Mitigating the Impacts of Covert Cyber Attacks in Smart Grids Via Reconstruction of Measurement Data Utilizing Deep Denoising Autoencoders

Abstract

As one of the most diversified cyber-physical systems, the smart grid has become more decumbent to cyber vulnerabilities. An intelligently crafted, covert, data-integrity assault can insert biased values into the measurements collected by a sensor network, to elude the bad data detector in the state estimator, resulting in fallacious control decisions. Thus, such an attack can compromise the secure and reliable operations of smart grids, leading to power network disruptions, economic loss, or a combination of both. To this end, in this paper, we propose a novel idea for the reconstruction of sensor-collected measurement data from power networks, by removing the impacts of the covert data-integrity attack. The proposed reconstruction scheme is based on a latterly developed, unsupervised learning algorithm called a denoising autoencoder, which learns about the robust nonlinear representations from the data to root out the bias added into the sensor measurements by a smart attacker. For a robust, multivariate reconstruction of the attacked measurements from multiple sensors, the denoising autoencoder is used. The proposed scheme was evaluated utilizing standard IEEE 14-bus, 39-bus, 57-bus, and 118-bus systems. Simulation results confirm that the proposed scheme can handle labeled and non-labeled historical measurement data and results in a reasonably good reconstruction of the measurements affected by attacks.

Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm

“…Their methods were tested in IEEE-14, IEEE-57 and IEEE-118 bus standard system, and compared mutually. Ahmed et al in (198) suggested a model to recreate sensorcollected power network measurement data by eliminating the impacts of the hidden information-integrity attack. The model is utlized by a denoising autoencoder, which learns from the data about robust nonlinear representations to root out the bias that a smart attacker has added to the sensor measurements.The scheme was evaluated utilizing standard IEEE 14-bus, 39-bus, 57bus, and 118-bus systems.…”

A Study on High-Speed Outlier Detection Method of Network Abnormal Behavior Data Using Heterogeneous Multiple Classifiers

“…In addition, this research proposed a method of minimizing the influence of noise and deriving high performance by appropriately refining data from an unbalanced dataset using the methodology of Few-shot learning. Ahmed et al [18] proposed filtering normal data using AutoEncoder to detect and remove noise data present in a dataset in an industrial control environment. This study detects noise data and intentionally changes it into a shape similar to normal data, thereby minimizing data loss and reducing the influence of noise data.…”

Autoencoder Based Anomaly Detection for SCADA Networks

“…The proposed framework was used for unsupervised feature learning in complex security scenarios. Deep denoising autoencoders were used to propose a reconstruction scheme to mitigate the impact of covert cyber-attacks in smart grids (Ahmed et al, 2019). The results identified a low error ratio, compared to other schemes.…”