Application of KNN prediction model in urban traffic flow prediction

Abstract

Traffic congestion is one of the most important problems of urban traffic. Real time prediction of urban traffic flow can provide data reference to congestion dredging and driving route planning. In order to realize real-time urban traffic flow prediction, an urban traffic flow prediction model based on K nearest neighbor (KNN) model is studied. The experimental results show that the average prediction time of the urban traffic flow prediction model based on KNN is 1.3s and the average prediction accuracy is 91.1%. It can effectively realize the real-time urban bayonet traffic flow prediction efficiently and accurately, and it is of great practical value for the traffic management department to prevent and dredge road congestion and for the driver to choose a smooth driving path.