Wind speed prediction method for wind farm spatial correlation

Abstract

The present invention discloses a wind speed prediction method of a wind farm. Problems are mainly considered that spatial correlation among wind farms, unscented Kalman Filter optimization, and the like are not well considered in an existing method. The method mainly comprises: calculating a rank correlation coefficient between a target wind farm and the other 21 wind farms if 22 wind farms are given; determining a wind farm for prediction according to the correlation coefficient; and selecting a wind farm with a Kendall rank correlation coefficient greater than 0.55 and a Spearman rank correlation coefficient greater than 0.75; then establishing a non-linear state space model by using support vector machine regression, and performing unscented Kalman filter prediction by using the established non-linear state space model; optimizing a scale parameter of the unscented Kalman filter according to a principle of prediction error minimization; and finally, selecting wind speed data of a wind farm of a same time in four years, and performing grey correlation analysis by using the wind speed data and wind speed data of a target wind power turbine, No.9 wind power turbine, of the same time in the first year.

Description

Technical field [0001] The wind speed prediction field of the wind farm of the present invention, especially in areas with densely distributed wind farms, predicts the wind speed of a certain wind farm, and is used to solve the problem of insufficient prediction accuracy caused by ignoring the location of the wind field in the wind speed prediction process. Background technique [0002] Wind power has developed rapidly in recent years because of its environmental protection, renewable and other advantages, and has become an ideal energy source recognized worldwide. However, when the penetration power of wind power reaches a certain value, the randomness, volatility and instability of wind power will have a great impact on the operation of the power system. Relevant scholars have carried out a lot of related research in this area, and have reached some practical conclusions. To reduce the impact, the main thing is to make a more accurate forecast of wind speed or wind power. [00...

AI Technical Summary

Problems solved by technology

[0008] In the literature Windpowerpredictionbasedonnumericalandstatisticalmodel, this method predicts wind speed based on numerical weather prediction and Kalman filter prediction model. The author considers the influence of meteorological parameters on wind speed, and uses the Kalman filter model to predict wind speed in real time. The spatial model is linear, so it cannot describe the actual situation of wind speed well

Images