基于多源异构数据融合的高速公路交通流预测OA

Expressway traffic flow prediction is affected by multiple factors,such as holidays,historical traffic conditions and climate,and exhibits complex spatio-temporal dependencies.To address this problem,this paper proposes a novel Data-fused Spatio-Temporal Graph Attention Network(RSTGCN),which is specifically designed for short-term expressway traffic flow prediction.The model integrates data preprocessing,feature fusion,spatio-temporal graph attention and Transformer architecture.The feature fusion module integrates multi-source data to comprehensively capture variations in traffic flow.The spatio-temporal graph attention network extracts the spatio-temporal features of traffic flow,taking into account spatial layout and temporal dependencies.The Transformer architecture enhances the capability of processing long-sequence data.Experimental results show that the model outperforms benchmark models in prediction performance,and ablation experiments verify the effectiveness of each module.