A hybrid A-UKF-PINN digital twin architecture for real-time state estimation in Smart Grids
Information Technology and Computer Engineering · 20.04.2026 · (23) · 140-152
DOI: 10.31649/vitce/1.2026.140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Technology and Computer Engineering, online erschienen am 20.04.2026. Verfasst von Vladimir Vychuzhanin und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The increasing variability, nonlinearity, and real-time operational requirements of Smart Grids (SGs) make static digital models insufficient for reliable state estimation and control of distributed assets such as Vehicle-toGrid (V2G) storage systems. The purpose of the study was a formal and model-based substantiation of the advantages of dynamic digital twins (DTs) over static data model (DM) in real-time lithium-ion storage system condition assessment tasks. To achieve this, a hybrid adaptive unscented Kalman filter – physics-informed neural network (A-UKF-PINN) architecture was proposed, combining an A-UKF (Adaptive Unscented Kalman Filter), which provided robust state estimation in the presence of noise and uncertainty, with a physics-informed PINN (Physics-Informed Neural Network) model that considers the dynamics and nonlinear processes of the battery cell. The originality of the study lies in the integration of these components into a single model that supports bidirectional synchronisation, which improves forecast stability and significantly reduces desynchronisation between the model and the physical object in SG conditions. Simulation validation was carried out on V2G operating cycles with modelled Phasor Measurement Unit / Internet of Things sensor noise. The obtained Root Mean Square Error (RMSE) of 0.87% demonstrated a 44% accuracy improvement compared to a traditional DM (ECM (equivalent circuit models) + UKF, RMSE 1.98%) and a 56% improvement relative to the baseline digital twin (pure PINN). The architectural assessment confirmed the necessity of using a hierarchical Edge-Cloud platform that ensures optimal distribution of computational workloads: PINN training in the cloud environment and high-frequency state estimation at the edge. The proposed architecture forms the basis for scalable dynamic DTs in SG, helps to reduce operational risks, supports the implementation of proactive maintenance strategies, and increases the efficiency of the energy infrastructure life cycle
Zitieren
APA
Vychuzhanin, V., & Vychuzhanin, A. (2026). A hybrid A-UKF-PINN digital twin architecture for real-time state estimation in Smart Grids. Information Technology and Computer Engineering, 140-152. https://doi.org/10.31649/vitce/1.2026.140
Vancouver
Vychuzhanin V, Vychuzhanin A. A hybrid A-UKF-PINN digital twin architecture for real-time state estimation in Smart Grids. Information Technology and Computer Engineering. 2026:140-152. doi:10.31649/vitce/1.2026.140
BibTeX
@article{Vychuzhanin2026,
author = {Vychuzhanin, Vladimir and Vychuzhanin, Alexey},
title = {A hybrid A-UKF-PINN digital twin architecture for real-time state estimation in Smart Grids},
journal = {Information Technology and Computer Engineering},
year = {2026},
number = {23},
pages = {140--152},
doi = {10.31649/vitce/1.2026.140}
}
EUVIMED