Multivariate physics-informed convolutional autoencoder for anomaly detection in power distribution systems with widespread deployment of distributed energy resources

Despite the relentless progress of deep learning models in analyzing the system conditions under cyber-physical events, their abilities are limited in the power system domain due to data availability issues, cost of data acquisition, and lack of interpretation and extrapolation of the data beyond th...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Sustainable Energy, Grids and Networks Ročník 44; s. 102022
Hlavní autoři:	Jabbari Zideh, Mehdi, Khushalani Solanki, Sarika
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.12.2025
Témata:	Anomaly detection Convolutional autoencoder Distributed energy resources Physics-informed neural network Power distribution grids Unsupervised data-driven method Physics-informed neural network Power distribution grids Unsupervised data-driven method Convolutional autoencoder Distributed energy resources Anomaly detection
ISSN:	2352-4677, 2352-4677
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Despite the relentless progress of deep learning models in analyzing the system conditions under cyber-physical events, their abilities are limited in the power system domain due to data availability issues, cost of data acquisition, and lack of interpretation and extrapolation of the data beyond the training windows. In addition, the integration of distributed energy resources (DERs) such as wind and solar generations increases the complexities and nonlinear nature of power systems. Therefore, an interpretable and reliable methodology is of utmost importance to increase the confidence of power system operators and their situational awareness for making reliable decisions. This has led to the development of physics-informed neural network (PINN) models as more interpretable, trustworthy, and robust models where the underlying principled laws are integrated into the training process of neural network models to achieve improved performance. This paper proposes a multivariate physics-informed convolutional autoencoder (PIConvAE) model to detect cyber anomalies in power distribution systems with unbalanced configurations and high penetration of DERs. The physical laws are integrated through a customized loss function that embeds the underlying complex nodal power balance equation into the training process of the autoencoder. The performance of the multivariate PIConvAE model is evaluated on two unbalanced power distribution grids, IEEE 123-bus system and a real-world feeder in Riverside, CA. The results show the exceptional performance of the proposed method in detecting various cyber anomalies in both systems. In addition, the model’s effectiveness is evaluated in data scarcity scenarios with different training data ratios. Finally, the model’s performance is compared with existing machine learning models where the PIConvAE model surpasses other models with considerably higher detection metrics. •Introduce a multivariate physics-informed convolutional autoencoder (PIConvAE) for cyber anomaly detection.•Embed the power balance equation into the autoencoder’s training for enhanced interpretability.•Evaluate PIConvAE on unbalanced IEEE 123-bus and Riverside, CA power distribution grids.•Demonstrate superior performance of PIConvAE in detecting various anomalies under data scarcity conditions.•PIConvAE outperforms existing machine learning models with higher detection metrics.
ISSN:	2352-4677 2352-4677
DOI:	10.1016/j.segan.2025.102022