Multi-agent System for Detecting False Data Injection Attacks Against the Power Grid
Multi-agent System for Detecting False Data Injection Attacks Against the Power Grid
复制标题
用于检测针对电网的虚假数据注入攻击的多代理系统
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
L. Keel
中科院分区：
文献类型：
--
作者：
Esther M. Amullen;Hui Lin;Z. Kalbarczyk;L. Keel
研究界目前正在研究一类称为虚假数据注入攻击的网络攻击，其目标是用于电网状态估计的测量数据。这些攻击会修改从仪表获得的传感器读数，目的是误导控制中心采取不明智的响应行动。事实证明，了解网络拓扑的攻击者可以发起攻击，绕过电网中现有的不良数据检测方案（主要基于剩余发电）。我们提出了一种多代理系统，用于检测针对状态估计的虚假数据注入攻击。多代理系统由为每个变电站创建的软件实现的代理组成。代理促进变电站之间的信息交换，包括测量数据和状态变量。我们证明，变电站之间交换的信息，即使是不可信的，也使代理能够合作检测变电站的局部状态变量与状态估计器计算的全局状态变量之间的差异。我们证明，通过整个系统的不良数据检测的虚假数据注入攻击不会通过每个代理的不良数据检测。
A class of cyber-attacks called False Data Injection attacks that target measurement data used for state estimation in the power grid are currently under study by the research community. These attacks modify sensor readings obtained from meters with the aim of misleading the control center into taking ill-advised response action. It has been shown that an attacker with knowledge of the network topology can craft an attack that bypasses existing bad data detection schemes (largely based on residual generation) employed in the power grid. We propose a multi-agent system for detecting false data injection attacks against state estimation. The multi-agent system is composed of software implemented agents created for each substation. The agents facilitate the exchange of information including measurement data and state variables among substations. We demonstrate that the information exchanged among substations, even untrusted, enables agents cooperatively detect disparities between local state variables at the substation and global state variables computed by the state estimator. We show that a false data injection attack that passes bad data detection for the entire system does not pass bad data detection for each agent.