Wind power prediction method and system based on frequency domain adaptive hyperparameter optimization

By adaptively optimizing VMD hyperparameters in wind power prediction and combining the Grey Wolf algorithm and Pearson correlation coefficient differential modeling, the problem of insufficient VMD hyperparameter dependency is solved, achieving efficient wind power prediction, improving prediction accuracy and reducing computational complexity.

CN121983970BActive Publication Date: 2026-07-07STATE GRID JIANGXI ELECTRIC POWER CO LTD RES INST
2 Cites 0 Cited by

Patent Information

Application Number
CN202610434675.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-03
Publication Date
2026-07-07
Estimated Expiration
2046-04-03

AI Technical Summary

Technical Problem

In existing technologies, the adaptability of variational mode decomposition (VMD) hyperparameters is insufficient, resulting in limited accuracy of wind power prediction and high computational complexity, making it difficult to meet the needs of engineering applications.

Method used

The frequency domain coverage overlap coefficient is used as the fitness function. The total number of modes and the penalty factor of VMD are adaptively optimized by combining the gray wolf optimization algorithm. The components are reconstructed by the sample entropy value, and meteorological features are screened by combining the Pearson correlation coefficient. Differential modeling is used for prediction.

Benefits of technology

It significantly improves the accuracy of wind power prediction, reduces computational complexity, and provides more reliable grid dispatch data support.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a wind power prediction method and system based on frequency domain adaptive super parameter optimization, which comprises the following steps: firstly, collecting historical wind power and meteorological data; secondly, proposing a brand-new frequency domain coverage overlap coefficient as a fitness function, combining the grey wolf optimization algorithm to adaptively optimize the super parameter of the variational mode decomposition, and using the optimized parameter to decompose the power sequence; thirdly, calculating the sample entropy of each component and reconstructing it into three categories of randomness, fluctuation and trend according to the entropy value to reduce the complexity; then, screening the strongly correlated meteorological features for each component based on the Pearson correlation coefficient, and inputting them into a prediction model for prediction; finally, superimposing the predicted values of each component to obtain the final power prediction result. The application solves the problem of artificial setting of the VMD super parameter, realizes the balance between the decomposition quality and the prediction efficiency, and significantly improves the accuracy and practicability of the ultra-short-term wind power prediction.
Need to check novelty before this filing date? Find Prior Art