基于深度时序聚类的城市卡口短时交通流量预测  

Short-term traffic flow prediction of city intersection based on deep temporal clustering

作　　者：郭健 郑皎凌[1] 乔少杰 邓鸿耀 孙吉刚 李欣稼 Guo Jian;Zheng Jiaoling;Qiao Shaojie;Deng Hongyao;Sun Jigang;Li Xinjia(School of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China;Sichuan Efang Intelligence Technology Co.,Ltd.,Chengdu 610000,China)

机构地区：[1]成都信息工程大学软件工程学院,成都610225 [2]四川易方智慧科技有限公司,成都610000

出　　处：《计算机应用研究》2025年第2期371-380,共10页Application Research of Computers

基　　金：香港中文大学(深圳)开放课题广东省大数据计算基础理论与方法重点实验室开放课题基金资助项目(B10120210117-OF02);云南省智能系统与计算重点实验室开放课题(ISC22Y02);四川省科技计划重点研发项目(2023YFG0027)。

摘　　要：目前,基于深度学习的交通流量预测方法存在不足。首先,基于图卷积网络的预测模型使用简化的路网拓扑,忽视了实际交通组织信息,影响预测准确性。其次,基于聚类的预测模型未考虑交通流的区域和时间相似性,未能有效利用时空模式,导致聚类结果对预测提升有限。此外,过大的训练样本增加了训练和预测时间,影响实时性。为了解决上述问题,提出了基于深度聚类的城市卡口短时流量预测模型(deep temporal clustering traffic flow prediction,DTCTFP)。首先,构建包含实际交通组织信息的路网拓扑,利用图卷积网络挖掘卡口间的时空特性;其次,引入改进的动态时间规整和最短路径分析方法,将相似的交通流对象归类到同一簇,使模型充分利用流量、时间、位置等特征信息,提升预测精度;最后利用基于簇的循环神经网络进行预测,提高模型的实时性和计算效率。基于重庆大渡口交通数据进行了实验验证,结果显示,相较于最新基准模型,在MAE、RMSE、MAPE指标上,平均降低了15.02%、10.72%、10.98%,并通过消融实验证实了所提出的聚类方法能够提升14.5%的预测准确性。Currently,deep learning-based traffic flow prediction methods have deficiencies.Firstly,the prediction model based on graph convolutional network uses a simplified road network topology,ignores the actual traffic organization information,and affects the prediction accuracy.Secondly,the clustering-based prediction model does not consider the regional and temporal similarity of traffic flow and fails to effectively utilize spatio-temporal patterns,resulting in limited enhancement of prediction by clustering results.In addition,overly large training samples increases the training and prediction time,affecting real-time performance.In order to solve the above problems,this paper proposed a deep temporal clustering traffic flow prediction(DTCTFP)model based on deep temporal clustering for short-term traffic flow prediction at urban chokepoints.Firstly,the method constructed the road network topology containing actual traffic organization information and used a graph convolutional network to mine the spatio-temporal characteristics between chokepoints.Secondly,it introduced improved dynamic temporal regularization and shortest path analysis methods to classify similar traffic flow objects into the same cluster,allowing the model to make full use of feature information such as flow rate,time,and location to improve prediction accuracy.Finally,it used a cluster-based recurrent neural network for prediction to enhance the real-time and computational efficiency of the model.Using Chongqing Dadukou traffic data,experiments show that the model reduces MAE,RMSE,and MAPE by 15.02%,10.72%,and 10.98%on average compared to the latest benchmark.The ablation test also confirms a 14.5%improvement in prediction accuracy with the proposed clustering method.

关 键 词：深度聚类 交通流量预测 循环神经网络 动态时间规整 交通卡口 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]