Machine learning (ML) algorithms are remarkably good at approximating complex non-linear relationships. Most ML training processes, however, are designed to deliver ML tools with good average performance, but do not offer any guarantees about their worst-case estimation error. For safety-critical systems such as power systems, this places a major barrier for their adoption. So far, approaches could determine the worst-case violations of only trained ML algorithms. To the best of our knowledge, this is the first paper to introduce a neural network training procedure designed to achieve both a good average performance and minimum worst-case violations. Using the Optimal Power Flow (OPF) problem as a guiding application, our approach (i) introduces a framework that reduces the worst-case generation constraint violations during training, incorporating them as a differentiable optimization layer; and (ii) presents a neural network sequential learning architecture to significantly accelerate it. We demonstrate the proposed architecture on four different test systems ranging from 39 buses to 162 buses, for both AC-OPF and DC-OPF applications.

翻译：机器学习(ML)算法在接近复杂的非线性关系方面非常出色。然而,多数ML培训过程的设计是为了提供ML工具,其平均性能良好,但并不保证其最坏的估计错误。对于诸如电力系统等安全关键系统来说,这为采用这些系统设置了一个主要障碍。到目前为止,各种办法可以确定只有经过训练的ML算法最坏的违反情况。据我们所知,这是引入神经网络培训程序的第一个文件,其目的是实现良好的平均性能和最低最坏的违反情况。利用最佳电力流动(OPF)问题作为指导应用,我们的方法(一) 引入一个框架,在培训期间减少最坏的一代限制违规情况,将其纳入一个不同的优化层;以及(二) 提出一个神经网络连续学习结构,以大大加速这种系统。我们为所知,为AC-OPF和DC-OPF应用程序展示了从39大客车到162大客车的四种不同的测试系统的拟议结构。