Résumé

Wind power is generated by wind turbines. To assess the wind power potential of a particular site, wind data is collected from anemometers during a short period of time (e.g. one year) and the wind turbine engineers use long-term reference datasets to predict wind speed over a longer time period. Some of these datasets represent real data, collected far from the site and others, simulated data from a mesoscale model, specifically tailored for the site. We will assess the usefulness of mesoscale data in wind speed prediction using cross-validation and will use block bootstrap to assess the accuracy of the ten-year wind speed average prediction.

Janie Coulombe