Short-Term Wind and Solar Power Prediction Based on Feature Selection and Improved Long- and Short-Term Time-Series Networks

Table 4

Forecasting errors of different models.

Models	MAPE	RMSE
LSTNet	57.806	2.427
RF-LSTNet	50.340	2.335
GRA-LSTNet	42.767	2.468
PCA-LSTNet	43.145	2.336
CNN-LSTM	55.364	2.812
CNN-BiLSTM	42.627	2.816
CNN-LSTM-attention	50.722	2.610
CNN-BiLSTM-attention	45.375	2.960

Source: author.