SKIPP’D: A SKy Images and Photovoltaic Power Generation Dataset for short-term solar forecasting

Large-scale integration of photovoltaics (PV) into electricity grids is challenged by the intermittent nature solar power. Sky-image-based forecasting using deep learning has been recognized as a promising approach to predicting short-term fluctuations. However, there are few publicly available standardized benchmark datasets for image-based forecasting, which limits comparison different models and exploration methods. To fill these gaps, we introduce SKIPP’D—a SKy Images Photovoltaic Power Generation Dataset. The dataset contains three years (2017–2019) quality-controlled down-sampled sky images PV power generation data that ready-to-use learning. In addition, support flexibility in research, provide high resolution, frequency well concurrent video footage. We also include code base containing processing scripts baseline model implementations researchers reproduce our previous work accelerate their research forecasting.