Power grid key section screening method and system based on reinforcement learning, medium and processor

By constructing a dynamic state space for the power grid based on reinforcement learning, adaptively optimizing evaluation indicators, and simulating complex fault scenarios, the limitations of traditional power grid critical section screening methods are overcome. This enables accurate characterization and real-time response to power grid risks, improving the accuracy and efficiency of critical section screening.

CN121009458APending Publication Date: 2025-11-25CHINA SOUTHERN POWER GRID COMPANY
0 Cites 0 Cited by

Patent Information

Application Number
CN202510878593.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-27
Publication Date
2025-11-25

AI Technical Summary

Technical Problem

Traditional methods for screening critical sections of power grids are ill-suited for handling multi-source dynamic data, lack simulation of complex fault scenarios, and are unable to dynamically balance multi-dimensional optimization objectives. This results in risk assessment results being out of sync with actual operating scenarios and failing to respond in real time to rapid changes in the power grid.

Method used

A reinforcement learning-based approach is adopted, which constructs the dynamic state space of the power grid through graph convolutional neural networks, combines deep Q-networks to assess risks, adaptively optimizes the reward function, uses Monte Carlo tree search to simulate fault scenarios, dynamically adjusts the weights of assessment indicators, and iteratively optimizes model parameters online.

Benefits of technology

It enables efficient processing of multi-source dynamic data, accurately depicts the real-time state of the power grid, simulates complex fault scenarios, dynamically balances multi-dimensional optimization objectives, improves the accuracy and real-time performance of key section selection, and adapts to the needs of complex power grid engineering.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a power grid key section screening method and system based on reinforcement learning, a processor and a medium, and belongs to the technical field of power grid safe operation. According to the method, a power grid dynamic state space is constructed by collecting multi-source data and utilizing a graph convolutional neural network, a partition risk is evaluated in combination with a deep Q network to obtain candidate key sections, meanwhile, a reward function and weight parameters thereof are adaptively optimized, a simulation fault scene is searched through a Monte Carlo tree to calculate a risk index, and the risk index is calculated. And finally, screening out a key section and carrying out online iterative optimization on model parameters. According to the method, the problems that a traditional method is difficult to process multi-source dynamic data, lacks complex fault scene simulation and cannot dynamically balance a multi-dimensional optimization target are solved, the dynamic risk characteristics of the power grid can be accurately described, the accuracy and the real-time performance of key section screening are improved, and effective support is provided for safe and stable operation of the power grid.
Need to check novelty before this filing date? Find Prior Art