In order to meet the demand of estimating regional heat load for cogeneration enterprises

an estimation method using elastic network regression model is proposed. Firstly

the influencing factors of the actual heating heat index are analyzed to determine the input parameters of the model. Then

based on the actual operation data of 123residential areas in Xi'an in the heating season from 2022 to 2023

the estimation model is established

and it is proved that the accuracy of the model is higher than that of Lasso regression and ridge regression models. Finally

part of the communities in Xi'an are selected to form a verification set to verify the elastic network regression model. The verification results show that

the elastic network regression model combines the advantages of Lasso regression and ridge regression

and has higher prediction accuracy than the conventional machine learning model.The MAE and goodness of fit of the model are 1.150 and 0.953

respectively

indicating that the method can accurately estimate the actual heating heat index with different parameters

and can meet the actual engineering needs of cogeneration enterprises.