系统仿真学报 ›› 2020, Vol. 32 ›› Issue (6): 1164-1171.doi: 10.16182/j.issn1004731x.joss.19-0565

• 国民经济仿真 • 上一篇    下一篇

基于深度学习的节假日高速公路交通流预测方法

戢晓峰1,2, 戈艺澄1,2   

  1. 1. 昆明理工大学交通工程学院,云南 昆明 650504;
    2. 云南综合交通发展与区域物流管理智库,云南 昆明 650504
  • 收稿日期:2019-10-08 修回日期:2020-01-07 出版日期:2020-06-25 发布日期:2020-06-25
  • 作者简介:戢晓峰(1982-),男,湖北随州,博士,教授,博导,研究方向为交通运输规划与管理等。
  • 基金资助:
    国家自然科学基金(71563023),云南省院省校合作研究项目(SYSX201611)

Holiday Highway Traffic Flow Prediction Method Based on Deep Learning

Ji Xiaofeng1,2, Ge Yicheng1,2   

  1. 1. School of Traffic Engineering, Kunming University of Science and Technology, Kunming 650504, China;
    2. Yunnan Integrated Transportation Development and Regional Logistics Management Think Tank, Kunming 650504, China
  • Received:2019-10-08 Revised:2020-01-07 Online:2020-06-25 Published:2020-06-25

摘要: 准确的预测节假日期间高速公路交通流量,能够为节假日高速公路应急管理提供重要的数据基础。利用深度学习的理论框架建立了LSTM-SVR 预测模型,利用BP 神经网络对样本数据进行处理,再将LSTM 捕获的数据特征输入SVR 回归层中实现交通流预测。选取“ 十一” 黄金周前后时段,利用位于丽江市的交调站流量监测数据对LSTM-SVR 模型进行验证,并将LSTM-SVR 模型与其它模型预测效果进行对比。发现LSTM-SVR 模型在节假日不同时段、天气、流量状态下的高速公路交通流预测中有较好的适用性。

关键词: 交通工程, 节假日交通流预测, 深度学习, LSTM-SVR, 高速公路交通流

Abstract: Accurately predicting highway traffic holiday flow can provide important data for the emergency management of highway. The LSTM-SVR prediction model is established by using the theoretical framework of deep learning. The BP neural network is used to process the sample data, and the data features captured by LSTM are input into the SVR regression layer to realize the traffic flow prediction. Before and after the “Eleventh” Golden Week, the LSTM-SVR model was verified by using the traffic monitoring data of the intermodulation station in Lijiang City and the prediction results were compared with the others. It is found that the LSTM-SVR model has good applicability in the highway traffic flow prediction of different periods, weathers and traffic conditions.

Key words: traffic engineering, holiday traffic flow prediction, deep learning, LSTM-SVR, expressway traffic flow

中图分类号: