Short-term Solar Power Forecasting Using XGBoost with Numerical Weather Prediction

In recent years, solar photovoltaic (PV) generation becomes one of the most relevant energies. However, the intermittent characteristics of solar generation create significant problems to power system operations. To overcome this problem, many solar power forecasting techniques have been developed, and different forecasting horizons require different methodologies. For a short-term prediction, forecasting horizons generally require numerical weather prediction models (NWP) that provide an important estimation of weather variables such as solar irradiance, temperature, wind speed, rainfall, air pressure, etc. This research proposes a machine learning model based on Kernel Principal Component Analysis (PCA)- XGBoost to improve the accuracy of one-hour-ahead solar power forecasts. The model considered the deterministic Weather Research and Forecasting (WRFD) provided by Taiwan Central Weather Bureau (CWB). Furthermore, a XGBoost model was built on an ensemble of decision trees, providing important information and appropriate results in the forecasting process.