A Short-Term Traffic Flow Prediction Method Based on SVR

Nowadays, the issue of urban traffic congestion is becoming more and more serious. Real-time and accurate short-term traffic flow forecasting is quite crucial in the urban intelligent transportation system, which helps traffic managers formulate relevant policies to alleviate traffic congestion and other issues. In this paper, a support vector regression model is established for the short-term traffic flow prediction, and the traffic flow in Xuancheng, Anhui from August 1 to August 7 is predicted. The experiments results show that the model proposed in this paper is superior to other models based on the RMSE, MSE and MAPE three evaluation indexes. The research in this paper improves the allocation and utilization efficiency of traffic resources.