A wind speed prediction method and system based on a combined model

Abstract

The present invention proposes a wind speed prediction method and system based on a combined model, which relates to the wind speed prediction field of wind power generation. The method includes: collecting historical wind speed data, constructing an original wind speed data set; The wind speed time series of the data set is decomposed into N modal components; the N modal components include K intrinsic modal components and 1 residual component; each of the modal components is separately input into the pre-trained improved Prediction is carried out in the Transformer model, and the prediction result of the natural mode component and the prediction result of the residual component are obtained; the prediction result of the natural mode component and the prediction result of the residual component are superimposed to obtain the final wind speed forecast result. By combining the variational mode decomposition method and Transformer model, the accuracy and reliability of wind speed prediction can be effectively improved.

Description

technical field [0001] The invention relates to the field of wind speed prediction for wind power generation, in particular to a wind speed prediction method and system based on a combined model. Background technique [0002] At present, wind speed prediction methods can be divided into three categories: physical methods, statistical methods and artificial intelligence methods. Among them, the physical method relies on a large number of physical laws to establish the relationship expressions between wind speed and temperature, humidity and air pressure, and uses the computer to perform numerical calculations based on the wind data in the measured area to obtain wind speed prediction results. This method has strict requirements on data and hardware, and has a huge amount of calculation, so it is not suitable for popularization. The statistical method needs to collect a large amount of wind speed data, and predict the wind speed after processing and analysis. Compared with th...

AI Technical Summary

Problems solved by technology

The statistical method needs to collect a large amount of wind speed data, and predict the wind speed after processing and analysis. Compared with the physical method, the statistical method is easier to implement, but the wind speed sequence is non-stationary, and the prediction accuracy of a single statistical method is not high.

Artificial intelligence methods use neural network models such as machine learning models or deep learning models to predict wind speed, but a single machine learning model or deep learning model cannot fully learn the overall characteristics of wind speed time series, and its prediction accuracy is not high

Therefore, the existing wind speed prediction methods generally have the problem of low prediction accuracy.

Images