| Title |
A Study on Photovoltaic Output Prediction Uncertainty and Intermittency Compensation Method |
| Authors |
박우근(Woo-Geun Park) ; 김지수(Ji-Soo Kim) ; 임승민(Seung-Min Lim) ; 김철환(Chul-Hwan Kim) |
| DOI |
https://doi.org/10.5370/KIEE.2021.70.7.961 |
| Keywords |
Artificial Intelligence; Artificial Neural Network; Battery Energy Storage System; Deep Learning; Intermittency; Uncertainty; Variable Renewable Energy |
| Abstract |
Variable Renewable Energy(VRE) is impossible to maintain stable output due to uncertainty and intermittency. In this paper, Photovoltaic(PV) output is predicted through deep learning prediction technology and compared with the actual PV output. The data used as the input of the deep learning prediction model was partially selected through correlation analysis to reduce overfitting and to have high prediction performance. A Hyperparameter optimization model was used in several deep learning prediction models and the Recurrent Neural Network(RNN) prediction model was selected after comparing the performances. The difference between Predicted PV output and actual PV is compensated using Battery Energy Storage System(BESS). Moreover, the BESS capacity is calculated and the BESS State of Charge (SoC) range profile is observed. |