Stochastic model of traffic jam and traffic signal control

Traffic signal control is an effective method to solve the traffic jam. and forecasting traffic density has been known as an important part of the Intelligent Transportation System (ITS). The several methods of the traffic signal control are known such as random walk method, Neuron Network method, Bayesian Network method, and so on. In this paper, we propose a new method of a traffic signal control using a predicted distribution of traffic jam based on a Dynamic Bayesian Network model. First, a forecasting model to predict a probabilistic distribution of the traffic jam during each period of traffic lights is built. As the forecasting model, the Dynamic Bayesian Network is used to predict the probabilistic distribution of a density of the traffic jam. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and the number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. Next, the probabilistic distribution of the density of standing vehicle in each cycle will be predicted using the Dynamic Bayesian Network constructed for the traffic jam. And then a control rule to adjust the split and the cycle to increase the probability between a lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of Kitakyushu city, the effectiveness of the method is shown.