Wind Power Forecast

[esnaque]

Hi all,

I have the following problem. Imagine we're at time t, and we have a forecast model who predicts the power production of a wind farm for the next hour (i.e at t+1). At time t we already know the real value of power production at t-2, t-3, t-4, ...(not in t-1!), hence the previous errors. This procedure is repeated hourly. Do you know some kind of control system able to improve the predictions knowing that previous information?

Thanks!

 

[xnuke]

You're talking about an adaptive time series predictor. The predictor model needs to be parameterized, and the parameters are then updated by a controller according to some control law. A common method is to design the controller so that its outputs, the parameters for your predictor, minimize the sum of weighted squared errors of a certain number of data points in your data history. This is easier said than done.

xnuke
"Live and act within the limit of your knowledge and keep expanding it to the limit of your life." Ayn Rand, Atlas Shrugged.
Please see FAQ731-376 for tips on how to make the best use of Eng-Tips.

 

[PNachtwey]

I wouldn't bother trying to predict the wind speed when someone else has already done it and can do it much better than you can.
Do a search for "weather report wind speed"
Find out if the service has an app or program that lets you get the future wind speeds and directions.

Peter Nachtwey
Delta Computer Systems

http://www.deltamotion.com

http://forum.deltamotion.com/