Traffic flow prediction model based on gated graph convolution with attention

Abstract

As a significant part, flow forecasting is crucial to road planning, traffic control, and planning. Aiming at the problem of insufficient dependence of traffic prediction methods, we proposes an Attention-based Gating mechanism Graph Convolution Network (AGGCN). Firstly, it constructures traffic flow data and adjacency matrix based on the graph data construction method. Secondly, it utilized the diffusion graph convolution method to model the traffic flow in the traffic road network. Finally, the attention mechanism to predict the traffic flow. The experiments were carried out on two highway datasets PeMS04 and PeMS08 in California, USA. Compared with the 7 commonly used algorithms in traffic flow prediction, the MAE, MAPE, and RMSE of the AGGCN model are better than other baseline experiments.