Power distribution network collaborative optimization control system based on digital twin and multi-agent reinforcement learning

CN122246708APending Publication Date: 2026-06-19ANHUI ZHONGKE YOUZHI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ANHUI ZHONGKE YOUZHI TECH CO LTD
Filing Date
2026-03-10
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing power distribution network dispatching methods suffer from issues such as lag between the twin and physical entity states, lack of dynamic coordination mechanisms, inability to cope with extreme faults and the fluctuating demands of distributed resources, resulting in insufficient adaptive control capabilities.

Method used

We construct a twin-decision-evolution closed-loop module, a hierarchical and partitioned hybrid collaborative architecture, a data-knowledge hybrid driving engine, and an extreme scenario elastic collaborative control module to achieve real-time synchronization, hierarchical collaboration, and resilient self-healing.

Benefits of technology

It enables real-time and precise control of the distribution network, hierarchical collaborative optimization, and resilient self-healing under extreme scenarios, improving the response speed and adaptive regulation capability to the volatility of distributed resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122246708A_ABST
    Figure CN122246708A_ABST
Patent Text Reader

Abstract

This invention discloses a distribution network collaborative optimization control system based on digital twins and multi-agent reinforcement learning, belonging to the field of distribution network optimization control technology. This invention solves the technical problems of existing distribution network control systems, such as lagging interaction between digital twins and physical entities, single-level multi-agent collaboration, and insufficient adaptive regulation capabilities under extreme scenarios. The system includes a twin-decision-evolution closed-loop module, a hierarchical and partitioned hybrid collaborative architecture module, a data-knowledge hybrid driving engine module, and an extreme scenario resilient collaborative control module. By constructing a digital twin that evolves synchronously with the physical entity, implementing hierarchical and partitioned multi-agent collaborative control, and incorporating hybrid driving decision-making with physical knowledge constraints, it achieves resilient collaborative regulation under extreme scenarios, significantly improving the optimization control level, operational safety, and resilience and self-healing capabilities of the distribution network under extreme events.
Need to check novelty before this filing date? Find Prior Art