Multi-classification deep learning short-term wind power prediction method based on pitch angle classification

Abstract

The invention discloses a multi-classification deep learning short-term wind power prediction method based on pitch angle classification. The method comprises the following steps: equally dividing original fan data into four data sets according to pitch angle intervals; respectively carrying out Pearson correlation analysis on the four data sets to determine the correlation degree between each variable in each data set and the wind power; according to the relevancy of the variables in each data set, selecting several variables with high relevancy with the wind power as the input of the deep neural network model, and taking the wind power as the output; and dividing each data set into a training set and a test set in proportion, and training and testing the deep neural network model by using the training set and the test set to obtain a final deep neural network model. According to the prediction method, the problem of low wind power prediction accuracy in the prior art is solved.

Description

technical field [0001] The invention relates to a short-term wind power prediction method based on multi-category deep learning based on pitch angle classification. The invention belongs to the technical field of fan wind power prediction. Background technique [0002] Wind energy is a clean and non-polluting new energy source. According to statistics from the Global Wind Energy Council (GWEC), the cumulative installed capacity of wind power in the world shows a trend of increasing year by year. [0003] Wind energy is intermittent and random. When wind farms are connected to the grid on a large scale, it will have a large impact on the grid, affecting the reliability, stability and power quality of the grid operation. In order to improve the impact of random changes in wind power on the power grid, real-time dispatch of wind farms is necessary, and the premise is a more accurate prediction of the power generation of wind farms. [0004] In addition, the randomness, interm...

AI Technical Summary

Problems solved by technology

The machine learning method is to predict the output power of the wind farm based on the historical wind turbine data information. The commonly used prediction methods include the BP neural network method and the support vector machine (SVM) method, etc., but the ordinary machine learning method is difficult to meet the prediction accuracy, and the neural network Model deep learning is an important part of machine learning and has sufficient prediction accuracy, so the method of neural network deep learning is adopted

Images