基于混合预测方法的园区月用电量预测

Prediction of Monthly Electricity Consumption in Parks Based on Hybrid Forecasting Method

随着用电量预测的重要性逐步提高,新电改下园区成为电力改革重要试验区,用电量预测开始面向小规模用户的电力需求。为此提出了一种新型电量预测方法,根据用电量数据的时序特性,将时间序列法与指数平滑法两者的设计思想相融合,优化指数平滑模型,引入时间序列模型,建立新的改进模型。结果显示,该方法能提高用电量预测精度,降低发电成本,提高经济效益和社会效益。

With the increasing importance of power consumption prediction,the park has become an important experimental area of power reform under the new power reform,and the power consumption prediction begins to face the power demand of small-scale users.In this paper,a novel electricity forecasting method is proposed.According to the time-series characteristics of electricity consumption data,the design ideas of time series method and exponential smoothing method are combined to optimize the exponential smoothing model.The time series model is introduced to establish a new improved model.The results show that this method can improve the accuracy of power consumption prediction,reduce power generation cost and improve economic and social benefits.