In order to reduce the influence of meteorological factors on the prediction accuracy of distributed photovoltaic power generation. In this paper

a distributed photovoltaic power prediction method based on similar days and VMD(variational mode decomposition)-DBO(dung beetle optimizer)-KELM (kernel extreme learning machine) is proposed. Firstly

the improved iterative self-organizing data analysis techniques algorithm (ISODATA) is used to divide the historical distributed photovoltaic power data into different similar days. Secondly

the photovoltaic power sequence is decomposed into different modal components by VMD

and each component is predicted separately in the KELM prediction model optimized by DBO. Then

the prediction component is reconstructed to realize the high-precision prediction of distributed photovoltaic power based on VMD-DBO-KELM. Finally

the measured data of a distributed photovoltaic station are used for example analysis. The results show that the proposed method has high prediction accuracy and strong adaptability on different similar days.