arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.08091cs.LGcs.SYeess.SY
收藏

确保具有凸约束的优化问题的DNN解可行性及其在DC最优潮流问题中的应用

Ensuring DNN Solution Feasibility for Optimization Problems with Convex Constraints and Its Application to DC Optimal Power Flow Problems

The Chinese University of Hong Kong(香港中文大学);City University of Hong Kong(香港城市大学);California Institute of Technology(加州理工学院)

Tianyu Zhao, Xiang Pan, Minghua Chen, Steven H. Low

AI总结:

本文提出“预防性学习”框架,通过校准不等式约束和对抗样本感知训练算法,在无需后处理下保证凸约束优化问题的DNN解可行性,应用于DC最优潮流问题实现100%可行性且最优性损失低于0.19%。

摘要:

由于DNN固有的预测误差,在开发用于求解约束优化问题的深度神经网络(DNN)方案时,确保解的可行性是一项关键挑战。本文提出了一种“预防性学习”框架,在满足约束校准的温和条件下,无需后处理即可保证具有凸约束和一般目标函数问题的DNN解可行性。不失一般性,我们仅关注包含不等式约束的问题。我们系统地校准DNN训练中使用的不等式约束,从而预测预测误差并确保最终解保持可行。我们刻画了足以确保普遍可行性的校准幅度和DNN规模。我们提出了一种新的对抗样本感知训练算法,在不牺牲可行性保证的前提下提高DNN的最优性表现。总体而言,该框架提供了两个DNN。第一个通过刻画充分的DNN规模可保证普遍可行性,而另一个通过所提出的训练算法进一步提高最优性并同时保持DNN的普遍可行性。我们将该框架应用于开发DeepOPF+,以解决电网运行中基本的DC最优潮流问题。在IEEE测试用例上的仿真结果表明,与最先进的求解器相比,它在保证100%可行性和在轻载及重载区域实现一致的最优性损失(<0.19%)和加速(高达×228)方面,均优于现有的强DNN基线。我们还将该框架应用于一个非凸问题,并展示了其优于现有方案的性能优势。

英文摘要:

Ensuring solution feasibility is a key challenge in developing Deep Neural Network (DNN) schemes for solving constrained optimization problems, due to inherent DNN prediction errors. In this paper, we propose a ``preventive learning'' framework to guarantee DNN solution feasibility for problems with convex constraints and general objective functions without post-processing, upon satisfying a mild condition on constraint calibration. Without loss of generality, we focus on problems with only inequality constraints. We systematically calibrate inequality constraints used in DNN training, thereby anticipating prediction errors and ensuring the resulting solutions remain feasible. We characterize the calibration magnitudes and the DNN size sufficient for ensuring universal feasibility. We propose a new Adversarial-Sample Aware training algorithm to improve DNN's optimality performance without sacrificing feasibility guarantee. Overall, the framework provides two DNNs. The first one from characterizing the sufficient DNN size can guarantee universal feasibility while the other from the proposed training algorithm further improves optimality and maintains DNN's universal feasibility simultaneously. We apply the framework to develop DeepOPF+ for solving essential DC optimal power flow problems in grid operation. Simulation results over IEEE test cases show that it outperforms existing strong DNN baselines in ensuring 100% feasibility and attaining consistent optimality loss ($<$0.19%) and speedup (up to $\times$228) in both light-load and heavy-load regimes, as compared to a state-of-the-art solver. We also apply our framework to a non-convex problem and show its performance advantage over existing schemes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑