A power generation prediction method, model training method and system

CN118826014BActive Publication Date: 2024-11-29XI AN JIAOTONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411296142.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-29
Estimated Expiration
2044-09-18

Smart Images

  • Figure CN118826014B_ABST
    Figure CN118826014B_ABST
Patent Text Reader

Abstract

The invention discloses a power generation prediction method, a model training method and a system, and belongs to the technical field of renewable energy power generation. The model training method adopts a correlation analysis method to reconstruct meteorological data to obtain multidimensional time series data, adopts the multidimensional time series data and the actual power generation time series to train the power generation prediction model, extracts the power time series characteristics of the actual power generation time series, and preliminarily predicts the first power generation in the future time period according to the power time series characteristics; predicts the second power generation in the future time period by extracting the time series fusion characteristics of the multidimensional time series data, and fuses the first power generation and the second power generation in the time dimension to obtain the final prediction result. The method effectively improves the accuracy and reliability of the new energy power generation prediction, and provides more powerful support for the efficient utilization of renewable energy power generation and the stable operation of the power system.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Wind power operation trend prediction method based on dual spatial-temporal feature extraction

    CN113537573A

  • Ultra-short-term wind power prediction method and system based on time sequence representation and multi-level attention

    CN116826727A