An optimal correction energy storage frequency modulation instruction prediction method and system

CN120601451BActive Publication Date: 2026-06-30XIAN THERMAL POWER RES INST CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XIAN THERMAL POWER RES INST CO LTD
Filing Date
2025-04-14
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

In existing technologies, VMD and CEEMD suffer from high computational complexity, complex parameter tuning, modal redundancy and aliasing, difficulty in integrating prediction models, information loss and reconstruction errors, and insufficient handling of abrupt changes and non-stationarity when processing power grid frequency regulation command predictions, resulting in low prediction accuracy.

Method used

An optimization correction method is adopted to correct the original frequency modulation command sequence by obtaining the optimal position, the optimal straight line slope angle and the number of hits, thereby reducing its nonlinearity, and a neural network is used for prediction.

Benefits of technology

This improved the accuracy of frequency regulation command prediction, enhancing the power plant's response accuracy and frequency regulation benefits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120601451B_ABST
    Figure CN120601451B_ABST
Patent Text Reader

Abstract

An optimization-correction method for predicting frequency regulation commands in energy storage involves: obtaining an original frequency regulation command sequence; acquiring optimized correction parameters for each signal in the original frequency regulation command sequence, including the optimal position, optimal straight line slope angle, and hit count; using the optimal position, optimal straight line slope angle, and hit count from the optimized correction parameters to correct the original frequency regulation command sequence signal, resulting in a corrected frequency regulation command sequence; and using a neural network to predict the corrected frequency regulation command sequence to obtain the final prediction result. This method makes the prediction result of the frequency regulation command more accurate, allowing for early prediction of the magnitude of the frequency regulation command for energy storage regulation, thereby improving response accuracy and frequency regulation benefits.
Need to check novelty before this filing date? Find Prior Art