Detection of false data injection attacks on power systems using graph edge-conditioned convolutional networks

Chen, Bairen; Wu, Qiang; Li, Mengshi; Xiahou, Kaishun

doi:10.1186/s41601-023-00287-w

Cited by 17 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concurrently, stringent demands are placed on system modeling and parameter adjustment, necessitating real-time threshold updates. A framework for fault identification and diagnosis is introduced in [17]. It harnesses graph-edge conditional convolutional networks.…”

Section: Fdia Detection Based On a Data-driven Approachmentioning

confidence: 99%

The Detection of False Data Injection Attack for Cyber–Physical Power Systems Considering a Multi-Attack Mode

Zhou,

Li,

Zang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Amidst the evolving communication technology landscape, conventional distribution networks have gradually metamorphosed into cyber–physical power systems (CPPSs). Within this transformative milieu, the cyber infrastructure not only bolsters grid security but also introduces a novel security peril—the false data injection attack (FDIA). Owing to the variable knowledge held by cyber assailants regarding the system’s network structure, current achievements exhibit deficiencies in accommodating the detection of FDIA across diverse attacker profiles. To address the historical data imbalances encountered during practical FDIA detection, we propose a dataset balancing model based on generating adversarial network-gated recurrent units (GAN-GRU) in conjunction with an FDIA detection model based on the Transformer neural network. Harnessing the temporal data extraction capabilities of gated recurrent units, we construct a GRU neural network system as the GAN’s generator and discriminator, aimed at data balance. After preprocessing, the balanced data are fed into the Transformer neural network for training and output classification to discern distinct FDIA attack types. This model enables precise classification amidst varying FDIA scenarios. Validation involves testing the model on load data from the IEEE 118-bus system and affirming its high accuracy and effectiveness in detecting power systems after multiple attacks.

show abstract

Section: Fdia Detection Based On a Data-driven Approachmentioning

confidence: 99%

The Detection of False Data Injection Attack for Cyber–Physical Power Systems Considering a Multi-Attack Mode

Zhou,

Li,

Zang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For such contradiction, some researchers have proposed predictive control methods, which can greatly promote the power production [9,10] and reduce the operational cost [11] of wind turbines. Facing the difficulty in obtaining accurate previewed wind speed information with common measurements, the development of wind lidar measurement technology has promised a solution.…”

Section: Introductionmentioning

confidence: 99%

From Lidar Measurement to Rotor Effective Wind Speed Prediction: Empirical Mode Decomposition and Gated Recurrent Unit Solution

Shi,

Liu,

Deng

et al. 2023

Sensors

View full text Add to dashboard Cite

Conventional wind speed sensors face difficulties in measuring wind speeds at multiple points, and related research on predicting rotor effective wind speed (REWS) is lacking. The utilization of a lidar device allows accurate REWS prediction, enabling advanced control technologies for wind turbines. With the lidar measurements, a data-driven prediction framework based on empirical mode decomposition (EMD) and gated recurrent unit (GRU) is proposed to predict the REWS. Thereby, the time series of lidar measurements are separated by the EMD, and the intrinsic mode functions (IMF) are obtained. The IMF sequences are categorized into high-, medium-, and low-frequency and residual groups, pass through the delay processing, and are respectively used to train four GRU networks. On this basis, the outputs of the four GRU networks are lumped via weighting factors that are optimized by an equilibrium optimizer (EO), obtaining the predicted REWS. Taking advantages of the measurement information and mechanism modeling knowledge, three EMD–GRU prediction schemes with different input combinations are presented. Finally, the proposed prediction schemes are verified and compared by detailed simulations on the BLADED model with four-beam lidar. The experimental results indicate that compared to the mechanism model, the mean absolute error corresponding to the EMD–GRU model is reduced by 49.18%, 53.43%, 52.10%, 65.95%, 48.18%, and 60.33% under six datasets, respectively. The proposed method could provide accurate REWS prediction in advanced prediction control for wind turbines.

show abstract

“…With the rapid growth of renewable energy and the increasing access to distributed power, the development of LVDG is imperative (Azizivahed et al, 2020;Memmel et al, 2023). As the complexity of LVDG increases, efficient and accurate topology detection methods become crucial to ensure their reliable operation and optimal utilization (Wang et al, 2023a;Chen et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Virtual impedance based low-voltage distribution grid topology detection using double hidden layer recurrent neural network

Xuan,

Sun,

Fan

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Low-voltage distribution grid (LVDG) topology detection refers to detecting whether the topology connection between distribution grid nodes is correct. Accurate topology connection is critical for the normal operation and planning of LVDG. However, due to the incomplete measurement device, unknown line parameters, and rapid growth of renewable energy, the topology detection of LVDG becomes one of the most prominent challenges. This paper proposes an LVDG topology detection method based on virtual impedance, utilizing measurement data from nodes in the LVDG to achieve the detection of abnormal topological connections. Specifically, the electrical distances between nodes are analyzed to establish a topology detection model using virtual impedance. Then, the double hidden layer recurrent neural network is proposed to fit the mapping relationships between variables in the power flow constraints. The virtual impedance between nodes is solved. The value of virtual impedance is used to determine whether the topological connection between nodes is correct. Finally, the test results in the actual LVDG prove the effectiveness of the proposed method.

show abstract

Detection of false data injection attacks on power systems using graph edge-conditioned convolutional networks

Cited by 17 publications

References 26 publications

The Detection of False Data Injection Attack for Cyber–Physical Power Systems Considering a Multi-Attack Mode

The Detection of False Data Injection Attack for Cyber–Physical Power Systems Considering a Multi-Attack Mode

From Lidar Measurement to Rotor Effective Wind Speed Prediction: Empirical Mode Decomposition and Gated Recurrent Unit Solution

Virtual impedance based low-voltage distribution grid topology detection using double hidden layer recurrent neural network

Contact Info

Product

Resources

About