PREDICTION OF SPEED FLOW IN THE ROAD NETWORK

The purpose of this study is to provide a model to predict the speed of the traffic flow, in the road network. Using a neural network in which estimated relationship between the flow and traffic parameters including flow rate, volume flow percentage of heavy vehicles. The distinctive feature of this study with previous studies is using neural network model and the efficacy of both volume and percentage of heavy vehicles in estimating the flow rate. The data used in this study is derived from the output of loops in the road networks of Markazi province. The results of the modeling showed that by increasing the volume to capacity of up to 0.6, It is not seen a noticeable change in speed. And in these conditions and in the case of percentage of heavy vehicles is less than 10% of the flow rate, speed flow is more than 90% of the free flow speed. The results also showed that in the common day in the road network, the level of speed is on the A and B.