Wind turbine generator generated power prediction method based on K-means mean clustering

Abstract

The invention provides a wind turbine generator generated power prediction method based on K-means mean clustering. The method comprises the following steps of collecting historical meteorological data and corresponding wind speed values of a to-be-predicted region wind power plant and preprocessing the historical meteorological data and the corresponding wind speed values; calculating a correlation coefficient of the historical meteorological data to a wind speed value by adopting a Pearson correlation coefficient, reserving data of which the correlation coefficient is greater than a threshold value, and constructing a training set; clustering the training set data by adopting a K-means mean value clustering method; optimizing the initial weight of the BP neural network through a cuckoo algorithm, and constructing a wind turbine generator generated power prediction model; inputting the training set into the prediction model for training to obtain an optimal solution of the network weight of the prediction model, and storing the optimal solution; predicting meteorological factor data of a to-be-predicted day according to a clustering result of the training set, inputting the meteorological factor data into the prediction model to obtain a predicted wind speed value, and obtaining a predicted power generation power value of the wind turbine generator through predicted wind speedconversion calculation.

Description

technical field [0001] The present invention relates to the technical field of electric power system and automation thereof, and more specifically, relates to a method for predicting the generated power of wind turbines based on K-means clustering. Background technique [0002] Wind energy, as the most mature renewable energy, has been widely used in grid power generation. Due to uncertain factors such as randomness, volatility, and intermittency of wind speed, the integration of large-scale wind power into the grid will bring a series of problems to the safe and stable operation of the power system, such as voltage and frequency deviations, voltage fluctuations, etc. and offline. Accurate prediction of wind power generation power is beneficial to large-scale wind power grid integration and reduces the harm caused by wind power grid integration, which is of great value and significance. [0003] At present, the power generation prediction methods of wind turbines include p...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the defect of low prediction accuracy in the method for predicting the generated power of wind turbines in the prior art, the present invention provides a method for predicting the generated power of wind turbines based on K-means clustering

Images