ADDP: Anomaly Detection for DTU Based on Power Consumption Side-Channel

With the rapid development of information technology and the Internet of Things, the common information technologies are being applied to the power grid. It brings about the tremendous improvement in productivity, yet breaks down the safety barrier, which makes the power grid a popular target for attacks. The Distribution Terminal Unit (DTU) is a critical part of the power grid because of the acts as access points in the substation and controls the grid equipment. However, DTUs are vulnerable to different types of attacks, which can cause significant property loss or even casualties To monitor the operation of DTU, we proposed a real-time monitoring system by analyzing the side-channel information of power consumption. To validate this idea, we design 3 types of attacks and collect the power information separately, then we choose representational power features and machine learning algorithm for detecting those attacks. We validate that it is feasible to detect attacks and achieves a detection accuracy above 99%.