灰色模型GM(1,1)中积分参数的确定

Determination of Integral Parameter in GM(1,1)

灰色模型GM(1,1)中主要有3个参数,其中积分参数直接影响着灰色模型的短期预报,对其求解需要一个约束条件。给出了灰色模型中基于一次累加序列约束和基于原始序列约束条件下积分参数的确定方法,并通过实际算例进行了比较。结果表明,总体而言,不同准则下获取的c值对短期预报结果相差较小,实际应用中可以采用最常用、最简单的过第一点准则来确定。

There are three main parameters in GM （ 1,1 ）. One of them is the integral parameter. It directly affects the shortterm forecasting. It requires a constraint to get the value of the integral parameter. Based on a cumulative sequence constraint and the original sequence constraint this paper presents the integral parameter determination method. Practical examples showed that the difference between the results of the short-term prediction under the different criterions is small, and that the integral parameter can be determined in practice through the first point.