Prieto-Herráez, DiegoMartínez-Lastras, SarayFrías Paredes, LauraAsensio, María IsabelGonzález-Aguilera, Diego2024-11-182024-05-31Prieto-Herráez, D., Martínez-Lastras, S., Frías-Paredes, L., Asensio, M. I., González-Aguilera, D. (2024). EOLO, a wind energy forecaster based on public information and automatic learning for the Spanish Electricity Markets. Measurement: Journal of the International Measurement Confederation, 231, 1-17. https://doi.org/10.1016/j.measurement.2024.1145570263-224110.1016/j.measurement.2024.114557https://academica-e.unavarra.es/handle/2454/52523For the correct operation of the electricity system, producers must provide an estimate of the energy they are going to discharge into the system, and they must face financial penalties if their forecasts are wrong. This is especially difficult in the case of renewable energies, and in particular wind energy because of its variability and intermittency. The tool proposed allows, in a first step, to improve the prediction of wind energy to be produced and, in a second step, to optimize the offer to be presented to the electricity market, so that the overall economic performance can be improved. This tool is based on the use of public information and automatic learning and has been evaluated on a set of 30 wind farms in Spain, using their historical production data. The results indicate improvements in both the accuracy of the energy estimation and the profit obtained from the energy sold.application/pdfeng© 2024 Elsevier Ltd. This manuscript version is made available under the CC-BY-NC-ND 4.0Automatic learningElectricity marketsFeature selectionPublic informationRenewable energyWind power forecastinginfo:eu-repo/semantics/article2024-11-18info:eu-repo/semantics/embargoedAccess