چكيده به لاتين
Daily growth in the number of cars and increasing traffic has become one of the challenges for metropolitan areas in different fields, including traffic jam, fuel consumption, and environmental pollution. Deployment of Intelligent Transportation Systems (ITS) is a proper solution to overcome these challenges. One of the most important technologies in these systems is vehicular communication, which tries to overcome these challenges through providing a variety of safeties, infotainment and traffic services. Predicting the state of urban traffic has a significant role in traffic management and improving the performance of intelligent transportation systems. Generally, there is useful information to better management of traffic in large volumes of traffic data collected in Intelligent Transport Systems. In recent research, use of data mining algorithms has been considered due to their performance in the field of extracting information from Big Data such as traffic data. In this thesis, collected data from intelligent transportation system in the city of Mashhad was used to predict the traffic congestion in various approaches in the city. To do this, the streets traffic data was collected and pre-processed at 15 minutes intervals over a year, and a traffic data set was obtained along with other parameters such as calendar data and meteorological data. Afterward, to predict the traffic congestion, regression and classification models were created through data mining algorithms on the prepared data set. The results of evaluation of data mining algorithms showed that the method can predict future traffic congestion at different time intervals satisfactorily. In the next step, cars awareness of the situation of traffic congestion ahead in the vehicular network and the result of choosing low traffic congestion routes to reduce travel time was measured. To evaluate the proposed method in the vehicular network, the real data was collected and a realistic simulation was used. This kind of simulation is based on simultaneous use of three simulators including traffic simulator SUMO, network simulator OMNeT++ and vehicular networks simulator Veins. These three simulators are connected to each other through TCP sockets. Simulation was done in four different urban maps for the city of Mashhad in terms of phasing and timing of traffic lights. The simulation results showed the significant reduction of travel time for the city of Mashhad on various routes and traffic conditions.