Vehicular movement patterns: A prediction-based route discovery technique for VANETs

Applications for Vehicular Ad-hoc Networks (VANETs) have been surfacing every day as with any new network architecture. One of the many challenges that have been addressed is the use of probabilistic models and behavioral patterns to predict routes vehicles undertake in a certain geographical area. This challenge, once overcome, could prove to be very beneficial for problems such as vehicular traffic control. This paper proposes a predictive technique based on sequential patterns and two mechanisms used to prepare data for this technique, as well as some performance evaluation for these mechanisms to determine the most feasible choice in terms of communication overhead. From the experiments, it can be noticed that one of the data collecting schemes has proven to be more efficient when travelling at different speeds.