用深度神经网络快速求解电网开关优化，保证实时可行且省电。
Dispatch-Aware Deep Neural Network for Optimal Transmission Switching: Toward Real-Time and Feasibility Guaranteed Operation
- 设计可微分的神经网络，直接预测线路开关状态并内置电网约束
- 训练后单次推理时间与传统潮流计算相当，大电网仍稳定有效
- 适合需要实时调度的电力系统，尤其适用于超大规模电网
最优输电切换（OTS）通过选择性断开输电线路提升最优潮流（OPF）性能，但其混合整数规划形式显著增加计算复杂度，尤其在大型电网中。为此，我们提出一种调度感知的深度神经网络（DA-DNN），在不依赖预解标签的情况下加速直流最优输电切换（DC-OTS）。DA-DNN预测线路状态，并通过可微分的直流最优潮流（DC-OPF）层，以生成成本作为损失函数，确保训练和推理过程中所有物理网络约束均被满足。此外，采用定制化的权重-偏置初始化策略，使每次前向传播从第一轮迭代起即保持可行，从而在大型电网上实现稳定学习。模型训练完成后，所提方法在与求解直流潮流（DCOPF）相同的时间内，生成一个可证明可行的拓扑与调度组合，而传统混合整数求解器则变得不可行。结果表明，该方法成功捕捉了OTS的经济优势，同时具备良好可扩展性。
原文摘要 · Abstract (English)
Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To deal with this, we propose a dispatch-aware deep neural network (DA-DNN) that accelerates DC-OTS without relying on pre-solved labels. DA-DNN predicts line states and passes them through a differentiable DC-OPF layer, using the resulting generation cost as the loss function so that all physical network constraints are enforced throughout training and inference. In addition, we adopt a customized weight-bias initialization that keeps every forward pass feasible from the first iteration, which allows stable learning on large grids. Once trained, the proposed DA-DNN produces a provably feasible topology and dispatch pair in the same time as solving the DCOPF, whereas conventional mixed-integer solvers become intractable. As a result, the proposed method successfully captures the economic advantages of OTS while maintaining scalability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。