| Title |
Artificial Neural Network-based Predictive Model for Stored Energy in a Solar Thermal Collector |
| Authors |
Ho Seong Jeon ; Sang Hun Yeon ; Min Hwi Kim ; Chul Ho Kim ; Kwang Ho Lee |
| DOI |
https://doi.org/10.6110/KJACR.2024.36.1.18 |
| Keywords |
인공신경망; 머신러닝; 태양열 집열기; 태양열 에너지; 태양열 시스템 Artificial neuron network; Machine learning; Solar collector; Solar thermal energy; Solar thermal system |
| Abstract |
Among a variety of renewable energies, solar energy can be economically used to replace conventional heating and hot water energy. However, it is greatly affected by the surrounding environment. Therefore, research for predicting renewable energy is an essential factor in securing the reliability and stability of renewable energy, and research using artificial intelligence has recently been actively conducted. This study conducted research on the development and analysis of an artificial neuron network (ANN)-based solar thermal energy predictive model. The predictive model was developed using in-situ data from a solar collector installed in a public building in the Jincheon Eco-Friendly Energy Town, which were collected from August 1, 2019 to July 31, 2020. The performance evaluation of the predictive model was conducted using Cv(RMSE), NMBE, and R2, as recommended by ASHRAE 2014 guidelines. The accuracy verification of the prediction model for hourly data showed that the solar thermal energy predictive model had a Cv(RMSE) of 11.7%, a NMBE of -1.2%, and a R2 of 0.93%. These results indicate that the predictive model can be properly used in the subsequent control algorithm for eventual energy saving. |