Improving Wind Power Forecasts by considering the Spatio-Temporal structure of Wind Power Forecast Errors

With the ongoing increase in installed wind power production and due to the variability of this resource, forecasting the production is becoming a critical process. So far, forecasts have usually been generated individually for a given site of interest (either a wind farm or a group of wind farms). However, it is intuitively expected that owing to the inertia of meteorological forecasting systems, a forecast error made at a given point in space and time will be related to forecast errors at other points in space in the following period. The existence of such underlying correlation patterns is demonstrated and analyzed, considering a simple case-study of western Denmark. Wind direction is shown to play a crucial role, while the effect of wind speed is more complex. Models permitting capture of the interdependence structure of wind power forecast errors are proposed, and their efficiency discussed. Even though focus is on one-hour-ahead forecast errors and on western Denmark only, results show significant improvements and motivates a generalization to further look-ahead times, larger areas, or more complex topographies