Predicting Short-Term Electricity Demand by Combining the Advantages of ARMA and XGBoost in Fog Computing Environment

Table 8

MAE and Score values of models with or without user clustering.

Model without user clustering	ARMA	XGBoost	GBDT	Random forest	XGB-ARMA
MAE	188274.29	191378.12	257591.77	277195.20	194278.54
Score	0.8652	0.8678	0.8258	0.8158	0.8616
Model with user clustering	ARMA	XGBoost	GBDT	Random forest	XGB-ARMA
MAE	145605.80	245134.24	176533.17	187297.21	124609.62
Score	0.8954	0.8318	0.8755	0.8674	0.9085