Method for intelligently forecasting wind speed in wind power station

Abstract

The invention discloses a method for intelligently forecasting the wind speed in a wind power station. The method comprises the following steps of acquiring and inputting data, layering data sequences, establishing models, forecasting and comprehensively calculating, and outputting forecasting results, wherein in the step of layering data sequences, the original unstable wind speed is decomposed into two stable wind speed data outputs by adopting a wavelet packet decomposition method, and the number of the wind speed data outputs is defined as the number of wind speed sequence layers; in the step of establishing mathematical models, each layer of data in the wind speed sequence layers are independently processed, a BP (back propagation) neural network model is established for the high-frequency sequence layer, high-frequency data are calculated and then enter a data stack; a time sequence model is established for a low-frequency layer, the low-frequency data are calculated and then enter the data stack; after entering the data stack, all the data in the data stack just enter the forecasting and comprehensive calculating step for weighting calculation, and finally the forecasted results are output. The method provided by the invention belongs to an intelligent method, and can be used for realizing multi-step advance forecasting.

Description

[0001] technical field [0002] The invention relates to an intelligent prediction method of wind speed in a wind farm. Background technique [0003] In recent years, the green and environment-friendly wind power generation has received widespread attention from all over the world, and its development is also very rapid. Before deciding on the installation capacity and installation location of wind turbines, the forecast results of wind speed can help decision makers obtain the resource potential of wind power generation in the predicted place in advance. In addition, wind speed prediction technology is also very important for protecting wind turbines and other equipment and monitoring wind power grid connection. Therefore, the wind speed prediction of wind farms is of great social and economic significance. [0004] The Chinese invention patent "A Short-Term Wind Speed ​​Prediction Method for Wind Farms" (application number: 201019146035.5) discloses a wind speed predicti...

AI Technical Summary

Problems solved by technology

Although this method obtains higher prediction accuracy directly through the support vector machine, the support vector machine solves the support vector through quadratic programming, and solving the quadratic programming will involve the calculation of a large m-order matrix (m is the number of samples number), when the number of m is large, the storage and calculation of the matrix will consume a lot of machine memory and computing time, and the model will not be able to output the predicted value in real time

Its shortcoming: this invention can't be used in the real-time large-scale wind farm wind speed warning monitoring system

Its shortcomings: due to the use of various types of sample data, the BP neural network model is responsible, the training and prediction output time of the model is too long, the prediction accuracy is not high, and the real-time prediction is difficult to guarantee. Acquisition is bound to increase the burden on the actual application system

None of the above patents can achieve advanced multi-step prediction

Images