Short-term classification prediction method of photovoltaic power based on MIV-BP neural network

Abstract

An embodiment of the present invention provides a short-term classification prediction method of photovoltaic power based on MIV-BP neural network. The method includes using MIV algorithm to screen the weather factors that have a greater impact on the photovoltaic power under different conditions as the input of the prediction model, and according to the rainfall data in the weather information and data sampling time to establish a classification prediction model for forecasting. At present, most of that method are based on the solar radiation intensity, temperature and humidity as necessary inputs to the prediction model, By decomposing the original data series into rainfall time series and non-rainfall time series according to the rainfall amount in the weather factors, and the average influence value algorithm is used to select the weather factors which have great influence on the photovoltaic power under different conditions as the input of the prediction model. The non-rainfall time series are further decomposed according to the sampling time of the data, and the sub-models are established to forecast each series respectively, which reduces the prediction cost of the photovoltaic power, improves the prediction accuracy of the prediction model in sudden change weather, and improves the adaptability of the model.

Description

technical field [0001] The invention belongs to the field of power prediction, in particular to a photovoltaic power short-term classification and prediction method based on MIV-BP neural network. Background technique [0002] With the rapid growth of energy consumption and the continuous deterioration of the climate environment, photovoltaic power generation technology has developed rapidly in recent years, and more and more MW-level photovoltaic power generation systems have been integrated into the grid. However, affected by weather conditions, the randomness and intermittency of photovoltaic power brings great challenges to the stable operation and dispatch management of the power grid. Accurate prediction of photovoltaic power is not only conducive to the coordinated dispatch of photovoltaic power plant output, but also provides support for the decision-making and control behavior of the power grid, which is of great significance for improving the safety and stability o...

AI Technical Summary

Problems solved by technology

The physical method predicts the photovoltaic output by modeling the photoelectric conversion device and the control system. The prediction accuracy depends on the structure of the object to be measured and the accuracy of the selected parameters. However, this method involves many links and the process is relatively complicated; the statistical method is based on A large amount of historical data, using mathematical statistics, artificial intelligence algorithms, etc. to obtain the law between photovoltaic output, weather data, and historical operating conditions, has high requirements for data samples, and the prediction accuracy depends on samples, so it is difficult to measure the weather conditions under different weather conditions. The degree of influence of factors on photovoltaics

Images