Publication library

M., David, J., Alonso-Montesinos, J., Le Gal La Salle, P., Lauret (2023). Probabilistic Solar Forecasts as a Binary Event Using a Sky Camera. Energies, 16, 7125.


With the fast increase of solar energy plants, a high-quality short-term forecast is required to smoothly integrate their production in the electricity grids. Usually, forecasting systems predict the future solar energy as a continuous variable. But for particular applications, such as concentrated solar plants with tracking devices, the operator needs to anticipate the achievement of a solar irradiance threshold to start or stop their system. In this case, binary forecasts are more relevant. Moreover, while most forecasting systems are deterministic, the probabilistic approach provides additional information about their inherent uncertainty that is essential for decision-making. The objective of this work is to propose a methodology to generate probabilistic solar forecasts as a binary event for very short-term horizons between 1 and 30 min. Among the various techniques developed to predict the solar potential for the next few minutes, sky imagery is one of the most promising. Therefore, we propose in this work to combine a state-of-the-art model based on a sky camera and a discrete choice model to predict the probability of an irradiance threshold suitable for plant operators. Two well-known parametric discrete choice models, logit and probit models, and a machine learning technique, random forest, were tested to post-process the deterministic forecast derived from sky images. All three models significantly improve the quality of the original deterministic forecast. However, random forest gives the best results and especially provides reliable probability predictions.


M., David, M.N.  Andriamandroso, M. N., P., Behrensdorff Poulsen, J., Castaing-Lasvignottes, N., Cutululis, K., Das, C., Durif-Aboukali, J., Francou, P., Lauret, J., Le Gal La Salle, E., Lorenz, O., Marc, D., Melgar and S., Spataru (2023). A set of study cases for the massive integration of solar renewables in non-interconnected areas. SWC 2023: ISES Solar World Congress 2023, New-Delhi, 30 Oct. – 4 Nov.


The massive integration of solar renewable energies is challenging in non-interconnected areas such as remote islands or isolated regions. Indeed, their power grid, which cannot rely on the support of larger electricity networks, is more vulnerable to the inherent variability of the solar resource and grid failures, such as sudden breakdown of production units or transmission lines. The TwInSolar project, funded by the European Commission, aims to provide support and solutions to overcome the problems faced by island territories not connected to continental electricity grids. As a part of this project, four study cases are presented to the scientific community, each highlighting specific issues observed at different scales on the island of La Reunion. This article aims to provide a detailed description of the four selected systems, the corresponding challenges, and the data available.


Lorenz, E., Tobias Zech, Herzberg, W., Lauret, P., & David, M. (2024). Probabilistische Kurzfristvorhersage der Globalstrahlung mittels Analog Ensemble unter Nutzung von satellitenbasierter Einstrahlung. Fachtagung Energiemeteorologie, Bad Staffelstein, Germany, 24 Jan..


At the German Energy Meteorology Conference in January 2024 Fraunhofer ISE presented on “Probabilistic short-term prediction of global radiation using analog ensembles and satellite-based irradiation” along with an evaluation of these forecasts in a probabilistic benchmark of intra-hour irradiance forecasting, a joint work with University of La Reunion. UR was leading the benchmarking exercise that was carried out in the framework of the IEA PVPS Task 16 “Solar Resource for High Penetration and Large Scale Applications” and received funding from the TwInSolar project. Warning: The presentation is written in German.


Find back all previous editions of the TwInSolar newsletter.

Do not forget to subscribe to receive the next editions!


NEWSLETTER #1 – June 2023