A Batch Power Prediction Method for Wind Turbines Based on Mixed Core Machine Learning

Abstract

The invention provides a wind turbine batch power prediction method based on mixed-core machine learning, including: establishing an offline historical database of wind turbines in a wind farm; dividing the historical data of each wind turbine in the wind farm offline history database into 12 histories Data collection; divide the wind turbines in the wind field into batches; use the wind turbines in each batch that are closest to the average wind power in the batch as the batch prototype; establish wind power prediction models for each batch of prototypes in different months; according to the wind field The future meteorological information predicts the wind power of each batch of prototypes, and multiplies and sums the predicted wind power of each batch of prototypes by the number of fans in the batch to obtain the predicted value of the total wind power of the wind field. The present invention collects meteorological data and wind power data, predicts the wind power of different batches of prototypes in the wind field, and combines the Gaussian kernel function and the polynomial kernel function as the kernel function, which has better adaptability and can predict the wind power of the entire wind field. The purpose of power is to provide guarantee for the power dispatching of wind farms.

Description

technical field [0001] The invention belongs to the technical field of wind power forecasting in wind farms, and in particular relates to a batch power forecasting method for wind turbines based on mixed-core machine learning. Background technique [0002] In recent years, with the increasing scarcity of global petroleum energy, the warning of nuclear power caused by the earthquake in Japan, and the increase in greenhouse gas emissions, wind energy has become the world's growing energy demand. Therefore, it has become a trend to accelerate the development of safe and clean energy industries including wind power. In order to improve the ability of my country's power grid to receive wind power and improve the utilization efficiency of wind farms, my country's National Energy Administration promulgated the "Interim Measures for the Management of Wind Farm Power Forecasting and Forecasting" in July 2011. The operating wind farm must establish a wind power forecasting system and ...

AI Technical Summary

Problems solved by technology

The above method uses wind power error information, probability model distribution of wind power, and traditional data analysis methods to predict the wind power of the wind field and identify the prediction error, but it does not combine the distribution of the location of the wind turbines in the wind field wind power prediction

Images