基于残差自回归方法的短期区域用电量预测

Short-term Regional Electricity Demand Forecasting Based on Residual Autoregression

基于我国区域用电量数据展开了短期用电量预测研究,采用了基于残差自回归方法的时间序列预测模型,有效提高了短期区域用电量预测准确性。相比于传统的时间序列模型(ARIMA模型和Holt-Winters模型),基于残差自回归方法的时间序列预测模型的MAPE值和RMSE值均最小,并在两个不同的数据集上表现平稳。

This paper applies time series model based on residual autoregression to regional electricity demand data in China which effectively improves the accuracy of short-term regional electricity demand forecasting.Compared with the traditional time series models(the ARIMA model and the Holt-Winters model),the model based on residual autoregression has smaller MAPE and RMSE values and is stable on two different data sets.