航空航天大学学报（英文版）

基　　金：supported by the National Key R&D Program of China(Nos.2022YFB2602403,2022YFB2602401);the National Natural Science Foundation of China(No.71971112)。

摘　　要：为了提高终端区不同气象场景下的交通流预测准确率,提出一种融合多元时序和模式挖掘(Multivariate time series and pattern mining,MTSPM)的终端区交通流预测模型。首先,给出了一种基于多元时间序列的终端区交通流预测模型,通过深度学习模型CNN-GRUA将终端区的交通需求、天气和策略特征进行融合并用于交通流预测;其次,针对交通流这一单变量时间序列,设计了一种基于趋势分段符号化的时间序列BOP(Bag-of-pattern)表示方法——TSSBOP,通过基于趋势的分段、符号化和模式表示来挖掘交通流序列中的内在模式;最后,根据两个模型在验证集上的预测精度进行加权融合,得到最终的终端区交通流预测值。在广州终端区的历史数据集上的对比实验表明,所提出的TSSBOP表示法能够有效挖掘出原始序列中的模式,所提出的基于MTSPM的终端区交通流预测模型能有效提高不同气象场景下的交通流预测性能。To improve the accuracy of traffic flow prediction under different weather scenarios in the terminal area,a terminal area traffic flow prediction model fusing multivariate time series and pattern mining(MTSPM)is proposed.Firstly,a multivariate time series-based traffic flow prediction model for terminal areas is presented where the traffic demand,weather,and strategy of terminal areas are fused to optimize the traffic flow prediction by a deep learning model CNN-GRUA,here CNN is the convolutional neural network and GRUA denotes the gated recurrent unit(GRU)model with attention mechanism.Secondly,a time series bag-of-pattern(BOP)representation based on trend segmentation symbolization,TSSBOP,is designed for univariate time series prediction model to mine the intrinsic patterns in the traffic flow series through trend-based segmentation,symbolization,and pattern representation.Finally,the final traffic flow prediction values are obtained by weighted fusion based on the prediction accuracy on the validation set of the two models.The comparison experiments on the historical data set of the Guangzhou terminal area show that the proposed time series representation TSSBOP can effectively mine the patterns in the original time series,and the proposed traffic flow prediction model MTSPM can significantly enhance the performance of traffic flow prediction under different weather scenarios in the terminal area.

关 键 词：交通流预测 多元时间序列 时间序列表示 模式挖掘 深度学习 

分 类 号：TN925[电子电信—通信与信息系统]