Photovoltaic power prediction method based on deep convolution nerve network

Abstract

The invention discloses a photovoltaic power prediction method based on a deep convolution nerve network; the method comprises the following steps: using a variation modal decomposition algorithm to carry out modal decomposition for an obtained history photovoltaic power sequence, and decomposing the sequence into a plurality of frequency components and a remainder component; respectively arranging the components into data of a two dimensional format; using the frequency components of the two dimensional format as the input of a multichannel deep convolution nerve network model, predicting andoutputting a frequency component predicted value sum; using a single-channel deep convolution nerve network model to extract high order features of the remainder component in the two dimensional format, using the extracted high order features and meteorology data as the input of a support vector machine model, and predicting and outputting a remainder component predicted value; adding the frequency component predicted value sum with the remainder component predicted value, thus obtaining a photovoltaic power prediction result at a to-be-predicted moment. The method can obviously improve the photovoltaic power prediction precision, and can effectively guide the power grid in scheduling, thus ensuring the power system to stably and safely operate.

Description

technical field [0001] The invention relates to a photovoltaic power prediction method based on a deep convolutional neural network, which belongs to the technical field of photovoltaic systems. Background technique [0002] With China's vigorous development, the problems of energy consumption and environmental pollution are becoming more and more serious. Comprehensive economic development and environmental governance to achieve sustainable development have become an important policy of the country. As a non-polluting, renewable and clean energy, solar energy has made photovoltaic power generation technology widely promoted and applied. However, solar energy resources are easily affected by weather factors, resulting in large fluctuations in the output power of photovoltaic power generation, resulting in great randomness and uncertainty in the operation and scheduling of photovoltaic grid-connected power systems. Therefore, the development of photovoltaic power forecasting...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of traditional photovoltaic prediction methods, including low prediction accuracy and limited number of training samples, the present invention provides a photovoltaic power prediction method based on deep convolutional neural network. Based on deep learning technology, the method combines deep convolution The product neural network model can directly learn a large amount of historical data sample information, which further improves the prediction accuracy

Images