Urban expressway short-term traffic state forecasting

Traffic control and guidance is very important to intelligent transportation, which is realized by precise real time traffic state forecasting. CTM (Cell Transmission Model) can describe exactly how traffic shock wave and queue form, yet off-ramp diversion coefficients are set to be time-invariant, which is not conform to the reality that is full of random events. Therefore, CTM could not practically meet the forecast demand. To address this problem, a hybrid modeling strategy based on both CTM and traffic flow diversion coefficients forecast is proposed in this paper. In the proposed method, traffic flow diversion coefficients are firstly forecasted using an advanced NN (Neural Network) with error compensation mechanism, and then CTM is used to forecast traffic state on the basis of the first step's predictions. Simulation results show that, the present model can obtain accurate predictions whose accuracy are 4.6 and 5.8 percent higher than CTM, reaching 92.6 and 93.2 percent, in terms of cell vehicle number and link traffic flow, respectively. For this reason, the present model can practically meet the forecast demand.