Genetic algorithm least square wind power prediction method

Abstract

The invention discloses a genetic algorithm least square wind power prediction method. A genetic algorithm least square support vector machine (GA-LSSVM) prediction model is established by use of collected actual measurement wind speeds, and input and output variables used for modeling are determined; normalization processing is performed on original data, and by use of a genetic algorithm, data of parameters and sample data trained and tested by a least square support vector machine (LSSVM) prediction model are optimized; initialization setting is performed on the genetic algorithm and parameters of the LSSVM prediction model, the model is trained, optimized LSSVM prediction model parameters are obtained through multi-generation evolution of the genetic algorithm, and the LSSVM prediction model is established; and wind speed short-term prediction is performed on test samples by use of the LSSVM prediction model. According to the invention, parameter searching optimization is performed on the LSSVM model by use of the genetic algorithm, a wind speed information prediction model based on a GA-LSSVM is established, and accurate prediction of data can be well realized.

Description

technical field [0001] The invention belongs to the technical field of wind power, and in particular relates to a genetic algorithm least squares wind power prediction method. Background technique [0002] Wind Power Prediction / Wind Farm Power Prediction WPP (Wind Power Prediction) (also known as Wind Energy Prediction in some domestic professional magazines) wind power prediction refers to the prediction of the power generation of wind turbines in wind farms. [0003] Most of the existing wind power forecasting techniques use numerical weather forecasting for corrections, and the historical data are insufficiently utilized, relying heavily on the accuracy of numerical weather forecasting. Contents of the invention [0004] The purpose of the present invention is to propose a method for predicting ultra-short-term power of wind power, using genetic algorithm to optimize the parameters of the least squares vector machine (LSSVM) model, and establishing a method based on GA-...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing wind power forecasting technologies are corrected by using numerical weather forecasting, and the historical data are not used enough, and they rely heavily on the accuracy of numerical weather forecasting

Images