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

Table 6

Comparison with relevant recent works of the literature.

Model	MSE	RMSE	MAE	MAPE (%)	R	ANOVA	Authors
Deep reservoir architecture	2.15	1.466	5.42	0.64	0.8896	—	[55]
GC-LSTM	3.66	1.913	7.85	2.36	0.8795	—	[56]
ADDPG-AEFRIM	2.04	1.428	2.58	0.94	0.8996	—	[57]
TgDLF, EnLSTM	1.58	1.241	1.33	0.89	0.9654	—	[58]
CNN, DNN, GRU-FCL, LSTM-FCL, Bi-GRU-FCL	0.06	0.244	0.48	0.75	0.9788	—	[59]
ANFIS, grey, PSO	0.04	0.201	0.22	0.6	0.9969	—	[41]
k-means, QRLSTM, KDE	0.012	0.11	0.15	0.47	0.9979	—	[60]
CNN-LSTM	—	—	0.04	0.38	0.9987	—	[61]
TCN-DNN	0.0035	0.059	—	—	0.9995	—	[62]
MLP-LSTM	0.0023	0.047	0.01	0.1	0.9998	0.214	Writers
MLP-LSTM-GA	0.00012	0.002	0.005	0.014	0.9999	0.163	Writers