基于ARIMA模型的智能电网虚假数据注入攻击检测

ARIMA Model-based False Data Injection Attack Detection in Smart Grid

虚假数据注入攻击是针对智能电网运行变量的攻击,通过篡改量测值对智能电网造成威胁。文章提出一种基于差分自回归平均移动模型的智能电网虚假数据注入攻击检测方法。首先,利用历史数据和差分自回归平均移动模型对智能电网的运行变量进行短期预测,得到该时刻智能电网可能的状态变量值;然后,观察量测值与相邻节点预测的状态变量值之间的负荷偏差,判断该节点是否受到攻击;最后,在IEEE 118标准电力系统上进行测试,测试结果证明所提方法的有效性。

False data injection attack is an attack against the operation variables of smart grid,which threatens the smart grid by tampering with the measured values.This paper proposes an autoregressive integrated moving average(ARIMA)model-based false data injection attack detection method in smart grid.Firstly,the historical data and ARIMA model are used to predict the operation variables of smart grid in the short term,and the possible state variables of smart grid at that time are obtained.Then observe the load deviation between the measured value and the predicted state variable value of the adjacent node to judge whether the node is attacked.The method is tested on IEEE 118 standard power system and the results show the effectiveness of the proposed method.