Forecasting of Energy Production for Photovoltaic Systems Based on ARIMA and ANN Advanced Models

Table 1

The accuracy of the ARIMA model.

Statistical fitting	Average
	0.811
RMSE	18,367.868
MAPE	199.410
MaxAPE	3,838.473
MAE	10,359.011
MaxAE	54,998.512

represents how much of the variation of the dependent variable is determined by the estimated quantity, RMSE (Root Mean Squared Error) represents the difference between the predicted values and the observed ones, MAPE (Mean Absolute Percentage Error) represents the accuracy of the forecasted model, and MaxAPE (Maximum Absolute Percentage Error) is the largest predicted error, expressed as a percentage. This error is useful to determine the efficiency of the forecast. MAE (Mean Absolute Error) represents the degree of variation of the measured data compared to the forecast. MaxAE (Maximum Absolute Error) is the largest error in the forecast, like MaxAPE, also useful in determining the efficiency of the forecast at the point with maximum error.