Data-driven traffic flow analysis for vehicular communications

Due to high mobility and frequent disconnections in a vehicular network, reliable and efficient vehicular communication is very challenging. Previous studies focus on predicting the trajectories of single vehicles. Due to many random factors, however, there is little regularity in the movements of a single vehicle in an urban area, and this motivates us to take a holistic network perspective. With this insight, we model the time varying regularities of road traffic flows in road segments and intersections by mining statistic trajectories of all vehicles in the network. Based on these regularities and local real-time traffic information, we propose a new method to calculate the expected transfer delay from a current position to a given destination. We also propose a method to collect updated destination information. By combining the above two methods, we design a routing algorithm for vehicle-to-vehicle data transmission in vehicular networks, and then prove that it is a linear-time algorithm. Finally, we evaluate our algorithm by using information of real taxi vehicles. The results show that the performance of our algorithm is significantly better than other solutions in terms of packet delay.