Minimizing Worst-Case Violations of Neural Networks
This addresses safety concerns for power systems by minimizing worst-case errors, though it is incremental as it builds on existing methods for specific applications.
The paper tackles the problem of neural networks lacking worst-case performance guarantees in safety-critical systems like power grids, by introducing a training procedure that reduces worst-case constraint violations while maintaining good average performance, demonstrated on power flow problems with test systems up to 162 buses.
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.