A Traffic Flow Dependency and Dynamics based Deep Learning Aided Approach for Network-Wide Traffic Speed Propagation Prediction
A Traffic Flow Dependency and Dynamics based Deep Learning Aided Approach for Network-Wide Traffic Speed Propagation Prediction
复制标题
DOI：
10.1016/j.trb.2022.11.009
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Hanyi Yang;Lili Du;Guohui Zhang;Tianwei Ma
中科院分区：
文献类型：
--
作者：
Hanyi Yang;Lili Du;Guohui Zhang;Tianwei Ma
网络范围内未来交通速度分布及其传播的信息有利于制定主动的交通拥塞管理策略。然而，预测网络范围的流量速度传播是不平凡的。本研究开发了一种基于流量依赖性和动态性的深度学习辅助方法（TD 2-DL），该方法通过显式整合时空流量依赖性、流量动态性和深度学习方法技术来预测网络范围内的高分辨率流量速度传播。具体来说，我们首先开发了一个基于图论的方法来确定本地的时空交通依赖性的每一条道路之间的相邻道路自适应的预测范围和交通延误。然后，基于交通流的初始条件和边界条件，用v-CTM对各条道路上的交通速度传播进行了数学描述。接下来，使用长短期记忆（LSTM）模型来预测边界条件，其中考虑了交通时空依赖性和v-CTM预测的历史数据。通过这种方式，我们将物理模型（流量依赖和v-CTM）与深度学习方法很好地耦合，并进一步使它们在此框架下协同进化。最后，EKF被用来同化的预测交通速度由v-CTM预测耦合LSTM和现场交通数据;模糊神经网络被引入到插补丢失和损坏的数据，以提高交通速度预测精度。数值实验表明，TD 2-DL预测的网络范围内的交通速度传播在30分钟内的准确率从85%-98%。它优于最近在文献中开发的测试模型。消融实验结果证实了交通依赖因素和整合数据填补和同化技术，以提高预测精度的意义。
The information of network-wide future traffic speed distribution and its propagation is beneficial to develop proactive traffic congestion management strategies. However, predicting network-wide traffic speed propagation is non-trivial. This study develops atraffic flowdependency anddynamics based deep learning aided approach (TD2-DL), which predict network-wide high resolution traffic speed propagation by explicitly integrating temporal-spatial flow dependency, traffic flow dynamics with deep learning method techniques. Specifically, we first develop a graph theory-based method to identify the local temporal-spatial traffic dependency of each road among neighboring roads adaptive to the prediction horizon and traffic delay. Then, traffic speed propagation on every road is mathematically described byv-CTM based on traffic initial and boundary conditions. Next, the long short-term memory (LSTM) model is employed to predict boundary conditions factoring the traffic temporal-spatial dependency and historical data predicted byv-CTM. In this way, we well couple the physical models (traffic dependency andv-CTM) with the deep learning approach, and further make them coevolution under this framework. Last, an EKF is used to assimilate predicted traffic speed predicted byv-CTM coupled with the LSTMs and the field traffic data; an FNN is introduced to impute missing and corrupted data for improving the traffic speed prediction accuracy. The numerical experiments indicated that the TD2-DL predicted the network-wide traffic speed propagation in 30 minutes with accuracy varying from 85%-98%. It outperformed the tested models recently developed in literature. The ablation experimental results confirmed the significance of factoring traffic dependency and integrating data imputation and assimilation techniques for improving the prediction accuracy.