A Hybrid Model for Real-Time Traffic Prediction with Augmented Historical Data using Traffic Simulation

Real-time traffic prediction offers valuable tools for efficient traffic operation through timely and accurate information to road users and agencies. Despite the prevalence of data-driven approaches in traffic prediction with the advent of big data, these methods struggle to respond to unforeseen traffic situations during real-time prediction. To address this issue, we propose a hybrid model that integrates both data-driven and model-based approaches. Our model augments historical data using traffic simulation for unexpected traffic situations such as sudden speed drops on a road section, which can cause significant prediction errors. An artificial neural network is used to balance between the collected historical data and the augmented data. The proposed model was evaluated by predicting traffic conditions of an actual road section and significantly improved prediction accuracy. Our proposed method represents a state-of-the-art solution for enhancing realtime traffic prediction under the hybrid framework.