Options to Improve the Quality of Wind Generation Output Forecasting with the Use of Available Information as Explanatory Variables

Main Article Content

Rafał Magulski, Tomasz Pakulski

Abstract

Development of wind generation, besides its positive aspects related to the use of renewable energy, is a challenge from the point of view of power systems’ operational security and economy. The uncertain and variable nature of wind generation sources entails the need for the for the TSO to provide adequate reserves of power, necessary to maintain the grid’s stable operation, and the actors involved in the trading of energy from these sources incur additional of balancing unplanned output deviations. The paper presents the results of analyses concerning the options to forecast a selected wind farm’s output exercised by means of different methods of prediction, using a different range of measurement and forecasting data available on the farm and its surroundings. The analyses focused on the evaluation of forecast errors, and selection of input data for forecasting models and assessment of their impact on prediction quality improvement.

Article Details

How to Cite
Rafał Magulski, Tomasz Pakulski. (2015). Options to Improve the Quality of Wind Generation Output Forecasting with the Use of Available Information as Explanatory Variables. Acta Energetica, (02), 24–35. https://doi.org/10.52710/ae.426
Section
Articles

References

Sweeney C., Lynch P., Nolan P., Reducting

errors of wind speed forecasts by an

optimal combination of post-processing

methods, Department of Meteorology

and Climate Centre, Dublin, 2011.

Prondziński Z., Rubanowicz T.,

Zryczałtowana usługa operatora

handlowo-technicznego na potrzeby

rozwoju energetyki wiatrowej w Polsce,

Acta Energetica 2004, nr 19.

Hernandez L., Artificial Neural Network

for Short-Term Load Forecasting

in Distribution Systems, Energies

, 7 1576-1598, ISSN1996-1073,

marzec 2014, praca zbiorowa.

Perez-Llera C., Fernandez-Baizan

M.C., Gonzalez del Valle V., Local

Short-Term Prediction of Wind Speed:

A Neural Network Analysis, Universidad

Politecnica de Madrid, Spain.

Moghaddas-Tafreshi, S.M., Panahi D.,

One-hour-ahead forecasting of wind

turbine power generation using artificial

neural networks, University of

Technology, Teheran, Iran.

Mao J., Zhang X., Li J., Wind power forecasting

based on the BP neural network,

Beifang University of Nationalities,

Yinchuan, China.

Sweeney C. i in., Post-processing

COSMO output for improved wind forecast,

Meteorology and Climate Centre,

Universtity College Dublin, Ireland,

April 2012.

Selcuk Nogay H., Akinci T.C.,

Eidukeviciute M., Application of artificial

neural networks for short term wind speed

forecasting in Mardin, Turkey, Journal

of Energy in Southern Africa, November

, Vol. 23, No. 4.