Short-term photovoltaic power forecasting method based on irradiance correction and error forecasting

Accurate photovoltaic (PV) power forecasting is of great significance for safe and stable operation for PV power plant and reasonable dispatching of power grids, and it is also a fundamental technology to ensure the high ratio of PV power generation access to the power grid, but its forecasting error cannot meet the actual requirement. Based on data analysis from a 10 kW distributed PV power plant and a 60 MW large-scale power plant, this study shows the PV power short-term forecasting error mainly comes from the numerical weather prediction (NWP) and forecasting process. To improve the forecasting performance, a short-term PV power forecasting method based on irradiance correction and error forecasting is proposed. First, the measured irradiance is used to correct the irradiance in the NWP. Then, the particle swarm optimization (PSO) algorithm is used to optimize the forecasting model. Finally, an error forecasting model is introduced to correct the forecasting result further. It is proved that the proposed method can effectively improve the short-term forecasting accuracy through verification with an actual power plant. Taking the 6 steps correction as an example, the NWP correction can reduce RMSE(1) by 3.0%, the model optimization can reduce RMSE(2) by 0.4%, and the error correction can reduce RMSE by 0.4%.