Wind power plant short-term power prediction method

Abstract

The invention discloses a short-term power prediction method for a wind power plant. The method comprises the following steps of (1) initializing data selection days; (2) solving respective average values of the actual power generation power and the short-term power prediction data of the wind power plant in the period of time; and (3) solving a correlation coefficient r1 for the actual generatedpower and the short-term power prediction data, and performing differentiation processing according to the result of r1 to finally realize short-term power prediction of the wind power plant. According to the method, the wind power plant is prevented from excessively depending on the forecast wind speed in the numerical weather forecast, and short-term power forecast accuracy of the wind power plant when the forecast wind speed deviation is large is improved.

Description

technical field [0001] The invention relates to a new energy power prediction method, in particular to a wind farm short-term power prediction method. Background technique [0002] At present, more and more wind farms are being built, and wind farm power prediction is an important link in wind farms. Short-term power forecasting is an important link in wind farm power forecasting. The accuracy of short-term power forecasting for wind farms is crucial to the power generation efficiency of wind farms. Improving the accuracy of short-term power forecasting for wind farms is conducive to promoting the power grid to accommodate wind farm power generation increase the economic benefits of wind farms. [0003] The existing short-term power prediction of wind farms uses artificial intelligence algorithms. According to the input data of actual wind speed and actual power generation of wind farms, after using artificial intelligence algorithms, the mapping relationship between actual...

AI Technical Summary

Problems solved by technology

Due to the excessive reliance on numerical weather prediction in existing methods, once the numerical weather prediction data has a large deviation, the more accurate the mapping relationship is, the greater the error of short-term power prediction will be, resulting in a low accuracy rate of short-term power prediction

Images