Based on the prediction method of the least square method, this paper uses the linear regression analysis to sort out the historical data of the system, and takes the outdoor temperature in the weather forecast as the independent variable and the heating load as the dependent variable. At the same time, the historical data of these two variables are used as the prediction samples, which are fitted by the least square method. In order to improve the accuracy of heating load forecasting, the regression coefficient in linear relationship is determined by the method of Pauta criterion.