| Title |
Prediction of Heating Energy Consumption Using Machine Learning and Parameters in Combined Heat and Power Generation |
| Authors |
Yusun Ahn; Hye Jin Kim; Sang Kyu Lee; Byungseon Sean Kim |
| DOI |
https://doi.org/10.6110/KJACR.2019.31.8.352 |
| Keywords |
난방 에너지 수요량 예측; 열병합 발전; 에너지 절약; 공동주택; 기계 학습 Prediction of heating energy usage; CHP; Energy saving; Apartment houses; Machine learning |
| Abstract |
This study aimed to minimize the wasted heat by predicting the amount of heat energy consumed a day before heating. The flow rate and schedule variables data were measured in the apartment using cogeneration system. This study used ANN and SVM as machine learning prediction algorithms and was verified by CvRMSE and MBE based on the criteria provided by ASHRAE Guideline 14. As a result, ANN derived an error of CvRMSE 8.75% and MBE 7.13%, respectively. The SVM was classified into three cases, which satisfied all the criteria except for linear of CvRMSE. Thus, using the actual measured heating energy usage data, machine learning can be used to predict a reliable level of thermal energy usage. |