基于组合模型的交通流量预测方法  

Traffic Flow Forecasting Based on Combination Model

作　　者：丛新宇[1] 虞慧群[1] 范贵生[1] 

机构地区：[1]华东理工大学计算机科学与工程系,上海200237

出　　处：《华东理工大学学报（自然科学版）》2011年第3期340-345,共6页Journal of East China University of Science and Technology

基　　金：国家自然科学基金(60773094);上海市曙光计划(07SG32)

摘　　要：随着智能交通系统的蓬勃发展,交通控制和交通流诱导成为智能交通系统(ITS)研究的热门问题,而实现交通控制诱导的关键问题是实时准确的短时交通流量预测,预测的精度直接影响交通控制和诱导的效果。为此,提出基于组合模型的交通流量预测方法,该方法将历史趋势模型和多元回归模型加权组合以建立组合预测模型,并利用加权平均的方法,对较精确的预测值赋予较大的权重,从而提高模型预测的精度。通过对2009年上海城市交通流量预测结果的分析,证明该方法可提高预测准确度。With the vigorous development of intelligent transportation systems（ITS）,traffic control and traffic guidance have become a hot research issue.Real-time and accurate short-term forecasting of traffic flow is critical to traffic control and guidance,and the accuracy of forecasting directly influences the effect of traffic control and guidance.In order to improve forecast accuracy,this paper proposes a traffic flow forecasting method based on combination model,in which the historical trend model and the multiple regression model are weightedly combined to establish a forecasting model.Moreover,for the forecasting values of better accuracy,a larger weight will be given.By analyzing the forecasting results of Shanghai′s traffic flow in 2009,it is shown that the proposed method can improve the accuracy of forecast.

关 键 词：交通流量预测 组合模型 历史趋势模型 多元回归模型 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]