灰色季节变动指数模型GSVI(1,1)在农村用电量预测中的应用

Application of gray seasonal variation index model GSVI (1,1) in country electricity demand forecasting

季度用电量同时具有增长性和季节波动性的二重趋势,这使得季度用电量的变化呈现出复杂的非线性组合特征。对于这种具有复杂的非线性组合特征的时间序列,直接应用GM(1,1)灰色模型往往精度不高。GM(1,1)灰色模型只能反映时间序列的总体变化趋势,不能很好地反映其季节性波动变化的具体特征。为了提高短期用电量的预测精度,提出了用电量预测的灰色季节变动指数模型——GSVI(1,1)模型。GSVI(1,1)模型是将灰色预测方法与季节变动指数有机结合起来,对复杂的不确定性问题进行求解所建立的模型。算例计算表明,与灰色预测方法相比,GSVI(1,1)模型具有更强的适应性和更高的预测精度,适用于农村用电量预测。

The seasonal electricity demand possesses dual property of increase and seasonal fluctuation simultaneously, so it makes the electricity demand variations to possess complicated non-linear combined character. For such a suite with the character of complicated non-linear combination, the forecasting results by GM （ 1,1 ） model are not satisfied. It reflects the general trend of the time series with high accuracy, while fails to reflect the characteristics of seasonal fluctuation. This paper proposed gray seasonal variation index model GSVI （ 1,1 ） for forecasting of electricity demand in order to improve the forecasting accuracy of short-term electricity demand. The GSVI （ 1,1 ） model is the combination of gray system and seasonal variation index, which can solve the complex uncertain problems. The forecasting results demonstrate that the GSVI （ 1,1 ） model has higher adaptability and forecast precision for country electricity demand forecasting.