Ultra-short-period photovoltaic prediction method

Abstract

The invention discloses an ultra-short-period photovoltaic prediction method. The method comprises the following steps: selecting training data x; performing normalization processing on the training data; performing data exception handling on the training data; performing data functional transformation; performing significance analysis; training a generalized regression neural network model; and predicating the generalized regression neural network model. According to the ultra-short-period photovoltaic prediction method, a generalized regression neural network modeling theory and method is adopted; partial approximation is further accurate by adding a primary function in a hidden layer, and global optimum is achieved; significance extraction and improvement is carried out specific to the model input information; the correlation of historical data is enhanced through the functional transformation, and the historical data, used as the input signal, enters the generalized regression neural network prediction model, so that the prediction efficiency is effectively improved; in addition, after a training sample is chosen, the generalized regression neural network structure and the weight are determined automatically by only requiring to adjust smoothing parameters, so that the computational process for circuit training is avoided, and the global approximation study and prediction capability is realized more rapidly.

Description

technical field [0001] The invention relates to a photovoltaic power generation prediction method, in particular to an ultra-short-term photovoltaic prediction method. Background technique [0002] Solar photovoltaic power generation has the advantages of high conversion efficiency, long service life, and no moving parts. At present, foreign solar photovoltaic power generation has completed the initial development stage and is developing into the stage of large-scale application. However, due to the intermittent and random characteristics of solar energy, with the rapid expansion of photovoltaic installed capacity and large-scale photovoltaic grid connection, it will not be conducive to the stability of the grid and have a profound impact on the power market. Therefore, predicting photovoltaic power generation The power generation of the system is of great significance to the dispatching of power grid power. [0003] The power generation of solar photovoltaic power generati...

AI Technical Summary

Problems solved by technology

[0004] The existing forecasting technology, for the photovoltaic power generation forecasting model, mainly uses the combination of meteorological factors and historical radiation as the input of the BP neural network. However, the BP neural network is easily confused by local optimum and the training speed is slow.

Images