Support vector machine and Gaussian process regression based modeling for photovoltaic power prediction

Grid integration of Solar energy positively affects energy market due to inexhaustible fuel supply and virtually zero emissions. However, inexhaustible renewable fuel supply is punctuated by the problem of intermittency. Intermittency exacerbates the problem of grid operators to bridge the supply and demand gap. Thus, precise output power forecast of grid interfaced Photovoltaic (PV) systems is required for economic dispatch, market regulation, and stable grid operation. This study compares the statistical models of Gaussian Process Regression (GPR) and Support Vector Machine (SVM) for solar power prediction. The models are trained to predict PV system output power against the backdrop of data recorded for Abbottabad City, Pakistan. Both the models have been trained, validated, and compared with each other for varying irradiance and temperature settings. The results depicted that SVM based modeling excel in solar power prediction with Root Mean Square Error (RMSE) lower than GPR based modeling technique. Performance evaluation of models is conducted with error metrics of RMSE, Mean Absolute Error (MAE), and Mean Square Error (MSE). Moreover, prediction quality is qualified based on residual analysis benchmarked by load line analysis of PV system in Simulink.