Multi-model power system inertia probability prediction method based on crown-hoar optimization and adaptive kernel density estimation

By employing a multi-model power system inertia probabilistic prediction method based on porcupine optimization and adaptive kernel density estimation, the hyperparameters of the CNN-BiLSTM-MHAM model are optimized and an inertia prediction error database is constructed. This solves the problem of inertia uncertainty characterization and achieves efficient and accurate inertia prediction and decision support.

CN122309955APending Publication Date: 2026-06-30CHINA THREE GORGES UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA THREE GORGES UNIV
Filing Date
2026-03-03
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing power system inertia prediction methods cannot effectively handle the uncertainty of inertia. Traditional methods are unable to accurately characterize the complexity and uncertainty of inertia fluctuations, resulting in a lack of reliable basis for power grid operation, scheduling and control decisions.

Method used

A multi-model power system inertia probabilistic prediction method based on porcupine optimization and adaptive kernel density estimation is adopted. The hyperparameters of the CNN-BiLSTM-MHAM model are optimized by porcupine optimization algorithm, and an inertia prediction error database is constructed by combining the adaptive kernel density estimation method to generate the probability interval of inertia prediction.

Benefits of technology

It significantly improves the accuracy of inertia prediction and the ability to characterize uncertainties, provides comprehensive and reliable technical support, and enhances the reliability of power system operation and control decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122309955A_ABST
    Figure CN122309955A_ABST
Patent Text Reader

Abstract

A multi-model power system inertia probabilistic prediction method based on porcupine optimization and adaptive kernel density estimation includes the following steps: acquiring power system inertia-related characteristic variables, constructing a data sample set for inertia prediction, and building a CNN-BiLSTM-MHAM deep learning model based on the data sample set; optimizing key hyperparameters of the model using the porcupine optimization algorithm based on the constructed CNN-BiLSTM-MHAM deep learning model to obtain optimized model structure parameters and inertia prediction results; constructing an error database based on the error between the inertia prediction results and actual values; and using the constructed error database, probabilistically modeling the prediction error using the adaptive bandwidth kernel density estimation method, and generating the probability interval for inertia prediction by combining the Bootstrap resampling method, thereby realizing the quantification and probabilistic expression of the uncertainty of the inertia prediction results. This method not only significantly improves the accuracy of power system inertia prediction but also more effectively characterizes the uncertainty and probability distribution characteristics of inertia fluctuations.
Need to check novelty before this filing date? Find Prior Art