This study based on the deep learning and edge calculation,expounds on the power system load forecasting methods,and on this basis,respectively,set up power short-term load forecasting model based on the theory of the deep learning and power load forecasting model based on edge of computing,and then the selected two models respectively based on MATLAB platform by simulating the data set.Taking a charging station in N city as an example,the accuracy of the two models for power load prediction of the charging station is analyzed and compared.The research results show that the output value of the deep learning model has a small difference with the real value,and the correlation coefficient is 0.998 99.The established deep learning model has absolute advantages in data feature mining and classification .