Short-term power prediction method used for newly-built wind farm

Abstract

The invention provides a short-term power prediction method used for a newly-built wind farm. The short-term power prediction method comprises steps that A: by using a BP neural network, a historical data relation between a scale value weather forecast prediction factor in the newly-built wind farm and a wind farm early-stage anemometer tower actually-measured wind speed is established, and a wind speed statistic downscaling model of an anemometer tower position draught fan hub height is generated; B: the short-term prediction wind speed of the anemometer tower position draught fan hub height is generated according to the prediction factor of the scale value weather forecast in the wind farm area and the wind speed statistic downscaling model of the anemometer tower position draught fan hub height of the step A; C: a newly-built wind farm short-term power prediction model is established according to a wind speed-power characteristic curve analysis data and a wind farm integrated factory electricity loss proportion, and newly-built wind farm short-term prediction power is calculated. Newly-built wind farm integrated output short-term prediction is realized.

Description

technical field [0001] The invention relates to the technical field of wind farm power forecasting, in particular to a short-term power forecasting method applied to newly built wind farms. Background technique [0002] In recent years, with the rapid development of wind power generation in my country, a large number of new wind farms have been put into operation in a short period of time. These wind farms lack accurate and reliable historical operating data, and cannot establish high-precision short-term power prediction models through traditional statistical modeling methods. It greatly affects the short-term power prediction accuracy of new wind farms. In order to ensure safe, reliable and efficient grid-connected operation of large-scale wind power, it is very important to develop a wind power prediction system that meets engineering applications. Contents of the invention [0003] In view of this, the main purpose of the present invention is to provide a short-term po...

AI Technical Summary

Problems solved by technology

[0002] In recent years, with the rapid development of wind power generation in my country, a large number of new wind farms have been put into operation in a short period of time. These wind farms lack accurate and reliable historical operating data, and cannot establish high-precision short-term power prediction models through traditional statistical modeling methods. Greatly affects the short-term power forecast accuracy of new wind farms

Images