论文部分内容阅读
针对传统的灰色GM(1,1)预测模型在预测公交客运量中存在误差过大的问题,结合公交客运量随机波动的显著特征,通过对残差序列进行再处理,构造新的数据序列,构建GM(1,1)改进预测模型对公交客运量进行预测,并应用于某城市的2条公交线路客运量预测。结果表明:随机波动条件下的GM(1,1)改进预测模型,使用预测序列与残差序列绝对值之和来构造新序列,对新序列进行建模后预测的公交客运量的平均相对误差分别为4.9%和5.3%,明显优于传统GM(1,1)模型预测的公交客运量的平均相对误差7.5%和7.45%;相对误差最大值分别降低了4.68%和2.99%。
Aiming at the problem that the traditional gray GM (1, 1) prediction model has a large error in predicting the bus passenger volume, combined with the salient features of stochastic fluctuations of the bus passenger volume, a new data sequence is constructed by reprocessing the residual sequence, The GM (1,1) improved forecasting model is constructed to predict the passenger volume of buses, and applied to the prediction of the passenger volume of two bus lines in a certain city. The results show that GM (1,1) improved prediction model under stochastic volatility, the new sequence is constructed by using the sum of the prediction sequence and the absolute value of the residual sequence, and the average relative error of the predicted bus transit volume after the new sequence is modeled 4.9% and 5.3% respectively, which is obviously superior to the average relative error 7.5% and 7.45% of the bus passenger traffic predicted by the traditional GM (1,1) model. The relative error decreases by 4.68% and 2.99% respectively.