WindSim (Norway)

This research was supported by a grant from The Norwegian Research Council, project number 271080. We acknowledge Botnia-Atlantica, an EU-programme financing cross border cooperation projects in Sweden, Finland and Norway, for their support of this work through the WindCoE project. We would like to thank the High Performance Computing Center North (HPC2N) for providing the computer resources needed to perform the numerical experiments presented in this paper. We would also like to thank the two anonymous reviewers for their useful comments.

The ANN-based mesoscale-microscale coupling model forecasts wind speed and wind direction with high accuracy for wind parks located in complex terrain onshore, yet some weather regimes remains unresolved and forecast of such events failing. The model’s generalization improved significantly when categorization information added as an input. The improved model is able to resolve extreme events and converged faster with significantly smaller number of hidden neurons. The new model performed equally good on test data sets from both onshore and offshore wind park sites.