基于非参数回归预测下的干线协调控制研究

Research on Coordinated Control Based on Nonparametric Regression Prediction

城市干线协调控制是智能交通研究的关键环节。由于交通流是一个时变的、复杂的非线性系统,具有高度的不确定性、随机性,因此很难建立准确的模型,针对这一问题,本文采用非参数回归预测的方法对交通量进行预测,并运用到干线协调控制中,根据预测出的各交叉口短时交通量对干线协调控制进行配时设计。通过仿真表明,该方法能有效减少交叉口平均延误。

Urban arterial coordination control is a key link in the research of intelligent transportation. Traffic flow is a time-varying and complex nonlinear system, of a high degree of uncertainty and randomness, making it difficult to establish an accurate model. Therefore, we adopt the method of nonparametric regression forecast to forecast traffic volume. We apply the prediction into the coordinated control of main line, and into the timing arterial coordination control design according to predict short-term traffic volume of each intersection. Simulation results show that this method can effectively reduce the average delay in intersections.