发表机构
Dartmouth College; Hong Kong University of Science and Technology (Guangzhou); University of Alberta（达特茅斯学院; 香港科技大学（广州）; 阿尔伯塔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ML-OPF-Bench统一基准，评估机器学习求解最优潮流，发现精度非可行性指标，后处理关键，揭示速度-精度-可行性权衡，开源Python包。
AI 中文摘要
机器学习（ML）方法有望为最优潮流（OPF）提供快速求解过程。然而，现有研究中不一致的测试案例、实现方式和评估指标，使得确定哪些算法进展对实际部署最为关键变得困难。为此，我们提出了ML-OPF-Bench，一个用于交流和直流OPF的统一基准，它在一致的流程下评估代表性ML算法，在不同系统规模、分布偏移和资源预算下对其进行压力测试，并通过多目标框架对其进行排名。我们发现，仅凭预测精度并不能可靠地指示运行可行性。在重载、拥堵的条件下，即使是最强的分布内性能表现者也会失去其优势，而可行性主要依靠强制执行目标约束的后处理来维持，而非底层纯ML预测器。数据规模扩展表明，预测精度和约束违反遵循不同的轨迹，而计算规模扩展则表明收益递减，且更大的模型并不始终表现更好。这些结果揭示了ML方法在速度、精度和可行性之间的关键权衡，并为未来ML-OPF设计提供了实用指导。我们将该基准作为可扩展的Python包开源，以便集成新的基于学习的OPF算法，并使其在与现有基线相同的标准下进行评估。
英文摘要
Machine Learning (ML) methods promise a fast solution process for Optimal Power Flow (OPF). While inconsistent test cases, implementations, and evaluation metrics across existing studies make it challenging to determine which algorithmic advances are most critical for real-world deployment. To this end, we propose ML-OPF-Bench, a unified benchmark for AC- and DC-OPF that evaluates representative ML algorithms under a consistent pipeline, stress-tests them across system sizes, distribution shifts, and resource budgets, and ranks them with a multi-objective framework. We find that prediction accuracy alone is not a reliable indicator of operational feasibility. Under heavily loaded, congested conditions, even the strongest in-distribution performers lose their advantage, while feasibility is maintained largely by post-processing that enforces the target constraints rather than by the underlying pure ML predictor. Data scaling shows that prediction accuracy and constraint violations follow different trajectories, whereas compute scaling shows that returns diminish and that larger models do not consistently perform better. These results expose critical trade-offs among ML methods' speed, accuracy, and feasibility, and offer practical guidance for future ML-OPF design. We open-source the benchmark as an extensible Python package for integrating new learning-based OPF algorithms and evaluating them under the same standard as the existing baselines.
Comments25 pages, 9 figures, in submission. Code available at https://github.com/XinyiLiu04/ML-OPF-Bench; Datasets available at https://huggingface.co/datasets/xinyi-liu/ML-OPF-Bench
