一种基于条件生成对抗网络与迁移学习的暂态电压稳定超前判别方法
By combining conditional generative adversarial networks with transfer learning, the problem of fast and accurate transient voltage stability judgment in power systems is solved, achieving efficient forward judgment of transient voltage stability and improving the model's prediction accuracy and anti-interference capability.
CN116822361BActive Publication Date: 2026-07-17SICHUAN UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SICHUAN UNIV
- Filing Date
- 2023-06-25
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies cannot quickly and accurately determine the transient voltage stability of power systems. Traditional methods involve large amounts of calculation and are time-consuming, failing to meet the needs of rapid response in power systems.
Method used
By employing a method based on conditional generative adversarial networks (CGAN) and transfer learning, a transient voltage stability prediction model is constructed through sample set expansion and feature mapping to achieve advance discrimination.
Benefits of technology
While balancing speed and accuracy, it achieves advanced discrimination of transient voltage stability, improves the model's prediction accuracy and anti-interference ability, and reduces training time costs.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116822361B_ABST
Abstract
本发明公开了一种基于条件生成对抗网络与迁移学习的暂态电压稳定超前判别方法，步骤S1、以系统量测所获得的暂态电压稳定和失稳数据集作为原始样本训练CGAN网络，完成暂态电压样本集的定向扩增；S2、基于迁移学习构建暂态电压稳定预测模型：利用迁移学习继承CGAN中生成器预训练参数，构建预测模型；S3、基于预测模型的暂态电压预测：将扩增样本集作为预测模型训练集，利用暂态电压前一秒数据对后十秒内数据进行预测，并进行预测效果评估；S4、基于电压预测数据的暂态电压判别：根据暂态电压后十秒内预测数据，利用工程判据实现暂态电压稳定超前判别，并进行判别效果评估。该方法在兼顾快速性与准确性的情况下实现对暂态电压稳定的超前判别。
Need to check novelty before this filing date? Find Prior Art