Development of Stacked Long Short-Term Memory Neural Networks with Numerical Solutions for Wind Velocity Predictions

Table 2

Average performance measures of absolute error terms (MAE and RMSE) and relative error terms (MAPE and RMSPE) for 1–6 h predictions.

Station	Measure	MLP	DRNN	Stacked LSTM
Taipei	MAE (m/s)	1.241	1.070	0.928
	RMSE (m/s)	1.666	1.439	1.228
	MAPE	0.730	0.599	0.560
	RMSPE	2.129	1.764	1.593
Yilan	MAE (m/s)	1.863	1.714	1.528
	RMSE (m/s)	2.680	2.489	2.185
	MAPE	1.151	0.974	0.927
	RMSPE	3.643	3.030	2.847