公开(公告)号：US20210194424A1

公开(公告)日：2021-06-24

申请号：US17267918

申请日：2019-05-16

Applicant: SHANDONG UNIVERSITY

Inventor： Feng GAO ,  Xiangjian MENG ,  Tao XU ,  Chenghui ZHANG

IPC: H02S50/00 ,  H02S40/32 ,  H02J3/00

Abstract: The present disclosure provides a method and system for power prediction of a photovoltaic power station based on operating data of grid-connected inverters, including: constructing a photovoltaic module model according to parameters of a photovoltaic module in a photovoltaic power station; constructing a power prediction model based on an artificial neural network algorithm; acquiring output data of a photovoltaic array when being shaded by static shadows of different thicknesses and different shading areas, constructing a training set to train the power prediction model, and obtaining a trained power prediction model; and acquiring, classifying, and normalizing output powers in real-time operating data of an inverter when the photovoltaic array is under a clear sky condition, and predicting a output power of the entire photovoltaic power station by using the trained power prediction model, the power prediction including a rolling prediction of the output power of the photovoltaic power station under a clear sky condition and a minute-level power prediction of the photovoltaic power station when being shaded by a dynamic cloud cluster. The present disclosure reduces a device cost and overcomes the defect that cloud clusters of different thicknesses affect the precision of power prediction of the photovoltaic array.