Optical power prediction algorithm based on satellite cloud atlas

Abstract

The invention provides an optical power prediction algorithm based on a satellite cloud atlas. The optical power prediction algorithm uses a visible light satellite cloud picture as a prediction datamodel, predicts the cloud shielding condition above a certain specific photovoltaic power station in a plurality of hours in the future by analyzing and judging the cloud picture change condition in aplurality of hours in the past, and corrects the irradiation intensity prediction value of the specific photovoltaic power station through the empirical model, so that the problem that the optical power cannot be predicted due to the fact that the photovoltaic power station is shielded by the cloud is solved, and fluctuation of the cloud layer above the photovoltaic power station is effectively predicted, and the irradiance prediction precision is improved, and then prediction of the generating capacity is improved.

Description

technical field [0001] The invention relates to the field of photovoltaic power station power prediction, in particular to an optical power prediction algorithm based on satellite cloud images. Background technique [0002] With the increase of energy consumption and environmental awareness, the rapid development of new energy power generation, especially the installed capacity of photovoltaic power generation in my country has reached the first place in the world, photovoltaic power generation is affected by environmental factors and becomes unstable. The danger of power quality degradation or even disconnection, and the more accurate the photovoltaic power prediction, the smaller the impact on the safe operation of the grid after grid connection, which is of great significance for improving the development and utilization of photovoltaic power generation and ensuring the safe operation of the grid. [0003] At present, the power generation of photovoltaic power plants is gr...

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide an optical power prediction algorithm based on satellite cloud images. The present invention introduces visible light satellite cloud images as the input of the prediction data model, and judges the cloud images of the past few hours by comparing and analyzing the predictions in the next few hours. The cloud shading situation above the photovoltaic power station, and the irradiance prediction value is corrected through the empirical model to solve the problem that the shading effect of the cloud layer on the photovoltaic power station can not predict the optical power well