Short-term wind speed prediction at Bogdanci power plant in FYROM using an artificial neural network
The present study targets short-term wind speed prediction of the wind turbine station at Bogdanci in the Former Yugoslav Republic of Macedonia (FYROM), using artificial neural network (ANN) method. Wind directions and meteorological parameters (temperature, pressure, and humidity) measured at the i...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2019-07-01
|
Series: | International Journal of Sustainable Energy |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/14786451.2018.1516668 |
Summary: | The present study targets short-term wind speed prediction of the wind turbine station at Bogdanci in the Former Yugoslav Republic of Macedonia (FYROM), using artificial neural network (ANN) method. Wind directions and meteorological parameters (temperature, pressure, and humidity) measured at the interval of 10 min in between May 2015 and September 2015 have been used as the input of ANN to predict four kinds of wind speed (rotation mean, hub mean, tip low mean, and base mean). The best performance $\lpar R^2 = 0.84 - 0.86\rpar$ of ANN method was achieved using wind direction base mean (WDBM) in September 2015, and using temperature $\lpar {R^2 = 0.77 - 0.80} \rpar$ in May 2015. Reasonable performance of ANN method was achieved in the rest of the month. |
---|---|
ISSN: | 1478-6451 1478-646X |