Potential Predictability of Vehicular Staying Time for Large-Scale Urban Environment

The newly emerged vehicular communication network is seen as a key technology for solving increasingly serious vehicular traffic congestion and improving road safety. New applications of vehicular networks are also emerging at the same time. Predicting vehicular staying time is vital to both solving the vehicular system problem and building efficient vehicular networking. How much the vehicular staying duration of visits to different areas can be predicted is still an open and unsolved problem. In this paper, we use real vehicular traces in Beijing and Shanghai to explore the limit of predictability of the vehicular visiting time in different areas in large cities, and we analyze the impact of different precision and slot time on predictability. We conclude that using a proper time slot is an efficient way of prediction, and a higher predictability can be achieved if the requirement for precision is reduced. Among all the cases that we studied, we find the predictability to be 76.3% for Beijing and 82.5% for Shanghai in the case with the smallest slot time and reasonable requirements for precision.