Coordinated optimization method and system for reactive power control parameters of optical storage system based on deep learning

CN119362483APending Publication Date: 2025-01-24GUO JIA DIAN WANG YOU XIAN GONG SI XI NAN FEN BU +2
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411374617.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2025-01-24

AI Technical Summary

Technical Problem

The prior art has problems in the optimization of reactive control parameters of optical storage systems that take a long time, cannot automatically obtain optimal parameters, and fail to take into account voltage stability and dynamic response characteristics.

Method used

The chaotic multi-objective particle swarm optimization algorithm based on deep learning is used to improve the BP neural network, build a CMOPSO-BP model, and embed it into the PI control strategy of the optical storage system. The optimal control parameters under different operating scenarios are obtained through deep network learning.

Benefits of technology

It improves the algorithm search speed and efficiency, improves control accuracy, can automatically and quickly obtain the optimal reactive power control parameters of the optical storage system under different working conditions, and improves grid-connected voltage stability and dynamic response speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119362483A_ABST
    Figure CN119362483A_ABST
Patent Text Reader

Abstract

The invention discloses a coordinated optimization method and system for reactive power control parameters of an optical storage system based on deep learning, and the method comprises the following steps: analyzing a VSG control mechanism of the optical storage system, constructing a bottom reactive power voltage control model, and determining a to-be-optimized variable; a BP neural network is improved by adopting a chaos multi-target particle swarm optimization algorithm based on a Pareto dominating relation and a displacement distance, an improved CMOPSO-BP model is obtained, and a connection weight and a threshold value of the BP neural network are optimized according to the improved CMOPSO-BP model; the improved CMOPSO-BP model is embedded into an optical storage system PI control strategy, grid-connected stability and response speed indexes are considered, an optical storage system reactive power parameter automatic coordination optimization model based on CMOPSO-BP is constructed, optimal control parameters in different operation scenes are learned through a deep network, and training samples are acquired; and learning the sample data by using the improved CMOPSO-BP neural network again by using the obtained training sample, and obtaining the optimal control parameters of the optical storage system in all the operation scenes.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Pipe flange welding robot control method and system, equipment and storage medium

    CN119620597A