Short-term wind power prediction method based on IJS-SVR model

Abstract

The invention provides a short-term wind power prediction method based on an IJS-SVR model. The method comprises the following steps: acquiring a wind power generation related data set S, dividing the wind power generation related data set S into training data and test data, determining input and output of a prediction model, and performing normalization processing on the data; setting parameters of an improved artificial jellyfish (IJS) algorithm and a support vector regression (SVR) model; operating an improved artificial jellyfish (IJS) algorithm to obtain an optimal penalty factor C and a kernel function optimal parameter g in a support vector regression (SVR) model; the optimal parameter combination obtained through optimization is substituted into a support vector regression (SVR) model, and a support vector regression (IJS-SVR) model optimized by an improved artificial jellyfish algorithm is trained; and inputting the test data into the IJS-SVR model to obtain a prediction result, and carrying out reverse normalization on the prediction result. The result shows that under MAE, MAPE, RMSE and R2 performance indexes, the prediction performance of the IJS-SVR model is better, and the defect that an existing short-term wind power generation output power prediction method is low in prediction precision is effectively overcome.

Description

technical field [0001] The technical scheme of the present invention belongs to the technical field of wind power generation, in particular to a short-term wind power prediction method. Background technique [0002] In recent years, the introduction of the national new energy policy has made wind power generation technology widely used. However, with the continuous increase of the installed capacity of wind power generation, some shortcomings and limitations in the utilization process are also exposed. As a clean energy, wind energy has certain volatility and uncertainty. The output power of wind power generation is also affected by seasons, weather and other factors. When a large-scale wind power generation system with volatility is connected to the grid, it is bound to bring challenges to the safe and stable operation of the power system. [0003] Prediction of wind power is an important basis for realizing large-scale wind power generation systems connected to the power...

AI Technical Summary

Problems solved by technology

However, these algorithms have problems such as poor optimization ability and premature convergence, resulting in the accuracy and accuracy of the final wind power prediction results still need to be improved.

Images