Skip to main content
QUICK REVIEW

[论文解读] Learning to Solve AC Optimal Power Flow by Differentiating through Holomorphic Embeddings

Henning Lange, Bingqing Chen|arXiv (Cornell University)|Dec 16, 2020
Power System Optimization and Stability参考文献 31被引用 7
一句话总结

本文提出了一种可微分神经网络框架,通过反向传播穿过全纯嵌入潮流(HELM)求解器,学习求解交流最优潮流(AC-OPF),在确保物理可行性的同时满足非线性潮流方程。该方法相比传统求解器实现12倍的推理速度提升和40%更高的鲁棒性,在200节点系统上99.86%的情况下产生可行解。

ABSTRACT

Alternating current optimal power flow (AC-OPF) is one of the fundamental problems in power systems operation. AC-OPF is traditionally cast as a constrained optimization problem that seeks optimal generation set points whilst fulfilling a set of non-linear equality constraints -- the power flow equations. With increasing penetration of renewable generation, grid operators need to solve larger problems at shorter intervals. This motivates the research interest in learning OPF solutions with neural networks, which have fast inference time and is potentially scalable to large networks. The main difficulty in solving the AC-OPF problem lies in dealing with this equality constraint that has spurious roots, i.e. there are assignments of voltages that fulfill the power flow equations that however are not physically realizable. This property renders any method relying on projected-gradients brittle because these non-physical roots can act as attractors. In this paper, we show efficient strategies that circumvent this problem by differentiating through the operations of a power flow solver that embeds the power flow equations into a holomorphic function. The resulting learning-based approach is validated experimentally on a 200-bus system and we show that, after training, the learned agent produces optimized power flow solutions reliably and fast. Specifically, we report a 12x increase in speed and a 40% increase in robustness compared to a traditional solver. To the best of our knowledge, this approach constitutes the first learning-based approach that successfully respects the full non-linear AC-OPF equations.

研究动机与目标

  • 应对由于可再生能源大规模接入,导致的大型、时敏AC-OPF求解挑战。
  • 克服传统求解器因非线性潮流方程中出现虚假根而导致的脆弱性问题。
  • 开发一种基于学习的方法,在尊重完整非线性AC-OPF约束的同时,实现快速、可扩展的推理。
  • 实现端到端训练神经策略,同时满足等式约束(潮流方程)和不等式约束(电压、机组组合)。

提出的方法

  • 将可微分全纯嵌入潮流(HELM)求解器作为神经网络中的可微分计算层使用。
  • 通过HELM求解器反向传播梯度,训练神经策略网络,实现从系统负荷到最优发电出力分配的映射。
  • 集成对偶变量网络,通过拉格朗日松弛法强制实施凸约束(如电压幅值限制)和非凸约束(如机组组合)。
  • 使用基于梯度的学习方法端到端优化整体拉格朗日函数,确保推理过程中满足约束条件。
  • 利用全纯嵌入技术稳定收敛过程,避免训练和推理过程中出现虚假解。
  • 通过结合成本最小化和潮流可行性,利用基于功率级数系数的损失函数指导收敛,训练模型。

实验结果

研究问题

  • RQ1是否可以使用可微分潮流求解器训练神经网络求解AC-OPF,同时严格遵守完整的非线性潮流方程?
  • RQ2与MATPOWER的内点法求解器(MIPS)相比,所提方法是否能实现更高的鲁棒性和更快的推理速度?
  • RQ3所学策略在不同负荷条件下是否具有良好泛化能力,同时保持物理可行性?
  • RQ4该方法在统一可微分框架下,对凸约束(如电压限值)和非凸约束(如机组组合)的强制执行程度如何?
  • RQ5尽管可行性很高,为何所学策略产生的解成本仍存在次优性?该最优性差距是否可被消除?

主要发现

  • 所提方法相比传统MATPOWER混合整数规划求解器(MIPS)实现12倍的推理时间加速。
  • 该方法展现出99.86%的鲁棒性,在6,000个测试案例中成功生成可行解5,992个,而MIPS求解器仅为61%。
  • 所学神经策略可靠地满足完整的非线性AC潮流方程,避免了传统投影梯度法常遇到的虚假根问题。
  • 尽管可行性高,所学解的平均发电成本比MIPS求解器找到的最优解高出约29%。
  • 该方法通过可微分对偶变量网络成功强制实施了凸约束(电压幅值)和非凸约束(机组组合)。
  • 模型在训练过程中表现出瞬态失败,解在短时间内违反潮流可行性,可能源于成本最小化与收敛稳定性之间的权衡。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。