Wind Power Short-Term Combination Forecasting Method

Abstract

A short-term combination forecasting method for wind power, comprising: 1) normalizing wind speed and wind power data, and using support vector machine regression, Elman neural network, and BP neural network to establish corresponding single-item forecasting models; 2) according to the wind speed Stage the prediction results obtained from the training of each individual prediction model; 3) Select the parameters to be optimized and establish a combined forecasting model 4) Determine the objective function according to the combined forecasting model, and use the minimum average absolute percentage error as the constraint condition of the objective function to obtain the optimized Post-parameter 5) Obtain the weight coefficient value of each period after the stage according to the optimized parameters, and update the combined forecast model; 6) Dynamically select the corresponding weight coefficient value according to the wind speed, and use the wind power test data to update the combined forecast model Carry out training and make predictions to obtain combined prediction values. The invention effectively synthesizes the advantages of each single forecasting model, reduces forecasting risks, and has high forecasting accuracy.

Description

technical field [0001] The invention relates to the technical field of wind power forecasting, in particular to a short-term combination forecasting method of wind power based on entropy discrimination bee colony algorithm optimization. Background technique [0002] In recent years, wind energy, as a renewable energy, has developed rapidly around the world. As of December 2012, the world's installed wind power capacity has increased from 60GW in 2000 to 282.578GW, and it is expected that the world's installed wind power capacity will reach 460GW by 2015. With the rapid development of wind power, grid connection has become a research hotspot for making full use of wind power. The output power of wind power depends on the wind speed. However, due to the uncertainty and intermittency of wind speed, it is bound to have a serious impact on the stability of the power grid. [0003] Accurate short-term forecasting of wind power is conducive to the power sector to formulate reason...

AI Technical Summary

Problems solved by technology

The output power of wind power depends on the wind speed. However, due to the uncertainty and intermittency of wind speed, it is bound to have a serious impact on the stability of the power grid.

Images