通过系统感知图边界学习检测智能电网中的虚假数据注入与不稳定运行

中文摘要 AI 辅助

信息物理电力系统愈发依赖数据驱动工具检测不稳定状态并支撑电网可靠运行。然而，当不稳定运行配置在模型开发阶段较为罕见、敏感或无法获取时，可靠的稳定性预测难度很大，因为安全且大规模地收集此类数据通常不切实际。与此同时，虚假数据注入（False Data Injection, FDI）攻击可操纵上报的系统参数，触发虚假的不稳定告警或掩盖不安全运行状态，而分散式智能电网控制（Decentral Smart Grid Control, DSGC）系统中的这类威胁在很大程度上仍未被探索。这些挑战很少被共同解决，导致稳定性预测与攻击检测之间存在空白，本工作旨在填补这一空白。\n本文提出StarGNN，这是一种图学习框架，它仅从干净的稳定配置中学习稳定运行区域，并使用单一异常分数标记那些不应被视为安全运行证据的上报配置，覆盖真实不稳定状态和未见过的FDI操纵两种情况。每种配置都被表示为生产者-消费者星型图，并由角色感知图神经网络处理，同时通过扰动反应时间和价格响应参数生成受物理约束的伪负样本，以替代无法获取的不稳定数据和攻击数据。框架仅使用在留出的稳定数据上校准的单一阈值，无需针对任务或攻击进行特定调整。\n在9种未见过的FDI场景下进行评估，StarGNN对稳定配置上的攻击检测率在0.780到0.973之间，对不稳定配置的攻击后不稳定召回率保持在0.972到0.999之间，针对更强的自适应攻击者的召回率为0.899。这表明，仅用稳定数据进行边界学习，即可在训练阶段无需真实不稳定标签或攻击样本的情况下，同时支撑稳定性预测和攻击检测。

英文摘要

Cyber-physical power systems increasingly rely on data-driven tools to detect instability and support reliable grid operation. However, reliable stability prediction is difficult when unstable operating configurations are rare, sensitive, or unavailable during model development, since collecting such data safely and at scale is often impractical. At the same time, False Data Injection (FDI) attacks can manipulate reported system parameters to trigger false instability alarms or conceal unsafe operation, and such threats in Decentral Smart Grid Control (DSGC) systems remain largely unexplored. These challenges are rarely addressed jointly, leaving a gap between stability prediction and attack detection that this work aims to close. In this paper, we introduce StarGNN, a graph learning framework that learns the stable operating region exclusively from clean stable configurations and uses a single abnormality score to flag reported configurations that should not be trusted as evidence of safe operation, covering both genuine instability and unseen FDI manipulations. Each configuration is represented as a producer-consumer star graph and processed by a role aware graph neural network, with physics constrained pseudo-negatives generated by perturbing reaction time and price response parameters standing in for the unavailable unstable and attack data. A single threshold, calibrated only on held-out stable data, is used without task or attack specific adjustment. Evaluated on nine unseen FDI scenarios, StarGNN detects between 0.780 and 0.973 of attacks on stable configurations and retains a post attack instability recall between 0.972 and 0.999 on unstable ones, with 0.899 recall against a stronger adaptive attacker, showing that stable-only boundary learning can support both stability prediction and attack detection without access to genuine unstable labels or attack samples during training.

发表机构

• University of Padua（帕多瓦大学）
• Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会）
• Newcastle University（纽卡斯尔大学）

机构由 AI 辅助整理，请以论文原文为准。