Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications

TL;DR

This paper introduces a formal verification framework for neural networks in power systems, enabling safety assessment, adversarial example detection, and increased trust for practical deployment.

Contribution

It develops a mixed integer linear programming-based method for verifying neural network safety and robustness in power system applications, addressing scalability and accuracy.

Findings

Successfully verified neural networks on IEEE bus systems

Identified adversarial examples in power system neural networks

Enhanced trust in neural network deployment for power systems

Abstract

This paper presents for the first time, to our knowledge, a framework for verifying neural network behavior in power system applications. Up to this moment, neural networks have been applied in power systems as a black-box; this has presented a major barrier for their adoption in practice. Developing a rigorous framework based on mixed integer linear programming, our methods can determine the range of inputs that neural networks classify as safe or unsafe, and are able to systematically identify adversarial examples. Such methods have the potential to build the missing trust of power system operators on neural networks, and unlock a series of new applications in power systems. This paper presents the framework, methods to assess and improve neural network robustness in power systems, and addresses concerns related to scalability and accuracy. We demonstrate our methods on the IEEE 9-bus, 14-bus, and 162-bus systems, treating both N-1 security and small-signal stability.