Photovoltaic grid-connected power grid line loss prediction method based on gray neural network model

Abstract

The invention discloses a photovoltaic grid-connected power grid line loss prediction method based on a gray neural network model. The method comprises the following steps: 1) constructing a grid-connected photovoltaic array panel output power online monitoring system; 2) dividing the obtained characteristic information parameters into two classes, one class being called a training set for training learning of a prediction model, the other type being called as a test set for testing; 3) determining a gray model, and when the training accuracy meets a set requirement, performing test predictionon the gray model by using unknown characteristic information parameters, namely a test set; inputting the training set characteristic parameter sample obtained in the step 2 into the prediction model and carrying out training learning to obtain an output result, namely a result of photovoltaic grid connection on power grid line loss; and (4) inputting the data set sample obtained in the step (2)into the model trained in the step (3), completing the prediction of the line loss of the photovoltaic grid-connected power grid by the line loss prediction model, and verifying the accuracy of the prediction.

Description

technical field [0001] The invention belongs to the technical field of prediction of power grid line loss by photovoltaic power generation, and relates to a grid line loss prediction method for photovoltaic grid-connected grid based on a gray neural network model. Background technique [0002] With the continuous development of the social economy and the gradual enhancement of people's awareness of environmental protection, the development of clean energy and the protection of the ecological environment are not only the inevitable trend of social and economic development, but also the objective requirements of the people for the quality of life. In recent years, photovoltaic power generation technology has been continuously improved and matured, and has become a relatively important branch of the power industry, and its application range is also continuously expanding. However, photovoltaic power generation technology also has some unstable factors. For example, photovoltaic...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a grid line loss prediction method based on a gray neural network model for photovoltaic grid-connected grids, which solves the problems of large errors and low accuracy in the prior art

Images