交通流短时预测的相关性研究

Relation Analysis for Road Traffic Flow Short-term Forecasting

交通流短时预测中,多个检测点的道路交通状态间的时空联系是客观存在的,但以往研究中通常根据经验假定,很少定量研究其相关性.本文引进了多元统计分析中的多维标度法对多断面时间序列的相关性进行定量分析,为合理进行多断面短时交通流预测研究提供基础.首先,根据道路网多个断面各自的时间序列利用相关系数方法得到两两之间相关性的相关系数矩阵,然后,利用多维标度法将道路网中多个断面交通流的相关程度映射到一张二维拟合构图中,以拟合构图中代表各个断面的点之间的欧几里得距离来体现断面之间的相关强度,从而判别断面之间相关性强弱,确定道路网多断面短时交通流预测时相关性分组.最后,根据相关性分析结果进行多断面交通流预测及效果比较,验证了方法的可行性和有效性.

The relation of traffic state data and detective devices exists objectively, but previous attempts to perform short-time forecast are lack of quantitative analysis. Muhidimensional scaling from theory of multivariate statistical analysis is proposed to describe the relation for road traffic flow short-term forecast in this paper. It was used to associate the relevance of traffic flows data from road cross-sections with a two dimensional chart of derived stimulus configuration. According to the chart, the strong or weak of the relativity of each road cross-section can be obtained, which supplied research range, object, and base of data analysis to short-term traffic flow forecasting models and methods with consideration of the variety of time and space of traffic flow. The proposed method is verified to be reasonable and effective.