ENFOR

Wind Power Prediction Tool (WPPT)

The Wind Power Prediction Tool or WPPT can be used for generating short-term (say up to 120 hour) predictions of the wind power production. The system is very flexible and it can be configured to cover the total wind power (eg. for Denmark), the total wind power in a region (like the Northern part of Jutland), or a single wind farm (like the Horns Rev off-shore wind farm).

History

The development of WPPT started in 1992, and the system has been in used by a number of TSO's since 1996.

Input to WPPT

WPPT is build on artificial intelligence, and hence the system automatically calibrates to the observed situation. In the minimal setup the system requires online measurements of the wind power. However depending on the configuration the following data is taking into account:

  • Online measurements of wind power.
  • Aggregated energy readings form all (or nearly all) turbines in a region (for regional forecasting).
  • Meteorological forecasts of wind speed and direction covering wind farms and regions.
  • Other measurements or predictions like local wind speed, stability, number of active turbines, etc. can be used if available.

The input can be given in the standard European format as specified by the Anemos project.

Output from WPPT

WPPT typically generates predictions of the wind power up to around 120 hours ahead. The system also provides reliable estimates of the uncertainty of the predictions - which is very important for optimal scheduling or trading.

Methods used in WPPT

WPPT is based on advanced non-linear statistical models. The set of models includes a semi-parametric power curve model for wind farms taking into account both wind speed and direction, and dynamical predictions models taking describing the dynamics of the wind power and any diurnal variation, etc.

The models are self calibrating and adaptive. Hence they automatically account for

  • Changes in the number of turbines and their characteristics
  • Changes in surroundings and non-explicit modelled characteristics like roughness and dirty blasdes.
  • Changes in the NWP models.

For a more regious description of the models and methods we refer to our technical papers or the following PDF-presentation.

WPPT Configuration Examples

Example no. 1 - Large TSO

Example no. 1

This configuration of WPPT is used by a large TSO. The following facts characterizes the installation:

  • A large number of wind farms and stand-alone wind turbines.
  • Frequent changes in the number of wind turbines and the layout of wind farms.
  • Offline production data with a resolution of 15 min. is available for more that 99% of the wind turbines in the area.
  • No online data enters the model.

Example no. 2 - Large Wind Farm Owner

Example no. 2

This configuration is used by a large wind farm owner in Denmark, and the installation has the following characteristics:

  • A reasonable (less than 20) number of wind farms
  • Online power production data is available for a number of wind farms.
  • Offline production data with a resolution of 15 min. is available for almost all wind turbines. These offline data is released with a delay of 3-5 weeks.

Example no. 3 - Very Large TSO

Example no. 3

This configuration of WPPT is used by a very large TSO. The facts of the installation are the following:

  • A large number of wind farms and stand-alone wind turbines.
  • Frequent changes in the wind turbine population.
  • Offline production data is available for more than 99% of the wind turbines in the area.
  • Online data for a large number of wind farms is available. The number of online wind farms increases quite frequently.

E-mail: info ¤ enfor . eu | Phone: (+45) 45 350 350