| Summary: | The potential for solar power is available in Indonesia because it is located on the equator, with good sunshine all year round. The Indonesian government is currently actively developing a solar power plant while still looking at the consequences of development, especially on the surrounding environment. It is necessary to pay attention so that it does not disturb the surrounding environment, which can also cause climate change. The city of Medan is one of the largest cities in Indonesia, which has direct exposure to sunlight which is quite promising for predicting solar power plants in the future. Solar energy generation in the last decade has continued to improve and develop in solar power predictions in a short period. Integration of solar power sources without accurate power predictions can hinder network operations and the use of renewable generation sources. To solve this problem, virtual power plant modeling can solve as a solution that manages to minimize the prediction error. This research studies methods that can efficiently generate significant daily Photovoltaic (PV) predictions at the locations studied using available data from the Meteorology, Climatology, and Geophysics Agency (MCGA). The approach of the two models based on RMSE (root mean square error) and MAE (Mean Absolute Error), can be virtual power plant modeling can solve it as a management solution to be minimal in its prediction error. This research studies methods that can efficiently generate significant daily Photovoltaic (PV) predictions at the locations studied using available data from the Meteorology, Climatology, and Geophysics Agency (MCGA). The approach of the two models based on RMSE (root mean square error) and MAE (Mean Absolute Error), can be virtual power plant modeling can solve it as a management solution to be minimal in its prediction error. This research studies methods that can efficiently generate significant daily Photovoltaic (PV) predictions at the locations studied using available data from the Meteorology, Climatology, and Geophysics Agency (MCGA). The approach of the two models based on RMSE (root mean square error) and MAE (Mean Absolute Error), can be taking into account the uncertainty of predictions that can provide additional information from virtual power plants. Verified prediction strategy performance against PV module power output and a set based on geographic meteorological station data have been used to simulate Virtual Power Plants (VPP). The power forecasting prediction refers to the LSTM (Long Short-Term Memory) network and gives an error close to that of other learning methods, based on the RMS characteristic of 4.19 W/m2 under lead time with different launch times. The application of the VPP model can reduce the global error by about 12.37% with the model RMSE, and shows great potential.
|
|---|