Evelina Kotwa och Julija Vlasova presenterar sitt examensarbete

Spatio-temporal modeling of short-term wind power prediction errors

Abstract

The quality of the wind power prediction tools is very important, and
a reliable estimate of the uncertainty of the forecast is known to be
essential. Today the forecasts of wind power generation are provided
without a proper consideration to the spatio-temporal dependencies
observed in the wind power generation field. Aiming at improving
online short-term wind power predictions, the study focuses on
evaluating spatio-temporal correlation of the errors obtained from
WPPT (Wind Power Prediction Tool), which is one of the leading
systems. The analysis is based on the weather forecast information and
wind power prediction errors obtained for the territory of Denmark in
the year 2004.

 
For improving wind power prediction several statistical models were
used: Linear, Threshold, Varying-coefficient and Conditional
parametric. The introduction to the models, estimation procedures,
application details together with the obtained results are presented
and carefully discussed in the paper