DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems
DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems
复制标题
DeepOPF：一种可行性优化的深度神经网络方法用于交流最优潮流问题
DOI：
10.1109/jsyst.2022.3201041
复制
发表时间：
2020-07
影响因子：
4.4
通讯作者：
Xiang Pan;Minghua Chen;Tianyu Zhao;S. Low
中科院分区：
文献类型：
--
作者：
Xiang Pan;Minghua Chen;Tianyu Zhao;S. Low
为了应对可再生能源发电和灵活负载日益增加的不确定性，电网运营商需要更频繁地解决替代电流最优潮流（AC-OPF）问题，以实现高效可靠的运行。在本文中，我们开发了一种称为 DeepOPF 的深度神经网络 (DNN) 方法，用于解决 AC-OPF 问题，所需时间仅为传统迭代求解器的一小部分。应用机器学习技术解决 AC-OPF 问题的一个关键困难在于确保所获得的解决方案尊重平等和不平等的物理和操作约束。 DeepOPF 概括了我们之前研究中的预测和重建过程，首先训练 DNN 模型来预测一组独立的运行变量，然后通过求解潮流方程直接计算其余变量。这种方法不仅保留了潮流平衡等式约束，还减少了 DNN 预测的变量数量，从而减少了所需的神经元数量和训练数据。然后，DeepOPF 在训练过程中采用零阶梯度估计技术的惩罚方法来保证不等式约束。我们还根据所需的近似精度驱动调整 DNN 大小的条件，以衡量其泛化能力。它为使用 DNN 解决 AC-OPF 问题提供了理论依据。 IEEE 30/118/300 总线的仿真结果和综合 2000 总线测试用例证明了惩罚方法的有效性。他们还表明，与最先进的迭代求解器相比，DeepOPF 将计算时间加快了两个数量级，但代价是成本差异 < 0.2%。
To cope with increasing uncertainty from renewable generation and flexible load, grid operators need to solve alternative current optimal power flow (AC-OPF) problems more frequently for efficient and reliable operation. In this article, we develop a deep neural network (DNN) approach, called DeepOPF, for solving AC-OPF problems in a fraction of the time used by conventional iterative solvers. A key difficulty for applying machine learning techniques for solving AC-OPF problems lies in ensuring that the obtained solutions respect the equality and inequality physical and operational constraints. Generalized a prediction-and-reconstruction procedure in our previous studies, DeepOPF first trains a DNN model to predict a set of independent operating variables and then directly compute the remaining ones by solving the power flow equations. Such an approach not only preserves the power-flow balance equality constraints but also reduces the number of variables to be predicted by the DNN, cutting down the number of neurons and training data needed. DeepOPF then employs a penalty approach with a zero-order gradient estimation technique in the training process toward guaranteeing the inequality constraints. We also drive a condition for tuning the DNN size according to the desired approximation accuracy, which measures its generalization capability. It provides theoretical justification for using DNN to solve AC-OPF problems. Simulation results for IEEE 30/118/300-bus and a synthetic 2000-bus test cases demonstrate the effectiveness of the penalty approach. They also show that DeepOPF speeds up the computing time by up to two orders of magnitude as compared to a state-of-the-art iterative solver, at the expense of $< $0.2% cost difference.