Visible to the public Dynamic Detection of False Data Injection Attack in Smart Grid using Deep Learning

TitleDynamic Detection of False Data Injection Attack in Smart Grid using Deep Learning
Publication TypeConference Paper
Year of Publication2019
AuthorsNiu, Xiangyu, Li, Jiangnan, Sun, Jinyuan, Tomsovic, Kevin
Conference Name2019 IEEE Power Energy Society Innovative Smart Grid Technologies Conference (ISGT)
Keywordsbad data detection mechanisms, basic measurements, communication technology, compositionality, convolutional neural nets, convolutional neural network, data measurements, Deep Learning, deep learning algorithm, deep learning based framework, Detectors, dynamic detection, electricity grid, false data injection attack, FDI attacks, human factors, IEEE 39-bus system, injected data measurement, learning (artificial intelligence), long short term memory network, modern advances, modern cyber threats, network level features, power engineering computing, power meters, power system, Power system dynamics, power system measurement, power system security, power system state estimation, pubcrawl, Recurrent neural networks, redundant measurements, Resiliency, security of data, smart grid applications, Smart Grid Sensors, Smart grids, smart power grids, specific assumptions, system states, system variables, time-series anomaly detector, traditional state estimation bad data detection
AbstractModern advances in sensor, computing, and communication technologies enable various smart grid applications. The heavy dependence on communication technology has highlighted the vulnerability of the electricity grid to false data injection (FDI) attacks that can bypass bad data detection mechanisms. Existing mitigation in the power system either focus on redundant measurements or protect a set of basic measurements. These methods make specific assumptions about FDI attacks, which are often restrictive and inadequate to deal with modern cyber threats. In the proposed approach, a deep learning based framework is used to detect injected data measurement. Our time-series anomaly detector adopts a Convolutional Neural Network (CNN) and a Long Short Term Memory (LSTM) network. To effectively estimate system variables, our approach observes both data measurements and network level features to jointly learn system states. The proposed system is tested on IEEE 39-bus system. Experimental analysis shows that the deep learning algorithm can identify anomalies which cannot be detected by traditional state estimation bad data detection.
Citation Keyniu_dynamic_2019