基于遗传算法优化的BP神经网络城市道路延误预测研究

Research on urban road delay prediction based on BP neural network optimized by genetic algorithm

交通延误是评价道路交通状态、优化交通管控策略的重要指标之一。如何利用现有交通数据,构建精度高、时延小的交通延误预测模型,对城市交通状态精细化描述以及管控起着至关重要的作用。文章在分析延误预测模型适用性的基础上,提出了基于遗传算法优化的BP神经网络延误预测模型,融合浮动车和路段卡口检测器数据,预测路段平均延误。选择济南市典型路段和信号控制交叉口进行验证,结果表明,与传统的BP神经网络相比,该模型能显著地提高城市道路延误预测精度,用于预测城市道路交通延误具有一定可行性。

Traffic delay is one of the important indicators to evaluate road traffic status and optimize traffic control strategy.How to use the existing traffic data to build a traffic delay prediction model with high accuracy and small delay plays a vital role in the fine description and control of urban traffic state.Based on the analysis of the applicability of the delay prediction model,this paper proposes a BP neural network delay prediction model optimized by genetic algorithm,which combines the data of floating vehicle and section bayonet detector to predict the average delay of section.The results show that compared with the traditional BP neural network,the model can significantly improve the prediction accuracy of urban road delay,and it is feasible to predict urban road traffic delay.