A virtual power plant climbing capacity dynamic approval method based on AGC performance index

By generating a multi-source node power allocation manifold through phase space reconstruction and optimal transmission theory, and combining multi-agent reinforcement learning and rainflow counting method, the accuracy of virtual power plant ramp-up capability assessment and equipment fatigue damage issues are resolved, thus achieving real reliability and safety of high-frequency AGC control for virtual power plant clusters.

CN122065016BActive Publication Date: 2026-07-14HEFEI POWER SUPPLY COMPANY OF STATE GRID ANHUI ELECTRIC POWER +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HEFEI POWER SUPPLY COMPANY OF STATE GRID ANHUI ELECTRIC POWER
Filing Date
2026-04-21
Publication Date
2026-07-14

AI Technical Summary

Technical Problem

Existing technologies cannot accurately quantify the transient ramp-up capability of virtual power plants on extremely short time scales, nor can they dynamically map the actual capacity derating of equipment, leading to falsely advertised frequency regulation capabilities and scheduling default risks. Traditional evaluation mechanisms also ignore the microscopic fatigue damage of equipment.

Method used

High-frequency transient ramp-up features of the equipment are extracted by phase space reconstruction. Dynamic response strategies are generated by combining optimal transmission theory and multi-agent reinforcement learning. Fatigue damage is quantified by rainflow counting method, and the remaining available capacity is dynamically reduced.

Benefits of technology

It enables precise capture of the high-frequency transient ramping potential of virtual power plants, eliminates phase delay and spatial allocation distortion, ensures the safety of control commands and the health of equipment throughout its entire life cycle, and improves the scheduling accuracy and reliability of virtual power plant clusters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122065016B_ABST
    Figure CN122065016B_ABST
Patent Text Reader

Abstract

The application discloses an AGC performance index-based virtual power plant climbing capacity dynamic approval method and relates to the technical field of virtual power plant dispatching and power system control. The method comprises the following steps: reconstructing the phase space of distributed resources, extracting chaotic characteristics, generating a basic climbing characteristic set, generating a multi-source node power distribution manifold by using optimal transmission theory, converting the AGC index into a dynamic repulsive potential field based on a control barrier function, and solving an optimal response strategy in the manifold by using multi-agent reinforcement learning; and calculating the power fluctuation fatigue damage degree by using the rain flow counting method and dynamically reducing the remaining available capacity. The application is used to solve the problems of low precision of traditional static approval, phase distortion of massive resource response, lack of physical safety constraints in AI regulation and control, and inability to perceive the life attenuation of equipment under high-frequency frequency modulation working conditions, thereby causing dispatching default.
Need to check novelty before this filing date? Find Prior Art