Table 1.
Related works for solar power prediction based on AI tools.
Fig 1.
The LSTM structure.
Table 2.
Weather input data.
Table 3.
Power generation data.
Table 4.
Statistical data for the dataset.
Fig 2.
Data set visualization.
Fig 3.
The variation of DC POWER generation.
Fig 4.
daily power tracing, (a) daily DC power, (b) daily irradiation, (c) daily module temperature and ambient temperature.
Table 5.
Pearson correlation coefficient (ρcc) between the input features ad different outputs.
Fig 5.
The proposed X-LSTM-EO model.
Table 6.
Dataset after aggregation.
Table 7.
Hyper-parameters setting interval.
Fig 6.
The flowchart of the LSTM based EO for power forecasting.
Fig 7.
LSTM architecture.
Fig 8.
Updating concentration.
Table 8.
Experiment parameters for solar power generation forecasting using LSTM.
Table 9.
The experiment test results for solar power forecasting using LSTM.
Table 10.
Training time for solar power forecasting.
Fig 9.
LSTM performance and results before optimization.
Table 11.
EO algorithm parameters.
Fig 10.
EO execution performance.
Fig 11.
EO epochs results.
Fig 12.
The LSTM performance after optimization.
Table 12.
The experiment of test results for LSTM based EO.
Fig 13.
The LSTM performance based on PSO optimizer.
Table 13.
Experiment results of solar power generation forecasting using LSTM based on PSO.
Fig 14.
The comparison of LSTM performance based EO vs. PSO optimizers.
Fig 15.
Experimental models result: LSTM vs LSTM EO vs. LSTM-PSO.
Table 14.
Comparing with other works.
Fig 16.
XAI based LIME algorithm results for solar power generation forecasting model.