基于客流n日均量的地铁客流量的时间序列分析

Time-series Analysis for Metro Passenger Flow Based on N Days Average Volume

以上海城市轨道交通系统日客流总量为研究对象,构造客流n日均量作为时间序列数据,使用日客流量与客流7日均量的相对变化率进行平时客流特征分析。以此为基础,建立ARIMA预测模型。通过客流7日均量分别进行系统日客流量的迭代预测和递推预测。实证检验,递推方法的相对误差基本小于迭代方法的相对误差,平时系统日客流量预测的相对误差基本在2%左右。

Taking daily data of Shanghai metro passenger flow as research object, an index of ＂n-day＇ average passenger flow volume is introduced to construct time-series data, the change rate of daily volume against ＇ 7-day＂ average volume is used for analyzing the characteristics of daily passenger flow. On this basis, ARIMA forecast model is constructed. The ＇ 7-day＇ average volumes is adopted by iterated prediction model and recursive prediction model to forecast daily passenger flow volume. The relative error of recursive prediction model is less than that of iterated prediction model by empirical test .The forecast error is within 2% for daily flow.