Design of Short-Term Forecasting Model of Distributed Generation Power for Solar Power Generation

摘要： Background/Objectives: For efficient PhotoVoltaic (PV) power generation, computing and information technologies are increasingly used in irradiance forecasting and correction. Today the majority of PV modules are used for grid-connected power generation, so solar generation forecasting that predicts available PV output ahead is essential for integrating PV resources into electricity grids. This paper proposes a short-term solar power forecasting system that employs Neural Network (NN) models to forecast irradiance and PV power. Methods/Statistical Analysis: The proposed system uses the weather observations of a ground weather station, the medium-term weather forecasts of a physical model, and the short-term weather forecasts of the Weather Research and Forecasting (WRF) model as input. To increase prediction accuracy, the proposed system performs forecast corrections and determines the correction coefficients based on the characteristics and temperature of PV modules. The proposed system also analyzes the inclination angle of PV modules to predict PV power outputs. Results: In the correlation analysis of the forecasted and measured irradiance, R2 was over 0.85 for all look-ahead periods, indicating a high correlation between the two data. Conclusion/Application: In the future, the proposed forecasting system for solar power generation resources will be further refined and run in real environments.