短时交通流量两种预测方法的研究

实时、准确的完成短时交通流量预测是实现交通控制与诱导的关键。采用基于L-M算法的BP神经网络预测方法和基于混沌时间序列的预测方法对短时交通流量时间序列进行了预测研究,给出两种方法的基本原理及具体的预测步骤,并对一组实际的流量数据进行了预测。仿真结果表明:两种方法都能较准确的预测交通流量,但混沌时间序列方法的实时性更好一些,更适合于预测短时交通流量。

Study on Short-term Traffic Flow Forecsating Based on Two Different Methods

Accurate real-time prediction of short-term traffic flow is the key technology in traffic control and guidance.Two prediction methods are used to forecast short-term traffic flow:BP neural network prediction method based on L-M algorithm and the prediction method based on chaos time array.Provide the basic principles and concrete prediction step of the methods.Also use the methods to predict a real traffic flow data.The result show that the two prediction methods can be used in the prediction of traffic flow with considerably high accuracy,and the method based on chaos time array is more suitahle for forecasting short-term traffic flow.