Effective Short-term Forecasting of Wind Farms Power
Main Article Content
Abstract
Forecasting a specific wind farm’s (WF) generation capacity within a 24 hour perspective requires
both a reliable forecast of wind, as well as supporting tools. This tool is a dedicated model of
wind farm power. This model should include not only general rules of wind to mechanical energy
conversion, but also the farm’s specific features. There are many factors that influence a farm’s
generation capacity, and any forecast of it, even with an accurate weather forecast, carries error.
This paper presents analytical, statistical, and neuron models of wind farm power. The study
is based on data from a real wind farm. Most attention is paid to the neuron models, due to
a neuron network’s capability to restore farm-specific details. The research aims to answer the
headline question: whether and to what extent a wind farm’s power can be forecast short-term?
Article Details
References
Norma EN 61400-12-1:2006, Wind
Turbines, part 12.1: Power performance
measurements of electricity producing
wind turbines.
Petersen E.L. i in., Wind Power
Meteorology, publikacja Risø National
Laboratory, Roskilde, Denmark 1997.
Durajczyk M., Kołakowski R., Model
neuronowy mocy farmy wiatrowej
na potrzeby prognozowania mocy, praca
dyplomowa, WEiA Politechnika Gdańska,
Giebel G. i in., The state of the art in short
term prediction of wind power, Anemosplus
project report, 2011 [online], www.
windpowerpredictions.com.
Madsen H., Nielsen H., Nielsen T.S., A tool
for predicting the wind power production
of off-shore wind plants [online], www.
enfor.dk.
Wang X., Guo P., Huang X., A review of
wind power forecasting models, The Proc.
of Int. Conf. on Smart Grid and Clean
Energy Technologies, Ener. Proc. 2011,
Vol. 12, s. 770–778.
Bogalecka E., Rubanowicz T., Neuronowy
model mocy farmy wiatrowej, Mechanik
, nr 7, s. 579–586.