Stability evaluation method and device of power system, computer equipment, readable storage medium and program product

By extracting and fusing features from steady-state, fault, and topology data of power systems, and combining them with a stability assessment network optimized by dynamic weights, the problem of insufficient reliability in transient stability assessment in existing methods is solved. This achieves efficient collaborative optimization of stability and margin prediction, improving assessment accuracy and robustness.

CN121436728APending Publication Date: 2026-01-30ELECTRIC POWER RES INST CHINA SOUTHERN POWER GRID CO LTD +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202511655571.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-12
Publication Date
2026-01-30

AI Technical Summary

Technical Problem

Existing deep learning-based transient stability assessment methods for power systems fail to fully explore the potential correlation between transient stability discrimination and margin prediction, resulting in insufficient reliability and stability of the assessment results.

Method used

By extracting features from steady-state operation data, fault process data, and grid topology data of the power system, and using operations such as linear transformation, latent variable sampling, and low-rank interaction, fused latent variable features are generated. These features are then used in the stability assessment network to collaboratively optimize stability prediction and margin prediction, and the weights are dynamically adjusted to optimize the model loss function.

Benefits of technology

It improves the accuracy and robustness of power system stability assessment, and enables efficient and reliable stability judgment in heterogeneous data scenarios.

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

Abstract

The invention relates to a stability evaluation method and device of a power system, computer equipment, a computer readable storage medium and a computer program product. Comprising the following steps: for any iteration training, acquiring data from a stability data set of a power system, and performing feature extraction on steady-state operation data, fault process data and power grid topology data to obtain fusion latent variable features; inputting the fused latent variable features into a stability evaluation network to obtain a stability result and a margin result; determining stability loss and margin loss based on the stability result, the stability true value, the margin result and the margin true value; determining a stability weight and a margin weight; based on the stability loss, the margin loss, the KL divergence regular term, the stability weight and the margin weight, determining the total loss of the model, further judging whether a preset condition is met or not, and if not, continuing iterative training; if yes, the training is completed. According to the method, stability prediction and margin prediction can be collaboratively optimized.
Need to check novelty before this filing date? Find Prior Art