A short-term wind power forecasting method based on a hybrid algorithm

Abstract

The invention relates to a short-term wind power forecasting method based on a hybrid algorithm, which includes the following steps: S1 decomposing the original wind power into a series of intrinsic mode function (IMF) sub-modal components by using the integrated empirical mode decomposition technique, S2 extracting the main trend components of IMF and RES components except the first IMF componentIMF1 decomposed by the integrated empirical mode decomposition (IMD) technique by using the singular spectrum analysis (SSA) method to obtain more obvious sub-modal components, S3 preserving IMF1 andR, and decomposing IMF1 and R into a series of stationary sub-modal components by wavelet packet decomposition. S4 making use of on-line robust limit learning machine to to establish a prediction model for all the sub-modes obtained in the step S1-S3,, and obtaining a final wind power prediction result by superposing the sub-modes; The invention can effectively and accurately predict the actual wind power system, and provides an important reference for the operation and planning of the electric power system.

Description

technical field [0001] The present invention relates to the field of power system forecasting methods, more specifically, to a short-term wind power forecasting method based on a hybrid algorithm. Background technique [0002] With the development of wind power generation, the influence of wind power uncertainty on the stability, adequacy and economy of the power system and power market is becoming more and more obvious. Therefore, accurate short-term wind power forecasting is of great significance to power system planning and dispatching. At present, wind power forecasting methods are mainly divided into statistical learning methods and physical methods according to different data sources used. Among them, the statistical learning method establishes a statistical learning model based on the historical measurement data of the wind farm and surrounding measurement data. The most commonly used statistical learning models include machine learning methods such as time series an...

AI Technical Summary

Problems solved by technology

[0011] (2) The traditional neural network, such as a typical BP neural network, has complicated parameters, slow convergence rate and easy to fall into local optimal solution; the original extreme learning machine converges quickly, but is easily disturbed by outliers in the training set , and the improved robust extreme learning machine can better adapt to the situation where the sample contains outliers

However, the actual wind power is a time-varying online system, and the above prediction model is still not ideal for the actual time-varying system.

Images