H. Wang, X. Liu, A. Donofrio

Pages: 141-152

Abstract
Urban traffic problem has become one of the problems that restrict the sustainable development of cities. In order to improve the urban traffic situation, this paper provided a new intersection congestion prediction method based on Internet of vehicles technology. This method combines with the Internet of vehicles technology to effectively realize the efficiency, security and networking of urban traffic network. In the simulation environment of the Internet of vehicles, combined with the characteristics of urban road traffic flow and the factors affecting urban traffic congestion, the exit traffic flow of the road section is calculated, and the road network index value is weighted by the road section value according to the road section vehicle kilometers, and the traffic flow prediction model is constructed. The experimental results show that when the error rate is 0.5%, the prediction rate of this method is close to 100%, and the traffic flow prediction value is close to the actual value. The average total vehicle delay in one cycle of intersection is 4.604s, which can reduce the long total vehicle delay and alleviate traffic congestion.
Keywords: internet of vehicles; intersection; congestion prediction; traffic flow