摘要：

精准的交通流预测是实现智能交通系统的关键前提，对加强系统的仿真和控制、提高管理者的决策等方面具有重要意义。针对大多数现有的图卷积网络(GCN)模型忽略交通流数据的动态时空变化、对节点信息使用不足导致时空相关性提取不充分的问题，提出一种基于多时空图融合与动态注意力的交通流预测模型。首先，以不同的卷积单元提取交通流数据中多时域状态下的时间特征；然后，构建多时空图体现节点在空间分布中的动态变化趋势和异质性，并结合GCN提取空间特征；最后，利用多头自注意力机制分别对时空特征进行分析与融合，输出预测结果。在两个实际的公共数据集PeMS04和PeMS08上进行实验分析，并与基于注意力的时空图卷积网络(ASTGCN)、多视角的时空Transformer网络(MVSTT)和动态时空感知图神经网络(DSTAGNN)等基于时空图卷积网络的基准模型对比，结果表明所提模型在平均绝对误差(MAE)、平均绝对百分比误差(MAPE)和均方根误差(RMSE)指标上分别平均降低了7.10%、7.22%和6.47%，具有较强的适应性和鲁棒性。

关键词: 智能交通系统, 交通流预测, 时空特征, 图卷积网络, 多头自注意力机制

Abstract:

Accurate traffic flow prediction is a key prerequisite for realizing intelligent transportation systems, and is of great significance for strengthening system simulation and control and improving the decision-making of managers. To address the problem of most existing Graph Convolutional Network (GCN) models ignoring the dynamic spatial and temporal variations in traffic data and insufficiently employing node information, which leads to insufficient extraction of spatial and temporal correlations, a traffic flow prediction model based on multiple spatio-temporal graph fusion and dynamic attention is proposed. First, the temporal characteristics of traffic flow data in multi-temporal states are extracted by different convolutional cells. The next step involves constructing a multiple spatio-temporal graph to capture the dynamic trend and heterogeneity of nodes in spatial distribution, followed by extracting spatial characteristics through the integration of GCN. Finally, the spatial and temporal characteristics are analyzed and fused using the multi-head self-attention mechanism to output prediction results. Experimental analyses are performed on two public datasets, PeMS04 and PeMS08, and compared with the Attention Based Spatial-Temporal Graph Convolutional Network (ASTGCN), Multiview Spatial-Temporal Transformer Network (MVSTT), Dynamic Spatial-Temporal Aware Graph Neural Network (DSTAGNN) and other benchmark models that utilize spatio-temporal graph convolution. The results show that the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) of the proposed model are reduced by 7.10%, 7.22%, and 6.47%, respectively, demonstrating the proposed model′s strong adaptability and robustness.

Key words: intelligent transportation system, traffic flow prediction, spatio-temporal characteristics, Graph Convolution Network (GCN), multi-head self-attention mechanism