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

Table 2

Forecasting errors of different models.

Models	MAPE	RMSE
LSTNet	7.341	416.66
RF-LSTNet	5.161	316.09
GRA-LSTNet	6.964	413.23
PCA-LSTNet	6.771	359.57
CNN-LSTM	8.117	465.14
CNN-BiLSTM	7.710	441.92
CNN-LSTM-attention	7.440	408.64
CNN-BiLSTM-attention	8.277	444.37

Source: author.