arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.01545eess.SYcs.SY
收藏

迈向数据驱动的多阶段最优潮流

Towards Data-Driven Multi-Stage OPF

Oleksii Molodchyk, Philipp Schmitz, Alexander Engelmann, Karl Worthmann, Timm Faulwasser

AI总结:

本文提出一种数据驱动的多阶段最优潮流方法,利用系统与控制领域的最新成果直接从数据构建优化问题,绕过网络拓扑识别步骤,并在118母线系统上验证了其性能优于经典基于识别的方法。

摘要:

大规模电力系统的运行通常通过数值优化提前进行调度。然而,这需要电网拓扑、线路参数和母线规格的模型。经典方法首先识别网络拓扑,即互连图及相关的阻抗。然后通过求解围绕该模型构建的多阶段最优潮流(OPF)问题来计算发电计划。在本文中,我们探索了数据驱动方法用于多阶段最优潮流的前景。具体来说,我们利用系统与控制领域的最新发现,绕过识别步骤,直接从数据构建优化问题。我们在一个118母线系统上展示了所提方法的性能,并将其与基于识别的经典方法进行了比较。

英文摘要:

The operation of large-scale power systems is usually scheduled ahead via numerical optimization. However, this requires models of grid topology, line parameters, and bus specifications. Classic approaches first identify the network topology, i.e., the graph of interconnections and the associated impedances. The power generation schedules are then computed by solving a multi-stage optimal power flow (OPF) problem built around the model. In this paper, we explore the prospect of data-driven approaches to multi-stage optimal power flow. Specifically, we leverage recent findings from systems and control to bypass the identification step and to construct the optimization problem directly from data. We illustrate the performance of our method on a 118-bus system and compare it with the classical identification-based approach.

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。

↑