A Novel Deep Learning-Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid

Table 8

Comparison with the literature on PV power generation forecasting.

Model	MSE	RMSE	MAE	MAPE (%)	R	ANOVA	Authors
RNN, LSTM	15.26	3.90	7.85	4.59	0.98788	—	[66]
CNN, LSTM	13.31	3.64	6.52	3.22	0.98955	—	[67]
STFFNN	12.86	3.58	5.75	3.07	0.98996	—	[68]
VMD, LSTM, PSO-DBN	10.47	3.23	4.29	2.38	0.99287	—	[69]
MLP, SVM, LGBM, KNN, RF, XGBoost	—	—	4.05	2.27	0.99452	—	[70]
LSTM, SVM, GBT, DT, ANN, GLM	6.58	2.56	2.85	1.47	0.99656	—	[71]
ANN-SVM-PSO	14.97	3.86	3.32	0.867	0.99684	—	[72]
RF, DNN, LSTM	7.89	2.81	2.59	0.758	0.99699	—	[73]
Lasso, MLP, SVR, SVM, RF, RF, XGB, GB	—	—	1.58	0.82	0.99705	—	[74]
MLP-LSTM	5.86	2.42	1.23	0.25	0.99716	0.274	Writers
MLP-LSTM-GA	1.25	1.11	0.58	0.04	0.99999	0.196	Writers