Verification of Neural Network Behaviour: Formal Guarantees for Power System Applications
It addresses the lack of trust from power system operators in neural networks, which is a domain-specific problem, by providing formal guarantees, though it is incremental as it applies existing verification methods to a new application area.
This paper tackles the problem of verifying neural network behavior in power systems by developing a framework based on mixed integer linear programming to determine input ranges for safe/unsafe classifications and identify adversarial examples, demonstrated on IEEE 9-bus, 14-bus, and 162-bus systems for N-1 security and small-signal stability.
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.