Hour-Ahead Power Generating Forecasting of Photovoltaic Plants Using Artificial Neural Networks Days Tuning

PV power generation has an important place in sustainable energy production. The proportion of power generation systems in various countries has increased year by year. However, PV power generation is probabilistic and cannot be accurately predicted, so in recent years it has been an important and popular research topic. This paper proposes an ANN with days tuning to predict the PV power generation of hour-ahead using every ten minutes power generation of three hours ago (a total of 19 data). The neural network has an excellent learning ability, which can easily learn when using days tuning to make prediction results more accurate and yield a slight error. Different forecasting conditions have validated the effectiveness and performance of the proposed idea. The result can trigger an early response to the power system dispatcher and solve PV power generation probabilistic and forecasting.