Short-term traffic flow forecasting model based on Elman neural network

The real time adaptive control of urban traffic, as a complex large system, usually needs to know the traffic of every intersection in advance. So traffic flow forecasting is a key problem in the real time adaptive control of urban traffic. A kind of typical truck multi- intersection section of city road is researched in this paper. A dynamic recursion network which is called Elman neutral network model is presented. Because of its dynamic memory, the proposed recurrent model can predict traffic flow fast and correctly in the condition of smaller network size or fewer neurons. BP algorithm is used to determine the weights of Elman NN model respectively. The method enhances training speed and mapping accurate. The simulation results show the effectiveness of the model.