| Title |
A Study on Wind Power Forecasting Using LSTM Method |
| Authors |
이흥석(Heungseok Lee) ; 김규한(Kyuhan Kim) ; 정희명(Heemyung Jeong) ; 이화석(Hwaseok Lee) ; 김형수(Hyungsu Kim) ; 박준호(June Ho Park) |
| DOI |
https://doi.org/10.5370/KIEE.2020.69.8.1157 |
| Keywords |
Wind Power Forecasting; Deep Learning; Long Short-term Memory; Artificial Neural Network; Support Vector Regression |
| Abstract |
Recently, as the need for renewable and alternative energy increases, the proportion of wind power generation is increasing. The wind power generation can be produced anywhere in the windy place through fixed function. Commonly, the wind power generation is connected to end of system or microgrid, which have a small inertia. The wind power output depends heavily on the wind speed.
So, the wind power generation generates irregular power. When irregular wind power is connected to the grid, system quality problem would occur. Therefore, in order to stabilize the system operation, it is necessary to accurately forecast the wind power and calculate the reserve power. In this paper, the LSTM(Long Short-term Memory) model was used for wind power forecasting. Also, in order to verify the accuracy of the applied method, we analyzed it by comparing with the results of ANN(Artificial Neural Network) model and SVR(Support Vector Regression) technique. |