Dynamic Route Optimization Problem Based on Variable Range Short-Term Traffic Flow Forecast

Abstract

A dynamic route optimization scheme based on short-term traffic flow prediction is designed. The overall idea of this paper is to use the real-time information of each section of the urban road communication network to predict the short-term traffic speed of the road in the next 5 min, in order to reflect the changes of the road traffic state of each section of the urban road traffic network. Then, the speed prediction information of each section in the urban road traffic network is converted into the estimated average travel time of each section by using the speed-time conversion formula, and then the road weight of each section in the urban road traffic network is set. Finally, the optimal route at the current time is calculated by using the improved algorithm based on the traditional Dijkstra algorithm. Before the traffic participant arrives at the destination, the scheme will cycle through the short-term prediction and route optimization of the traffic flow until the traffic participant arrives at the destination. And then achieve the balance of traffic conditions of various sections in the urban road traffic network, improve the situation of urban road traffic congestion, and avoid the emergence of bad road traffic conditions such as “navigation congestion”.