Traffic Flow Prediction Model Based on Transformer and Dynamic Graph Convolutional Networks

Traffic congestion is a major challenge in urban life, and traffic flow prediction, as a critical task in intelligent transportation management, can effectively alleviate congestion and enhance traffic control efficiency. Although deep learning models have achieved significant progress in traffic flow prediction, most existing studies focus on capturing dynamic spatiotemporal features, with insufficient attention to the pivotal role of historical data's periodic characteristics in forecasting. To address this, we proposed a Transformer‐based Dynamic Graph Convolutional Network (T‐DGCN), which significantly improves prediction accuracy by integrating historical periodic features and real‐time dynamic variations. T‐DGCN employs the self‐attention mechanism of Transformer to capture temporal dependencies and combines dynamic graph convolutional networks to extract spatial features, thereby comprehensively modelling spatiotemporal dynamics. Experiments on the real highway datasets from California (PeMSD4 and PeMSD8) show that T‐DGCN outperforms state‐of‐the‐art models across multiple time horizons. On the PeMSD4 dataset, it reduces the MAE and RMSE by an average of 12.9% and 5.2% across the 15 min, 30 min, and 60 min prediction horizons, respectively. On the PeMSD8 dataset, it reduces the MAE and RMSE results by approximately 8.8% and 5.7% on average, respectively.