Learning to solve DCOPF: A duality approach

Learning to solve DCOPF: A duality approach
复制标题

学习解决 DCOPF:二元性方法

DOI:
10.1016/j.epsr.2022.108595
复制
发表时间:
2022
影响因子:
3.9
通讯作者:
Zhang, Baosen
Zhang, Baosen
中科院分区:
工程技术3区
文献类型:
--
作者:
Chen, Yize;Zhang, Ling;Zhang, Baosen

文献摘要

参考文献

被引文献

相似文献

最优潮流问题是电力系统运行和控制的基本工具。由于不确定的可再生资源的增加,快速准确地解决OPF问题提供了重要的价值,因为需要考虑大量的负载和发电场景。最近的工作集中在使用神经网络来代替迭代求解器,以加快计算的最优潮流问题。一个关键的挑战是确保解决方案满足OPF问题中的硬约束,这在端到端机器学习中很难做到。在这项工作中,通过利用丰富的对偶理论和物理解释的OPF,我们设计了一个基于学习的方法,具有理论特征的约束满足。这种方法比标准求解器快一个数量级,并且在可行性和最优性方面比其他学习方法表现得更好。
The optimal power flow (OPF) problem is a fundamental tool in power system operation and control. Because of the increase in uncertain renewable resources, solving OPF problems fast and accurately provides significant values because of a large number of load and generation scenarios need to be accounted for. Recent works have focused on using neural networks to replace iterative solvers to speed up the computation of OPF problems. A critical challenge is to ensure solutions satisfy the hard constraints in the OPF problem, which is difficult to do in end-to-end machine learning. In this work, by leveraging the rich theory of duality and physical interpretations of OPF, we design a learning-based approach that has theoretical characterizations of constraint satisfaction. This approach is an order of magnitude faster than standard solvers, and performs much better than other learning methods in terms of feasibility and optimality.
线性规划中的敏感性分析:小心!
DOI: 10.1016/s0377-2217(96)00172-5
发表时间: 1997
影响因子: 6.4
作者:
B. Jansen;J. Jong;C. Roos;T. Terlaky
通讯作者: T. Terlaky
DOI: 10.1007/s00041-008-9035-z
发表时间: 2008-12-01
影响因子: 1.2
作者:
Blumensath, Thomas;Davies, Mike E.
通讯作者: Davies, Mike E.
黎曼流形上的投影梯度下降及其在在线电力系统优化中的应用
DOI: 10.1109/allerton.2016.7852234
发表时间: 2016
期刊: 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
影响因子: --
作者:
Adrian Hauswirth;S. Bolognani;G. Hug;F. Dörfler
通讯作者: F. Dörfler
DeepOPF:一种用于直流最佳潮流的深度神经网络方法,以确保可行性
DOI: --
发表时间: 2020
期刊: IEEE International Conference on Smart Grid Communications
影响因子: --
作者:
Tianyu Zhao;Xiang Pan;Minghua Chen;Andreas Venzke;S. Low
通讯作者: S. Low
主动分发系统的快速概率托管容量分析
DOI: 10.1109/tsg.2020.3038651
发表时间: 2021
影响因子: 9.6
作者:
Taheri, Sina;Jalali, Mana;Kekatos, Vassilis;Tong, Lang
通讯作者: Tong, Lang