A power grid system management method, system and electronic device

CN121307849BActive Publication Date: 2026-06-30SICHUAN HYDROPOWER INVESTMENT & MANAGEMENT GROUP CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SICHUAN HYDROPOWER INVESTMENT & MANAGEMENT GROUP CO LTD
Filing Date
2025-10-13
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Traditional centralized load forecasting is difficult to adapt to the increasing complexity and regional differences of load characteristics in new power systems, leading to increased control dimensions and communication burden, and making it difficult to cope with changes in grid topology and fluctuations in operating conditions.

Method used

Deploy regional prediction servers on the edge side, build an edge node power load prediction model, introduce the constraint theory to select key constraint nodes, synchronize data from non-constraint nodes to constraint nodes, and perform dynamic coordination and optimization.

Benefits of technology

It reduces the control dimensions and communication burden, enables real-time adaptation to changes in power grid topology and operating conditions, and improves frequency control efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121307849B_ABST
    Figure CN121307849B_ABST
Patent Text Reader

Abstract

This invention relates to a management method, system, and electronic equipment for power grid systems, belonging to the technical field of power grid systems. The invention aggregates the electricity consumption data predicted by the load forecasting model of each edge node and introduces a constraint theory. Key constraint nodes are selected based on node importance and controllability. Non-constrained nodes synchronize data with the constraint nodes. Finally, based on the constraint optimization results and the electricity consumption data predicted by the load forecasting model of each edge node, the power supply in the target area is dynamically coordinated and optimized. Addressing the complexity of multi-node power grids, this invention introduces constraint control theory, selecting key constraint nodes based on node importance and controllability. Non-constrained nodes synchronize with the constraint nodes through a constraint matrix, significantly reducing the control dimension and communication burden. In practical applications, the online learning mechanism enables the controller to adapt to changes in grid topology and fluctuations in operating conditions in real time, achieving efficient frequency control.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • CN119994972A

  • CN120474054A