LAUSR

Abstract For the heating system with thermal inertia, accurate prediction of heating parameters is the premise of achieving on-demand heating. The existing prediction models do not evaluate the historical operation data before model training, which may lead to the establishment of non-on-demand models and affect their application in actual project. In this paper, firstly, the data evaluation method and application process were proposed based on heating professional mechanism and actual operation data. Secondly, the proposed method was used to evaluate the historical data of a heating substation, and the relationship between outdoor temperature and heating parameters (daily secondary supply temperature and daily heating consumption) for different indoor temperature intervals were obtained. Finally, the prediction models were training by historical data with and without evaluation method, and compared them from evaluation criteria and professional mechanism. The results showed that the accuracy of prediction model established by historical data with evaluation method was greatly improved, and can be used to guide the energy-saving operation of heating substation. In addition, it was also obtained that the prediction model established by big data can be used for prediction guidance at the middle heating period, and linear regression method was suitable for the end of heating period.