The traffic flow system is a complex dynamic system, and the traffic flow data have complex spatiotemporal characteristics. Therefore, to deeply explore the spatiotemporal characteristics of traffic flow data, a novel spatiotemporal multivariate partial grey prediction model for multi-segment traffic flow is proposed, which is suitable for short-term traffic flow prediction.
The model adopts grey relational degree analysis to screen multi-segment traffic flow data and further selects time-series data from different periods based on the periodic patterns of traffic flow to capture the spatiotemporal characteristics of traffic datasets. Matrix analysis is then performed for parameter estimation and model construction. To enhance model applicability, particle swarm optimization is employed to optimize the background value coefficient, thereby reducing prediction errors and improving prediction accuracy.
The proposed model achieves mean absolute percentage error (MAPE) values below 7% across all evaluated scenarios. Short-term traffic flow prediction is examined over three time periods from three perspectives. The predicted trends closely align with the actual traffic flow sequences, confirming the model’s strong predictive performance.
The effectiveness of the new model is illustrated by three effectiveness analysis cases. The results are better than comparison models that include several multivariate grey prediction models and deep learning models, which shows the effectiveness of the proposed model. The simulation results of three effectiveness analysis cases are applied to the short-time traffic flow prediction problem.
