In this paper, we propose a method based on the support vector regression to predict the gas energy consumption in a conditioning equipment. We analyzed the time series of gas consumption by using auto and partial correlation functions and found that the gas consumption contains a non-linear correlation in the time series. Based on this finding, we adopted the support vector regression as a non-linear model for the prediction of the gas consumption. By tuning two parameters in the model and introducing the cross validation, we demonstrated that the proposed model predicted the gas consumption with the relative errors and the average errors less than 1% and 0.5Nm3/h 3.2 Nm3/h respectively. The results of this study can be used for the effective control of the conditioning energy in the air conditioning process.