Abstract: With the continuous integration of new energy into the power system, it is particularly important to make more accurate and reliable predictions of new energy generation in order to reduce the uncertainty of wind power,photovoltaic and other new energy sources on the power grid, improve the reliability, economy, and safety of the power grid. This article introduces a method based on the root mean square error algorithm, which uses higher prediction difficulty assessment standards and involves the first power prediction value in the calculation to optimize the accuracy of power prediction for new energy sources such as wind power and photovoltaics. This method has been successfully validated and applied in the integrated dispatch system of the main distribution new energy of a power supply company. With higher accuracy standards for new energy prediction, it greatly improves the reliability and safety of the entire process of new energy generation prediction, production, and consumption in this area.