OPF-Learn
收藏arXiv2021-11-04 更新2024-08-06 收录
下载链接：
http://arxiv.org/abs/2111.01228v2
下载链接
链接失效反馈官方服务：
资源简介：
OPF-Learn是一个用于创建交流最优电力流（AC OPF）数据集的开源框架，由华盛顿大学的研究团队开发。该数据集包含50,000个样本，覆盖了AC OPF可行区域的大范围。数据集通过从包含AC OPF可行集的凸集中均匀采样负载配置文件来创建，对于每个不可行点，使用不可行性证书减少凸集。该数据集旨在通过提供更广泛的操作条件代表性，改进机器学习模型在AC OPF问题上的性能，特别是在处理可再生能源生成的不确定性方面。
OPF-Learn is an open-source framework for constructing alternating current optimal power flow (AC OPF) datasets, developed by a research team at the University of Washington. This dataset contains 50,000 samples covering a wide range of the feasible region of AC OPF problems. It is generated by uniformly sampling load profiles from a convex set that encompasses the AC OPF feasible set, and the convex set is pruned using infeasibility certificates for each infeasible point during the sampling process. This dataset aims to improve the performance of machine learning models on AC OPF tasks by providing representative coverage of a broader set of operating conditions, particularly when addressing the uncertainty of renewable energy generation.
提供机构：
华盛顿大学
创建时间：
2021-11-02
