TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures

2026-08-13

AI Summary

This work addresses the problem of optimally allocating capacity to network nodes under a fixed budget to mitigate cascading failures triggered by local load redistribution. The authors propose TANGCO, a novel approach that, for the first time, integrates graph neural networks with policy gradient reinforcement learning, enabling end-to-end training within a cascading failure simulator. A heuristic anchoring mechanism is introduced to facilitate topology-aware capacity allocation. TANGCO supports cross-graph transferability, allowing pretrained models to be deployed on new networks without fine-tuning. Evaluated across 450 synthetic and 45 real-world networks, the method significantly outperforms existing heuristics on 40 of the real networks, improving robustness by 1.6% to 246%. The training scales nearly linearly with network size, and deployment incurs computational costs comparable to those of heuristic baselines.

Abstract

Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds its capacity fails and sheds its load onto its neighbors, which can trigger a system-wide cascade. We study how to allocate a fixed capacity budget across nodes to resist these cascades under local load redistribution. The problem is difficult because no optimal allocation is known, and the fail-or-survive objective is non-differentiable and piecewise constant, so exact and gradient-based optimization methods do not directly apply. We introduce TANGCO (Topology-Aware Neural Graph-Guided Capacity Optimization), which uses a graph neural network policy trained through the cascade simulator with policy-gradient learning and a heuristic anchor. We evaluate TANGCO on five synthetic graph families and five real networks spanning power, road, air, and Internet topologies. The learned policy improves on the best of four hand-designed heuristics in all 450 synthetic instances and in 40 of 45 real-network conditions, with robustness gains ranging from 1.6% to 246%. The learned policies transfer to unseen graphs within a family and partially across related topologies, and TANGCO$^{pre}$, pre-trained on synthetic graphs, matches per-network training on unseen real networks. Training scales near-linearly with graph size, and TANGCO$^{pre}$ allocates on a new network with no per-target training, matching the deployment cost of a hand-designed heuristic. Free-vector variants without the GNN, stay close to the heuristics, so the graph representation carries the gain beyond numerical search. Finally, analysis of the learned allocations identifies when local risk is sufficient, leads to an improved closed-form heuristic, and reveals the regimes where a topology-aware learned policy remains necessary.

Problem

• cascading failures
• capacity allocation
• network robustness
• load redistribution
• topology-aware optimization

Innovation

• Graph Neural Network
• Cascading Failures
• Capacity Allocation
• Policy Gradient
• Topology-Aware Optimization