A new prediction method of short-term traffic flow at intersection based on internet of vehicles. (26th November 2022)

• Record Type: Journal Article
• Authors: Zheng, Ying; Zhou, Ying
• Is Part Of: International journal of vehicle information and communication systems. Volume 7:Number 3(2022)
• Page Start: 228
• Page End: 243
• Publication Date: 2022-11-26
• Subjects: internet of vehicles -- intersection -- short-term traffic flow -- prediction; Automobiles -- Electronic equipment -- Periodicals; 629.27
• Languages: English
• ISSNs: 1471-0242

Abstract

In order to overcome the problems of large error and long time-consuming in the prediction of short-term traffic flow at intersections, a new short-term traffic flow prediction method based on internet of vehicles is proposed in this paper. In the environment of internet of vehicles, the training samples are input into the prediction model of internet of vehicles, the output value is calculated, and the error is obtained. Then, the weights and wavelet factors of the network are modified by gradient descent algorithm. When the network error reaches the set accuracy or reaches the maximum training times, the training is stopped to get the predicted short-term traffic flow. The experimental results show that the mean square percentage error is about 0.01%, and the longest prediction time is 0.878 min. the fitting degree between the predicted value and the actual value of traffic flow is high, and the prediction effect is ideal.