Power dynamic allocation method and device based on hybrid energy storage system

By combining LSTM network models and wavelet decomposition techniques with temperature compensation coefficients, the problem of rigid power allocation strategies in hybrid energy storage systems was solved, achieving more accurate power allocation and improved equipment coordination efficiency.

CN120638408BActive Publication Date: 2026-07-03CHONGQING THREE GORGES UNIV +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHONGQING THREE GORGES UNIV
Filing Date
2025-04-17
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing power allocation methods for hybrid energy storage systems fail to consider the dynamic parameters of energy storage devices in real time, resulting in rigid allocation strategies, insufficient prediction accuracy, increased risk of equipment aging, and limited system adaptability and efficiency under complex operating conditions.

Method used

An LSTM network model is used for power prediction. Wavelet decomposition technology is used to separate high-frequency and low-frequency components, and the components are corrected by temperature compensation coefficient. Dynamic allocation is performed in combination with the state of charge of the energy storage device, and a weight function is designed to optimize power allocation.

Benefits of technology

It improves power prediction accuracy, enhances the adaptability and operational reliability of hybrid energy storage systems under complex operating conditions, reduces equipment performance deviation, and optimizes equipment coordination efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120638408B_ABST
    Figure CN120638408B_ABST
Patent Text Reader

Abstract

The application provides a power dynamic allocation method and device based on a hybrid energy storage system, and relates to the technical fields of hybrid energy storage and power allocation.The method comprises the following steps: predicting input power data of a future time interval through an LSTM network model, and separating the input power data into high-frequency components and low-frequency components by wavelet decomposition; collecting power input, equipment state of charge and working temperature of the energy storage system in real time, generating a temperature compensation coefficient to correct the decomposed components; combining the corrected components and real-time data, and calculating the power allocation ratio among energy storage devices through a dynamic weight function to realize dynamic optimization allocation of power.The method fuses time series prediction, dynamic compensation and differentiated allocation strategy, significantly improves the power prediction accuracy, equipment collaboration efficiency and adaptability of the system under complex working conditions, effectively reduces the equipment performance deviation caused by temperature fluctuation, and improves the overall operation reliability and working efficiency of the hybrid energy storage system.
Need to check novelty before this filing date? Find Prior Art