基于Graph Transformer的大规模路网交通流量预测  

Traffic Flow Prediction for Large-scale Road Network Based on Graph Transformer

作　　者：董成祥[1] 魏昕[1] 张坤鹏 汪永超 DONG Chengxiang;WEI Xin;ZHANG Kunpeng;WANG Yongchao(School of Electromechanical Engineering,Guangdong University of Technology,Guangzhou 510006,China;College of Electrical Engineering,Henan University of Technology,Zhengzhou 450001,China;School of Intelligent Manufacturing,Guangzhou Panyu Polytechnic,Guangzhou 511483,China)

机构地区：[1]广东工业大学机电工程学院,广东广州510006 [2]河南工业大学电气工程学院,河南郑州450001 [3]广州番禺职业技术学院智能制造学院,广东广州511483

出　　处：《工业工程》2023年第5期159-167,共9页Industrial Engineering Journal

基　　金：国家自然科学基金资助项目(62002101);广东省普通高校特色创新项目(2022KTSCX293);广州市教育局高校科研项目(202235232)。

摘　　要：为了捕捉大规模路网交通流量复杂、动态的时空特征,实现大规模路网交通流量的准确预测,建立了基于Graph Transformer的交通流预测模型。该模型运用GRU模块提取路网中历史交通流量的时间特征,根据分布在路网中的传感器之间的关联,建立以历史交通流量为节点、传感器间的相互联系为边的交通图。在此基础上,运用基于Graph Transformer的深度学习技术进行时空特征的提取。为了验证该预测模型的性能,基于PeMS高速公路数据集与6种基线模型进行对比,实验表明本文提出的预测模型展现了最优的预测性能。To accurately predict traffic flow in large-scale road networks,a traffic flow prediction model is proposed based on Graph Transformer to capture the complex and dynamic spatiotemporal characteristics of traffic flows.Gate recurrent unit(GRU)module is adopted in the model to extract temporal features of historical traffic flow data in a road network.According to the connections among sensors distributed in a network,traffic graphs are then established with historical traffic flows as nodes and connections of sensors as edges.On this basis,spatiotemporal characteristics are captured using Graph Transformer-based deep learning technologies.To verify the effectiveness of the proposed model,comparisons with six baseline models using the PeMS highway dataset are conducted.Experiments show that the proposed prediction model results in the best performance.

关 键 词：大规模路网 门控循环单元 时空特征 交通流量 

分 类 号：U491[交通运输工程—交通运输规划与管理]