论文标题
具有泛化的DCOPF的凸神经网络求解器
A Convex Neural Network Solver for DCOPF with Generalization Guarantees
论文作者
论文摘要
直流最佳功率流（DCOPF）问题是电力系统操作和计划中的基本问题。随着电力系统中不确定的可再生资源的高度渗透，需要在大量场景中反复解决DCOPF，这在计算上可能具有挑战性。作为迭代求解器的替代方法，通常对神经网络进行训练，并用于求解DCOPF。这些方法可以提供计算时间降低的数量级，但是它们不能保证概括，而小训练错误并不意味着测试错误很小。在这项工作中，我们提出了一种用于解决DCOPF的新型算法，以保证概括性能。首先，通过利用DCOPF问题的凸度，我们训练输入凸神经网络。其次，我们根据KKT最佳条件构建训练损失。通过结合这两种技术，训练有素的模型具有可证明的概括属性，其中小训练错误意味着小的测试错误。在实验中，与端到端模型相比，我们的算法将解决方案的最佳比率提高了五倍。
The DC optimal power flow (DCOPF) problem is a fundamental problem in power systems operations and planning. With high penetration of uncertain renewable resources in power systems, DCOPF needs to be solved repeatedly for a large amount of scenarios, which can be computationally challenging. As an alternative to iterative solvers, neural networks are often trained and used to solve DCOPF. These approaches can offer orders of magnitude reduction in computational time, but they cannot guarantee generalization, and small training error does not imply small testing errors. In this work, we propose a novel algorithm for solving DCOPF that guarantees the generalization performance. First, by utilizing the convexity of DCOPF problem, we train an input convex neural network. Second, we construct the training loss based on KKT optimality conditions. By combining these two techniques, the trained model has provable generalization properties, where small training error implies small testing errors. In experiments, our algorithm improves the optimality ratio of the solutions by a factor of five in comparison to end-to-end models.
