Short-term wind power prediction method, device, equipment, medium and product

Through the ICEEMDAN decomposition and multi-model fusion method, the problem of insufficient prediction accuracy of short-term wind power is solved, and higher prediction accuracy and more stable grid operation are achieved.

CN120127622APending Publication Date: 2025-06-10SHENYANG INST OF ENG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510112658.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-24
Publication Date
2025-06-10

AI Technical Summary

Technical Problem

The prior art has insufficient prediction accuracy in short-term wind power prediction, making it difficult to effectively deal with the randomness and volatility of wind power, affecting the stability of the power grid.

Method used

The original wind power power sequence is decomposed by ICEEMDAN method to obtain a modal component sequence, and the high-frequency components are further decomposed by the SVMD algorithm. Each subcomponent sequence and climatic factors are input into the CNN-BiLSTM model, the intermediate frequency and low frequency components are input into the DELM model respectively, and finally multi-model fusion is performed through the SVM model to improve the prediction accuracy.

Benefits of technology

Through the multi-model fusion method, the prediction accuracy of wind power is significantly improved, the prediction error is reduced, the prediction ability of wind power volatility is enhanced, and the stability of the power grid is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120127622A_ABST
    Figure CN120127622A_ABST
Patent Text Reader

Abstract

The invention discloses a short-term wind power prediction method and device, equipment, a medium and a product, and relates to the field of short-term wind power prediction.The method comprises the steps that an original wind power sequence is decomposed through an ICEEMDAN method to obtain modal component subsequences; performing mean value test on the residual component sub-sequence and the intrinsic mode component sub-sequence except the highest frequency to obtain an intermediate frequency sub-sequence and a low frequency sub-sequence; obtaining intermediate-frequency and low-frequency components according to the intermediate-frequency and low-frequency subsequences; an SVMD algorithm is adopted to decompose the intrinsic mode component sub-sequence with the highest frequency to obtain a plurality of sub-component sequences; inputting the sub-component sequence into a CNN-BiLSTM model to obtain a first wind power predicted value; respectively inputting the intermediate-frequency component and the low-frequency component into a DELM model to obtain a second wind power predicted value and a third wind power predicted value; and inputting the three wind power predicted values into the SVM model to obtain a final wind power predicted value. The method can improve the prediction precision of the wind power.
Need to check novelty before this filing date? Find Prior Art