Traffic Signal Control using Predicted Distribution of Traffic Jam
Traffic signal control is an effective method to solve the traffic jam. The several methods of the traffic signal control are known such as the random walk method, Neuron Network method, Bayesian Network method, and so on. However there is a common problem such that the information of neighboring roads can not be used in predicting the amount of traffic jam. In this paper, we propose new method of the traffic signal control using the predicted distribution of the traffic jam based on the Dynamic Bayesian Network. First, we built a forecasting model to predict the probabilistic distribution of vehicle for traffic jam during each period of traffic lights. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. As the forecasting model, the Dynamic Bayesian Network is used and predicted the probabilistic distribution of the amount of the standing vehicle in traffic jam. According to the Dynamic Bayesian network constructed for the traffic jam, the prediction of probabilistic distribution of the amount of standing vehicle in each time will be obtained. And a control rule to adjust the split and the cycle to maximize the probability of between the lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of a city, the effectiveness of our method is shown.
Chengyou. Cui Jisun. Shin Michio. Miyazaki Heehyol. Lee
WASEDA Univ. Ganto Gakuin Univ.
国际会议
The International Conference on Electrical Engineering 2009(2009 电机工程国际会议)
沈阳
英文
1-3
2009-07-05（万方平台首次上网日期，不代表论文的发表时间）