Traffic Flow Prediction Based on Information Aggregation and Comprehensive Temporal-Spatial Synchronous Graph Neural Network

Abstract

It is extremely important to build a reasonable traffic network structure for traffic flow prediction. Owing to the complexity and dynamic of traffic networks, the graph neural network model has become one of the most effective methods for mining the spatial-temporal relationship between traffic flow data. However, most current methods use two components to extract the spatial dependence and time dependence separately and do not consider the auxiliary effect of additional traffic factors on the prediction target. Based on the above problems, this paper proposes a neural network prediction model for a comprehensive spatial-temporal synchronous graph based on information aggregation. The model is composed of a fusion feature attention module, an information aggregation module, and a comprehensive information integration framework. The fusion feature attention module considers the impact of each traffic factor on the traffic flow and strengthens the internal relationship of various traffic features; the information aggregation module synchronously extracts the temporal-spatial dependence of traffic flow; The multi-information combination module combines the traffic flow with the secondary information to mine the hidden relationship between the primary and secondary information. The experimental results on two real-world datasets show that the prediction effect of the model set out in the present paper is significantly better than that of the baseline.