Cost Restrained Hybrid Attacks in Power Grids

TL;DR

This paper introduces a cost-constrained hybrid attack model on power grids, proposing new attack centrality metrics and demonstrating that optimized attacks outperform greedy methods, with local centrality sometimes surpassing global approaches under cost limits.

Contribution

It develops a novel attack centrality metric and applies Particle Swarm Optimization for optimal hybrid attacks, revealing insights into attack strategies under cost constraints.

Findings

Optimal hybrid attack is more effective than greedy attack.

Local attack centrality can outperform global centrality under cost constraints.

Simulation on IEEE test data validates the proposed methods.

Abstract

The frequent occurrences of cascading failures in power grids have been receiving continuous attention in recent years. An urgent task for us is to understand the cascading failure vulnerability of power grids against various kinds of attacks. We consider a cost restrained hybrid attack problem in power grids, in which both nodes and links are targeted with a limited total attack cost. We propose an attack centrality metric for a component (node or link) based on the consequence and cost of the removal of the component. Depending on the width of cascading failures considered, the attack centrality can be a local or global attack centrality. With the attack centrality, we further provide a greedy hybrid attack, and an optimal hybrid attack with the Particle Swarm Optimization (PSO) framework. Simulation results on IEEE bus test data show that the optimal hybrid attack is more efficient than the greedy hybrid attack. Furthermore, we find counterintuitively that the local centrality based algorithms are better than the global centrality based ones when the cost constraint is considered in the attack problem.