A Cloud-Based Spatio-Temporal GNN-Transformer Hybrid Model for Traffic Flow Forecasting with External Feature Integration

2025-10-30

AI Summary

Addressing the challenges of modeling spatiotemporal dependencies and mitigating strong interference from exogenous factors (e.g., weather, holidays, accidents) in large-scale road network traffic flow forecasting, this paper proposes a cloud-edge collaborative, scalable prediction framework. Methodologically, it innovatively integrates graph neural networks (GNNs) with the Transformer architecture to jointly capture spatial topological correlations and long-term temporal dynamics; additionally, a lightweight external feature fusion module is designed to enhance robustness under complex scenarios. The framework supports high-concurrency model training in the cloud and low-latency, real-time inference at the edge. Evaluated on real-world datasets, it achieves an RMSE of 17.92 and MAE of 10.53—substantially outperforming baseline models including LSTM, TCN, GCN, and vanilla Transformer. Results demonstrate its superior accuracy, generalizability, and engineering practicality.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Large Vision Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate traffic flow forecasting is essential for the development of intelligent transportation systems (ITS), supporting tasks such as traffic signal optimization, congestion management, and route planning. Traditional models often fail to effectively capture complex spatial-temporal dependencies in large-scale road networks, especially under the influence of external factors such as weather, holidays, and traffic accidents. To address this challenge, this paper proposes a cloud-based hybrid model that integrates Spatio-Temporal Graph Neural Networks (ST-GNN) with a Transformer architecture for traffic flow prediction. The model leverages the strengths of GNNs in modeling spatial correlations across road networks and the Transformers' ability to capture long-term temporal dependencies. External contextual features are incorporated via feature fusion to enhance predictive accuracy. The proposed model is deployed on a cloud computing platform to achieve scalability and real-time adaptability. Experimental evaluation of the dataset shows that our model outperforms baseline methods (LSTM, TCN, GCN, pure Transformer) with an RMSE of only 17.92 and a MAE of only 10.53. These findings suggest that the hybrid GNN-Transformer approach provides an effective and scalable solution for cloud-based ITS applications, offering methodological advancements for traffic flow forecasting and practical implications for congestion mitigation.

Problem

• Forecasting traffic flow in intelligent transportation systems
• Capturing complex spatial-temporal dependencies in road networks
• Integrating external factors like weather and holidays

Innovation

• Cloud-based GNN-Transformer hybrid model
• Integrates external features via fusion
• Deploys on cloud for scalability