Wind power generation power prediction method based on improved particle swarm

Abstract

The invention provides a wind power generation power prediction method based on an improved particle swarm. According to the method, equal-time-interval sampling is performed on historical power generation data of a wind power station per unit time to obtain a wind power station output power time sequence, the wind power station output power time sequence is preprocessed, and a wind power stationoutput power input space is constructed according to the preprocessed wind power station output power time sequence; a kernel function based on an SVM model is constructed through the output power input space; an optimization model of the kernel function based on the SVM model is constructed by introducing a Lagrangian multiplier and the preprocessed wind power station output power time sequence,and optimal solving is performed on the kernel function based on the SVM model through a weight-improved particle swarm optimization algorithm; and a prediction model is constructed through a proportion coefficient of an optimized Gaussian kernel function, a kernel coefficient of the Gaussian kernel function, a polynomial order of a polynomial kernel function, a penalty coefficient and the kernelfunction based on the SVM model. Compared with the prior art, prediction precision is improved through the method.

Description

technical field [0001] The invention belongs to the technical field of wind power generation, and in particular relates to a method for predicting wind power generation power based on improved particle swarms. Background technique [0002] Wind power generation is a new type of power generation system that utilizes natural wind energy and converts it into electrical energy. Due to the continuous turmoil in the political and economic situation of the world's major oil and natural gas exporting countries, all major energy-consuming countries are actively seeking alternatives to reduce their dependence on foreign energy and ensure the safety of the national economy and people's livelihood. It is against this background that wind energy, as a clean, cheap, sufficient and safe form of energy, has been more and more widely used. The International Energy Agency's "World Energy Outlook 2017 China Special Report" believes that China's energy structure will gradually shift to clean p...

AI Technical Summary

Problems solved by technology

[0003] However, there are some problems in the existing methods of predicting wind power output power prediction. When predicting the global characteristics, it is easy to ignore the local characteristics, and when the prediction focuses on the local characteristics, it is easy to ignore the global characteristics. and locality can meet the needs at the same time

Images