Short-Term Forecasting of Wake-Induced Fluctuations in Offshore Wind Farms

Abstract

The increasing share of offshore wind energy traded at the spot market requires short term wind direction forecasts to determine wake losses and increased power fluctuations due to multiple wakes in certain wind directions. The information on potential power fluctuations can be used to issue early warnings to grid operators. The current work focuses on analyzing wind speed and power fluctuation time series for a German offshore wind farm. By associating these fluctuations with wind directions, it is observed that the turbines in double or multiple wake situations yield higher fluctuations in wind speed and power compared to the turbines in free flow. The wind direction forecasts of the European Center for Medium-Range Weather Forecast model are compared with Supervisory Control and Data Acquisition (SCADA) data observations of the turbine yaw. The cumulative probability distribution of the difference in forecasted and observed wind directions shows that for a tolerance of +/−10 ∘ , 71% of the observations are correctly forecasted for a lead time of 1 day, which drops to 54% for a lead time of 3 days. The circular continuous rank probability score of the observed wind directions doubles over the lead time of 72 h.

Offshore wind farm wake modelling using deep feed forward neural networks for active yaw control and layout optimisation

“…Yaw optimisation has recently become a key topic, especially in wind farm configurations where the total power output of the plant can be significantly boosted based on the yaw settings of the turbines IOP Publishing doi:10.1088/1742-6596/2151/1/012011 9 [27]. Furthermore, active yaw optimisation is heavily dependent on fast predictions based on live weather forecasting [40], [41] as to take advantage of as much of the incoming wind energy as possible. This study attempts to demonstrate that even when compared to a relatively cheap wake model as the Gaussian, a DNN model can produce very good yaw setting predictions with significant computational cost gains, given that weather conditions are known.…”