arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.13486math.OC
收藏

基于参数近似的自监督学习用于安全约束直流最优潮流

Self-Supervised Learning of Parametric Approximation for Security-Constrained DC-OPF

Escuela Politécnica Nacional(国立理工学院);Purdue University(普渡大学)

Anderson Anrrango, André Quisaguano, Gonzalo E. Constante-Flores, Can Li

AI总结:

本文提出了一种基于参数近似的自监督学习方法,用于高效解决安全约束直流最优潮流问题,通过图神经网络预测参数并优化,实现高精度调度和低误差的电力系统运行。

摘要:

本文介绍了一种自监督学习框架,用于使用参数线性模型近似安全约束直流最优潮流(SC-DCOPF)问题。该方法在保持直流潮流的物理结构的同时,引入了依赖需求的可调参数,用于扩展输电线路限制。这些参数通过图神经网络预测,并通过可微层进行优化,使得可以直接从故障成本中进行训练而无需标注数据。该框架将预-后故障优化层整合到隐式损失函数中。在基准系统上的数值实验表明,所提出的方法在调度精度、成本近似误差和数据效率方面表现优异,优于半监督和端到端基线。这种可扩展且可解释的方法为实时安全电力系统运行提供了一种有前景的解决方案。

英文摘要:

This paper introduces a self-supervised learning framework for approximating the Security-Constrained DC Optimal Power Flow (SC-DCOPF) problem using a parametric linear model. The approach preserves the physical structure of the DC-OPF while incorporating demand-dependent tunable parameters that scale transmission line limits. These parameters are predicted via a Graph Neural Network and optimized through differentiable layers, enabling direct training from contingency costs without requiring labeled data. The framework integrates pre- and post-contingency optimization layers into an implicit loss function. Numerical experiments on benchmark systems demonstrate that the proposed method achieves high dispatch accuracy, low cost approximation error, and strong data efficiency, outperforming semi-supervised and end-to-end baselines. This scalable and interpretable approach offers a promising solution for real-time secure power system operations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑