Next Article in Journal
A Cross-Country Model for End-Use Specific Aggregated Household Load Profiles
Next Article in Special Issue
Framework for the Introduction of Vehicle-to-Grid Technology into the Polish Electricity Market
Previous Article in Journal
Leveraging Label Information in a Knowledge-Driven Approach for Rolling-Element Bearings Remaining Useful Life Prediction
Previous Article in Special Issue
Forecasting of 10-Second Power Demand of Highly Variable Loads for Microgrid Operation Control
Article

Day-Ahead Wind Power Forecasting in Poland Based on Numerical Weather Prediction

1
Institute of Meteorology and Water Management—National Research Institute, 01-673 Warsaw, Poland
2
Faculty of Environmental Engineering, Wrocław University of Science and Technology, 50-377 Wrocław, Poland
3
Faculty of Physics and Applied Computer Science, AGH University, 30-059 Krakow, Poland
*
Author to whom correspondence should be addressed.
Academic Editor: Mohamed Benbouzid
Energies 2021, 14(8), 2164; https://doi.org/10.3390/en14082164
Received: 23 March 2021 / Revised: 6 April 2021 / Accepted: 9 April 2021 / Published: 13 April 2021
The role of renewable energy sources in the Polish power system is growing. The highest share of installed capacity goes to wind and solar energy. Both sources are characterized by high variability of their power output and very low dispatchability. Taking into account the nature of the power system, it is, therefore, imperative to predict their future energy generation to economically schedule the use of conventional generators. Considering the above, this paper examines the possibility to predict day-ahead wind power based on different machine learning methods not for a specific wind farm but at national level. A numerical weather prediction model used operationally in the Institute of Meteorology and Water Management–National Research Institute in Poland and hourly data of recorded wind power generation in Poland were used for forecasting models creation and testing. With the best method, the Extreme Gradient Boosting, and two years of training (2018–2019), the day-ahead, hourly wind power generation in Poland in 2020 was predicted with 26.7% mean absolute percentage error and 4.5% root mean square error accuracy. Seasonal and daily differences in predicted error were found, showing high mean absolute percentage error in summer and during daytime. View Full-Text
Keywords: machine learning; wind power forecasting; day-ahead; numerical weather prediction; ALARO machine learning; wind power forecasting; day-ahead; numerical weather prediction; ALARO
Show Figures

Graphical abstract

MDPI and ACS Style

Bochenek, B.; Jurasz, J.; Jaczewski, A.; Stachura, G.; Sekuła, P.; Strzyżewski, T.; Wdowikowski, M.; Figurski, M. Day-Ahead Wind Power Forecasting in Poland Based on Numerical Weather Prediction. Energies 2021, 14, 2164. https://doi.org/10.3390/en14082164

AMA Style

Bochenek B, Jurasz J, Jaczewski A, Stachura G, Sekuła P, Strzyżewski T, Wdowikowski M, Figurski M. Day-Ahead Wind Power Forecasting in Poland Based on Numerical Weather Prediction. Energies. 2021; 14(8):2164. https://doi.org/10.3390/en14082164

Chicago/Turabian Style

Bochenek, Bogdan, Jakub Jurasz, Adam Jaczewski, Gabriel Stachura, Piotr Sekuła, Tomasz Strzyżewski, Marcin Wdowikowski, and Mariusz Figurski. 2021. "Day-Ahead Wind Power Forecasting in Poland Based on Numerical Weather Prediction" Energies 14, no. 8: 2164. https://doi.org/10.3390/en14082164

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop