DNN-based policies for stochastic AC OPF

DNN-based policies for stochastic AC OPF
复制标题

基于 DNN 的随机 AC OPF 策略

DOI:
10.1016/j.epsr.2022.108563
复制
发表时间:
2022
影响因子:
3.9
通讯作者:
Kekatos, Vassilis
Kekatos, Vassilis
中科院分区:
工程技术3区
文献类型:
--
作者:
Gupta, Sarthak;Misra, Sidhant;Deka, Deepjyoti;Kekatos, Vassilis

文献摘要

参考文献

被引文献

相似文献

负荷和可再生能源的不确定性日益增加,对现代电网的安全和优化运行提出了突出的挑战。随机最优潮流(SOPF)公式通过计算在不确定性下保持可行性的调度决策和控制策略,提供了一种处理这些不确定性的机制。大多数SOPF公式考虑简单的控制策略,例如仿射策略,它在数学上很简单,与当前实践中使用的许多策略相似。受机器学习(ML)算法的有效性和一般控制策略对成本和约束执行的潜在好处的激励,我们提出了一种基于深度神经网络(DNN)的策略,该策略可以实时预测响应不确定性的发电机调度决策。DNN的权重是使用随机原始对偶更新来学习的,该更新在不需要事先生成训练标签的情况下解决了SOPF,并且可以明确地说明SOPF中的可行性约束。DNN策略相对于更简单的策略的优势,以及它们在执行安全限制和产生接近最优解方面的有效性,在许多测试用例的机会约束公式的背景下得到了证明。
A prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.
DOI: 10.1109/ptc.2019.8810819
发表时间: 2019-02
期刊: 2019 IEEE Milan PowerTech
影响因子: --
作者:
Deepjyoti Deka;Sidhant Misra
通讯作者: Deepjyoti Deka;Sidhant Misra
DOI: 10.1109/tsg.2017.2654220
发表时间: 2016-08
影响因子: 9.6
作者:
L. M. Lopez-Ramos;V. Kekatos;A. Marques;G. Giannakis
通讯作者: L. M. Lopez-Ramos;V. Kekatos;A. Marques;G. Giannakis
DOI: 10.1109/naps.2014.6965430
发表时间: 2014
期刊: 2014 North American Power Symposium (NAPS)
影响因子: --
作者:
V. Kekatos;G. Wang;G. Giannakis
通讯作者: G. Giannakis
机会约束交流最优潮流:多项式混沌方法
DOI: --
发表时间: 2019
影响因子: 6.6
作者:
T. Mühlpfordt;Line A. Roald;V. Hagenmeyer;T. Faulwasser;Sidhant Misra
通讯作者: Sidhant Misra
使用代理控制智能逆变器:基于机会约束 DNN 的方法
DOI: 10.1109/tsg.2021.3132029
发表时间: 2022
影响因子: 9.6
作者:
Gupta, Sarthak;Kekatos, Vassilis;Jin, Ming
通讯作者: Jin, Ming