Traffic signal control based on predicted distribution of traffic jam

In this paper, we propose a new method of a traffic signal control based on the predicted distribution of the traffic jam. First, we built a forecasting model to predict the probability distribution of vehicles for traffic jam during the each period of traffic signal. As the forecasting model, the Dynamic Bayesian Network is used and predicted the probability distribution of the amount of the standing vehicle in traffic jam. According to calculation by the Dynamic Bayesian network, the prediction of probability distribution of the amount of standing vehicles in each time will be obtained, and a control rule to adjust the split and the cycle of the signal to maintain the probability of a lower limit and a ceiling of the standing vehicles is deduced. Through the simulation using the actual traffic data of a city, the effectiveness of our method is shown.