A Deep-Learning-Based Solution for Securing the Power Grid Against Load Altering Threats by IoT-Enabled Devices

Abstract

The growing integration of high-wattage Internetof-Things (IoT)-enabled electrical appliances at the consumer end has created a new attack surface that an adversary can exploit to disrupt power grid operations. Specifically, dynamic load-altering attacks (D-LAAs), accomplished by an abrupt or strategic manipulation of a large number of consumer appliances in a botnet-type attack, have been recognized as major threats that can potentially destabilize power grid control loops. This paper introduces a novel approach based a multi-output network (two-dimensional convolutional neural networks classifier and reconstruction decoder) -called "2DR-CNN"-to detect and localize D-LAAs with high resolution. To achieve this, we leverage the frequency and phase angle data of the generator buses monitored by phasor measurement units (PMUs) installed in the power grid. To verify the effectiveness of the proposed method, simulations are conducted on IEEE 14-and 39-bus systems. The performance of the 2DR-CNN method is compared against several benchmark machine learning-based approaches. The results confirm that the proposed method outperforms other techniques in detection and localizing D-LAAs with high resolution in a number of practical scenarios, including PMU measurement noises and missing measurements.

Comparison and Investigation of AI-Based Approaches for Cyberattack Detection in Cyber-Physical Systems

“…Moreover, the authors of [29], [30], [31] explained the potential of ML techniques to detect various attacks on CPS, including smart grids, power grids, and cyber-physical power systems. Lin et al [29] used deep reinforcement learning (DRL), propose a model for false data injection attacks and counter-detection techniques.…”

“…Lin et al [29] used deep reinforcement learning (DRL), propose a model for false data injection attacks and counter-detection techniques. Jahangir et al [30] proposed a novel approach for the identification and localization of highresolution. This method uses a multi-output network that includes a two-dimensional neural network classifier and a reconstruction decoder.…”

“…The study's limitations include the assumption of unrestricted attack resources, complete topology information, and the potential for future advancements in the detection method's perception capabilities. [30] 2DR-CNN The main contribution of this study is the development of an innovative technique called 2DR-CNN, which can accurately detect and identify dynamic load-altering attacks (D-LAAs) with high resolution.…”

Data‐driven detection and identification of IoT‐enabled load‐altering attacks in power grids

“…Nevertheless, LAAs can be localized by monitoring the power grid dynamics (i.e., voltage phase angle and frequency fluctuations) and inferring the attack parameters/attack location using machine learning algorithms. Advanced analytic techniques such as multi-dimensional convolutional neural networks can capture the correlations between power grid signals measured at different locations and quickly detect and localize LAA [10]. Such a detection mechanism can be seamlessly integrated into existing widearea monitoring systems, as shown in Figure 5.…”

YOLOv8-CGRNet: A Lightweight Object Detection Network Leveraging Context Guidance and Deep Residual Learning

“…With the evolution of computer technology and the widespread application of principles of computer vision, research on target detection and tracking using computer image processing technology is gaining popularity. Object detection [1] plays a pivotal role in applications such as autonomous driving and unmanned vehicles [2], security and surveillance [3], medical imaging [4], robotics [5], and agriculture [6], with image segmentation [7] and object tracking [8]. Pedestrian re-identification [9] often relies on it.…”