A Simple Hybrid Model for Short-Term Load Forecasting

Table 1

Forecasting accuracy metrics for 24-hour-ahead forecast of a typical day in each seasons.

Evaluation metric	Model	24-hr-ahead adaptive forecast
		July 14th	April 11th	Jan 15th
RMSE	DEM	1.2591	1.0554	0.8334
	Proposed model	0.2520	0.4756	0.5390
MAPE	DEM	2.9645	2.7862	2.7722
	Proposed model	0.7438	1.3075	1.4501

RMSE: root mean square error; MAPE: mean absolute percentage error;
DEM: double exponential smoothing model.