ST-WaveMLP:面向交通流量预测的时空全局感知网络模型  

ST-WaveMLP:Spatio-Temporal Global-aware Network for Traffic Flow Prediction

作　　者：包锴楠 张钧波[1,2,3] 宋礼 李天瑞 BAO Kainan;ZHANG Junbo;SONG Li;LI Tianrui(School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China;JD iCity,JD Technology,Beijing 100176,China;JD Intelligent Cities Research,Beijing 100176,China)

机构地区：[1]西南交通大学计算机与人工智能学院,成都611756 [2]京东城市(北京)数字科技有限公司,北京100176 [3]北京京东智能城市大数据研究院,北京100176

出　　处：《计算机科学》2024年第5期27-34,共8页Computer Science

基　　金：国家重点研发计划(2019YFB2103201);国家自然科学基金(62172034);北京市科技新星(Z201100006820053)。

摘　　要：交通流量预测在智能交通系统中起着至关重要的作用。精准的交通流量预测不仅能帮助城市管理者进行更好的交通管理,也能帮助人们制定合适的出行计划。然而精准预测交通流量颇具挑战性,主要难点在于如何捕获交通流量数据中复杂的时空依赖性。近年来,深度学习方法已被成功应用于网格交通流量预测,主要采用深度卷积神经网络来捕获时空依赖性。但是卷积神经网络主要关注数据中空间特征的提取与整合,难以充分挖掘其中复杂的时空依赖性,而且单层卷积网络只能捕获局部空间依赖,因此,要想捕获全局空间依赖就需要对超多层的卷积网络进行堆叠,这将使整个网络模型训练收敛速度变慢。为了解决些问题,提出了一种面向交通流量预测的全局感知时空网络模型ST-WaveMLP,主要使用以多层感知机(MLP)为基础的可重复结构ST-WaveBlock来捕获相关的时空依赖。ST-WaveBlock中包含了捕获全局空间依赖和局部时间依赖的模块(SGAC),以及用于捕获局部空间依赖和全局时间依赖的模块(SLAC)。ST-WaveBlock具有较强的时空表征学习能力,通常仅用2~4个ST-WaveBlock堆叠就能有效捕获数据中的时空依赖性。最后,在4个实际交通流量数据集上进行实验验证,结果表明ST-WaveMLP具有更好的收敛性以及更高的预测精度,相较于之前最好的方法,所提方法预测精度的提升最高可达9.57%,模型收敛速度的提升最高可达30.6%。Traffic flow prediction plays an incredibly important role in intelligent transportation systems.Accurate traffic flow prediction can not only benefit transportation management but also provide appropriate travel plans for people.However,it is very challenging and the main difficulty lies in how to capture the complex spatial and temporal dependencies.In recent years,deep learning methods,mainly based on convolutional neural networks,have been successfully applied to traffic forecasting tasks.However,convolutional neural networks mainly focus on the extraction and integration of spatial features in data,so it is difficult to fully explore the complex spatio-temporal dependencies.Moreover,single-layer convolutional networks can only capture the local spatial dependencies,it is necessary to stack multiple layers of convolutional networks to capture the global spatial dependencies,which will slow down the convergence speed of the whole network model training.To solve these problems,a global-aware spatio-temporal network model(called ST-WaveMLP)for traffic prediction is proposed,which mainly employs a multi-layer perceptron based repeatable structure ST-WaveBlock to capture the complex spatio-temporal dependencies.ST-WaveBlock has an excellent spatio-temporal representation learning capability,often using only 2~4 ST-WaveBlock stacks to effectively capture the spatio-temporal dependencies in the data.Finally,the experimental validation on four real traffic flow datasets shows that ST-WaveMLP has better convergence and better prediction accuracy,with a relative improvement of up to 9.57%in prediction accuracy and up to 30.6%in model convergence speed compared to the previous best method.

关 键 词：交通流量预测 时空依赖性 时空深度学习 时空数据挖掘 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]