基于聚类分析的非参数回归短时交通流预测方法

Non-parametric Regression for Short-term Traffic Flow Forecasting Based on Cluster Analysis

大部分非参数回归预测算法并不对交通流历史数据进行区分,而是将全部历史流量数据建立模式库进行分析。基于交通流的现实特征,提出基于聚类分析的非参数回归短时交通流预测方法,首先根据流量分布特点运用聚类分析将其分类成不同的流量模式,然后选择匹配待预测时刻的流量模式作为样本数据库运用非参数回归进行预测。实例计算结果表明,其预测精度优于传统非参数回归方法。

The majority of the non-parametric regression prediction algorithms do not distinguish among the historical traffic flow data by putting all the data into one model database for analysis.In this way,all the historical flow data are regarded as a time series,and the differences among the traffic flow distribution on different dates are neglected.On the basis of the characteristics of traffic flow,this paper puts forward a non-parametric regression method for short-term traffic flow forecasting based on cluster analysis.This method first classifies traffic flow into different traffic patterns according to the characteristics of flow distribution using cluster analysis.Then,it chooses the database to match the flow of the moment to be predicted as the sample database and applies non-parametric regression into prediction.The example shows that the prediction accuracy is higher than traditional non-parametric regression methods.