摘要
为更好地对道路客运量未来发展趋势进行预测,建立更加精确的预测模型,在分析主要预测方法的基础上,提出一种基于规划求解的组合预测模型。基于灰色模型、一元回归和指数平滑三种预测方法,建立了以历年预测值加权之和与实际值的差值的绝对值之和最小为目标函数,以权重系数非负和权重系数之和为1的规划求解模型。在权重计算过程中,目标函数值随着迭代次数的增加逐渐减少,通过对目标函数值的变化值进行观测,当目标函数的变化值出现拐点时,定义了组合权重迭代次数的确定方法。选取更具有代表意义的"百城百站"旅客发送量为基础数据,建立了道路旅客运输客运量组合预测模型。在规划求解过程中利用Excel中的"规划求解"功能。试验结果表明:随着迭代次数的增加,目标函数变化值逐渐减小,当迭代次数为7时,目标函数变化值出现拐点,以此确定了迭代次数;传统3种预测方法的绝对误差分别是1.26,0.48和2.98,基于规划求解的组合预测模型的绝对误差是0.12,预测精度更高、误差更小,并且该组合预测模型操作方便,可减少单个模型预测的不确定性,可根据上述模型对未来道路旅客发送量进行预测。
In order to better predict the future development trend of road passenger transport and establish a more accurate prediction model, a combined forecasting model based on planning solving is presented after analysing the main prediction method. Based on gray model, simple regression and exponential smoothing, the planning solution model is established with the objective function as the minimal sum of the absolute values of the difference between the weighted sum of the predicted values and the real values over the years, and with the sum of weighting factors is 1 and the weighting factors are positive number as the restrictions. In the process of weight calculation, the objective function values decreases gradually as the number of iterations increases. By observing the change of the objective function value, when the target function appears inflection point, the method of determining the number of iterations of combination weights is given. By choosing the more representative "Hundred Cities and Hundred Stations" road passenger transport volume as the basic data, the combined forecasting model is established, and the "planning solution" function in Excel is used in the planning process. The test result shows that ( 1 ) the change of the objective function is gradually decreasing as the number of iterations increases, there is an inflection point when the number of iterations is 7, thus the number of iterations is determined ; (2) the absolute errors of the 3 traditional prediction methods is 1.26, 0. 48 and 2.98 respectively, while the absolute error of the combined forecasting model based on planning solving is 0. 12 with more accuracy and fewer errors, the combined forecasting model could reduce the uncertainty of individual forecasting model and operate easily, it could be used in the road passenger transport volume forecast.
出处
《公路交通科技》
CAS
CSCD
北大核心
2017年第12期103-107,114,共6页
Journal of Highway and Transportation Research and Development
基金
交通运输部建设科技项目(2015 318 J36 110)
交通运输战略规划政策研究项目(2016-1-4)
中央级公益性科研院所基本科研业务费项目(2016 6110)
关键词
交通工程
预测模型
组合预测
客运量
权重确定
transport economics
forecasting model
combination forecasting
passenger transport volume
weight determination