A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis

When considering attacks against the power grid, one of the most effective approaches could be the attack to the transmission lines that leads to large cascading failures. Hence, the problem of locating the most critical or vulnerable transmission lines for a Power Grid Cascading Failure (PGCF) has drawn much attention from the research society. There exist many deterministic solutions and stochastic approximation algorithms aiming to analyze the power grid vulnerability. However, it has been challenging to reveal the correlations between the transmission lines for the critical line identification. In this paper, we propose a novel approach that learns such correlations, based on self-supervised learning and the self-attention mechanism, which is inspired by the Transformer model for natural language processing (NLP). Once the correlations are learned, a ranking algorithm is introduced for the critical line identification. With extensive experiments comparing our approach versus 2 other benchmark algorithms, it is proven that the proposed Dual PGCF model provides a novel and effective solution for critical line identification.