Wind power generation short-term load forecast method of least squares support vector machine

Abstract

The invention discloses a wind power generation short-term load forecast method of a least squares support vector machine. The method comprises the following steps of 1, preprocessing original data; 2, carrying out principal component analysis on an original data sequence which is input to the least squares support vector machine by a principal component analysis method, and analyzing and extracting a key impacting indicator of wind power loads; 3, building a mathematical model of the least squares support vector machine; 4, inputting the analyzed and extracted key impacting indicator to the mathematical model of the least squares support vector machine to be used as a training sample and a testing sample; 5, carrying out forecast on testing sample data by the mathematical model of the least squares support vector machine to obtain a forecast result. According to the wind power generation short-term load forecast method of the least squares support vector machine, the principal component analysis method and the mathematical model of the least squares support vector machine are combined, the calculated amount is reduced, the operability is increased, and the whole forecast performance and the whole forecast accuracy are improved.

Description

technical field [0001] The present invention relates to the field of electric power information technology, in particular to a short-term wind power generation load forecasting method based on Principal Component Analysis (PCA, Principal Component Analysis) Least Squares Support Vector Machine (LS-SVM, Least Squares-Support Vector Machine). Background technique [0002] In recent years, with the increasingly serious situation of energy shortage and energy supply security, the status of renewable energy has been continuously improved, and wind energy has played an important role in the supply of new energy due to its low cost, mature technology and high reliability. increasingly important role. China has abundant reserves of wind energy resources. According to the evaluation of the Chinese Academy of Meteorological Sciences, China's onshore wind energy development capacity is about 253GW, ranking third in the world. With the continuous development of wind power technology an...

AI Technical Summary

Problems solved by technology

They have their own research characteristics and application conditions, such as the slow convergence speed of the artificial neural network BP method, and the high time complexity of the SVM method; therefore, the current wind farm power generation prediction time is long, and the prediction error is large, which is easy to affect the wind power. The problem of timely scheduling and effective power resource allocation of power grid according to the change of power load

[0005] Therefore, it is necessary to propose a microgrid wind power ultra-short-term prediction method based on principal component analysis (PCA) least squares support vector machine, which combines principal component analysis and least squares support vector machine to play their respective advantages. It not only fully considers various factors that affect load forecasting, but also avoids the problems of complex calculation and long training time caused by low forecasting accuracy and excessive numbers due to the correlation between input variables.

Images