Analysis and Evaluation of Smart Ramp Metering System on Urban Traffic Flow Control (Case Study: Tehran-Hakim Highway)

Taking advantage of short-term traffic forecasts and using it in traffic management will reduce possible blockages and by reducing the travel time and distance traveled by cars, it will reduce noise pollution, air pollution and also consumption costs. It will be fueled. By knowing the traffic in different hours and predicting it, you can have a better management and planning for the roads of the country, the characteristics of the traffic flow in a road is one of the most important factors in decision making and traffic policy in a region. In this study, using traffic evaluation protocols by means of neural network, a traffic evaluation prediction model was built. Also, the technical evaluation and its economic benefits are discussed. In this regard, by using the traffic count in urban highways and by using the neural network model, the traffic prediction has been done. In the neural network, 4 input variables were used, low or high density, The volume of the number of cars, the type of vehicle, the flow speed, the number of 10 neurons were used in the hidden layer, and finally the numerical model was displayed as a numerical matrix. To predict the current density with proper accuracy, which was done here with r=0.93. Also, to compare the linear regression model, the accuracy of the regression model is lower than the neural network model and r=0.88 was obtained at a significance level of less than 0.05.