A Dimensional Augmentation-Based Data-Driven Method for Detecting False Data Injection in Smart Meters
Zhenyuan Du, Ziming Yan, Yan Xu
Abstract
To detect cyber-attacks on individual smart meters, this letter proposes a novel data-driven method based on dimensional augmentation with recurrence plots (RPs) and visual geometry group network (VGGNet). Firstly, the real-time 1-dimensional time-series smart meter data is augmented to 2-dimensional image data using the RPs method, which provides visual-distinguishable features that can be more easily identified by the computer vision-based algorithms. Then, the genuine and contaminated smart meter data are distinguished using the VGGNet on the augmented 2-dimensional data. The proposed method is tested on a public user-level load dataset with 20 residential buildings and shows high accuracy and strong interpretability.