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 prediction methods, we proposes an Attention-based Gating mechanism Graph Convolution Network (AGGCN). Firstly, it constructures data adjacency matrix based on graph construction method. Secondly, utilized diffusion convolution method model in network. Finally, attention predict flow. The experiments were carried out two highway datasets PeMS04 PeMS08 California, USA. Compared with 7 commonly used algorithms prediction, MAE, MAPE, RMSE AGGCN are better than other baseline experiments.