A Novel Scheme of Traffic Information Estimation by Vehicular Ad-hoc Networks

Vehicular Ad-hoc Network (VANET) is a new technology in the field of wireless networks and can support and facilitate various applications such as traffic information for vehicles. However marketing is vital factor on the performance of technology. This paper proposes a new approach for traffic volume estimation on a road segment based on real volume of VANET-equipped vehicles. Traffic information of different groups of vehicles has been collected by a clustering algorithm. Then a chaining technique of the clusters transmits the information to a roadside cloud. Finally, a machine learning method is applied to generalize total traffic volume from the collected data. Performance of the proposed approach is evaluated by a simulation on a real map of Hemmat Highway in Tehran and accuracy of the prediction has been shown in compared with real data.