Short-Term Solar Power Forecasts Considering Various Weather Variables

Abstract

Solar generation has been developed rapidly in recent years. The output of solar generation systems is affected by various uncertain factors, such as different weather variables. If a large number of solar power systems are connected to the grid, the stability of the power system would be reduced. Therefore, we must pay attentions to solar power forecasting to avoid system instability. One of the important factors that may affect solar power generation is the weather condition, but the meteorological data have considerable uncertainty. Therefore, the main purpose of this paper is to identify important weather variables that affect solar power forecasting. That is, the inputs used in this work to predict solar power generation focuses on numerical weather prediction (NWP) data, which includes meteorological data such as radiation, precipitation, wind speed, and temperature. In addition, this work also considers different time series of input data to explore the relation among data sequences. Finally, this work used various deep learning models for solar power forecasting.