| Title |
A Study on the Prediction Model of Photovoltaic Power Generation using Deep Learning Algorithm |
| Authors |
강병복(Byungbog Kang) ; 윤중현(Junghyun Yun) |
| DOI |
https://doi.org/10.5573/ieie.2023.60.2.119 |
| Keywords |
Photovoltic power generation; Deep learning; Prediction model; Weather; LSTM |
| Abstract |
In this paper, in order to predict the amount of power generation for solar energy, the prediction error rates for three deep learning algorithms were applied and tested. For the data used during the test, the parameters were optimized by extracting data from photovoltaic power generation facilities and Korea Meteorological Administration. Among the three algorithms, as a result of measuring the prediction error rate according to the weather environment, the LSTM(Long Short-Term Memory) algorithm showed excellent characteristics in common. When the meteorological environment changes, such as clouds, there is a large error between the actual power generation and the predicted power generation. In addition, when the weather is maintained at a constant level, the predicted power generation converges to the actual power generation. Through these results, it is thought that the prediction error rate between predicted power generation and actual power generation can be improved through learning of output characteristics according to various environments. |