|
| Author | Year | Problem | Data set | Techniques | Results | Limit |
|
| [63] | 2021 | Short-term solar PV power generation forecasting | Climate data in US | Markov model and genetic algorithm | MAE = 23.52; R = 0.952 | Low prediction |
| [64] | 2021 | PV power generation forecasting | Climate data in Australia | Multidirectional search optimization algorithm | MAE = 42.58; R = 0.935 | Abnormal climate conditions |
| [65] | 2022 | Solar PV energy generation | Climate data over 3 years in California | ANN, LSTM | MSE = 15.47; R = 0.962 | Complex structure |
| [66] | 2022 | Forecasting of PV generation | 03 solar fields in US over 4 years | RNN, LSTM | MSE = 15.26; RMSE = 3.90; MAE = 7.85; MAPE = 4.59%; R = 0.98788 | Model complexity |
| [67] | 2022 | Short-term solar generation forecasting | Climate data in Abu Dhabi | CNN, LSTM | MSE = 13.31; RMSE = 3.64; MAE = 6.52; MAPE = 3.22; R = 0.98955 | High simulation time |
| [68] | 2022 | PV power generation forecasting | Climate data in Vitoria–Gasteiz, Spain | STFFNN | MSE = 12.86; RMSE = 3.58; MAE = 5.75; MAPE = 3.07; R = 0.98996 | Require features adjustments |
| [69] | 2022 | Short-term wind power forecasting | Wind field in Dingbian, Shaanxi, China | VMD, LSTM, PSO-DBN | MSE = 10.47; RMSE = 3.23; MAE = 4.29; MAPE = 2.38; R = 0.99287 | Increase computation complexity |
| [70] | 2022 | PV power generation forecasting | Climate data in US | MLP, SVM, LGBM, KNN, RF, XGBoost | MAE = 4.05; MAPE = 2.27; R = 0.99452 | Aggregation complexity |
| [71] | 2022 | Short-term PV power generation forecasting | Climate data in Australia | LSTM, SVM, GBT, DT, ANN, GLM | MSE = 6.58; RMSE = 2.56; MAE = 2.85; MAPE = 1.47; R = 0.99656 | Hybridization complexity |
| [72] | 2022 | Long-term PV power generation forecasting | Climate data of Douala, Cameroon | ANN-SVM-PSO | MSE = 14.97; RMSE = 3.86; MAE = 3.32; MAPE = 0.867; R = 0.99684 | Convergence speed can be affected |
| [73] | 2023 | Short-term PV power generation forecasting | Climate data in Berlin, Germany | RF, DNN, LSTM | MSE = 7.89; RMSE = 2.81; MAE = 2.59; MAPE = 0.758; R = 0.99699 | Comparison with existing model is not evaluated |
| [74] | 2023 | PV power generation forecasting | Climate data in Utrecht, Netherlands | Lasso, MLP, SVR, SVM, RF, RF, XGB, GB | MAE = 1.58; MAPE = 0.82; R = 0.99705 | Model is not efficiently elaborated and exploited |
|
