Abstract: Aiming at the short-term load forecast of power system, we established the multiple regression and time series forecasting model, and analyzed the effects of maximum temperature, minimum temperature, average temperature, humidity and rainfall on the daily maximum load, daily minimum load and daily average load .The results show that the maximum temperature has the greatest influence on the daily maximum load, the daily minimum load and the daily average load, and the relative error between the predicted value and the actual value is within the allowable error range , thus the model reliability is higher