Real-time predication and navigation on traffic congestion model with equilibrium Markov chain

With the explosive growth of vehicles on the road, traffic congestion has become an inevitable problem when applying guidance algorithms to transportation networks in a busy and crowded city. In our study, the authors proposed an advanced prediction and navigation models on a dynamic traffic network. In contrast to the traditional shortest path algorithms, focused on the static network, the first part of our guiding method considered the potential traffic jams and was developed to provide the optimal driving advice for the distinct periods of a day. Accordingly, by dividing the real-time Global Positioning System data of taxis in Shenzhen city into 50 regions, the equilibrium Markov chain model was designed for dispatching vehicles and applied to ease the city congestion. With the reveals of our field experiments, the traffic congestion of city traffic networks can be alleviated effectively and efficiently, the system performance also can be retained.