With high Photovoltaics (PV) penetration, sudden changes in solar irradiance can trigger unacceptable voltage and frequency deviations. These can lead to grid instability and significant mismatches between announced and delivered electricity prices. The ability to forecast solar irradiance in the near time (nowcasting) can help grid operators ensure system reliability while providing an economic efficient dispatch of energy resources. A team from Qatar Environment and Energy Research Institute including Drs. Antonio Sanfilippo, Luis Martin-Pomares, Nassma Mohandes, Daniel Perez-Astudillo, and Dunia Bachour have developed a solar nowcasting algorithm that uses supervised classification of forecasting evaluation results from diverse stochastic models to select the best predictions, according to their expected superiority in terms of lower error rate. In an experimental study with solar irradiance data collected in Qatar and four competing models, the approach has shown improvements of 44.92% over the baseline model, and 19.06% over the best performing model. This study has appeared in Solar Energy 125 (2016) 77–85  and was filed in June 2015 as a provisional patent application.