A stochastic mobility model for traffic forecasting in urban environments.

With the steadily growing traffic demand, urban traffic congestion is becoming a critical issue threatening several factors, including public safety, emissions of greenhouse gas, and transport inefficiencies. Thus, intelligent transport systems (ITS) have emerged as a promising solution to easing the burden of congestion. ITS rely on different technologies such as VANET (Vehicular Adhoc Networks) which provide the transportation system with ubiquitous connectivity allowing the exchange of traffic information between vehicles and roadside terminals. This can support numerous smart mobility applications such as traffic signal control and real-time traffic management. Hence, mobility models were developed to emulate and forecast the distribution of traffic which will be helpful to the design and management of traffic control strategies. In this context, this study specifically concentrates on developing a mobility model that reflects vehicular activities in urban environments based on vehicular information collected using vehicular communications. The behavior of vehicles along multi-lane roads and intersections is modeled as a stochastic process using queuing theory. Particularly, the queue system is analyzed as a continuous-time Markov chain (CTMC) and by calculating the steady-state probabilities, different performance measures are derived and analyzed under various scenarios. To validate the model, the obtained forecasts are compared with a queue model and realistic traces. The results show that the model is capable of reproducing the realistic behavior of traffic in urban roads without incurring heavy costs and time-consuming computing. The obtained estimates were then used to design an actuated traffic light and a vehicle speed adaptor. From the simulation results, it is clear that using the proposed traffic forecasting model helps reduce vehicles idling and travel times. • Using real-time traffic data collected via V2X increases prediction accuracy. • Markov chains allow realistic, fast and efficient urban traffic prediction. • CTMC traffic model shows better prediction accuracy compared to basic queue models. • Traffic prediction improves the performance of traffic-aware ITS applications. [ABSTRACT FROM AUTHOR]