RT Journal Article
T1 Learning-based state estimation in distribution systems with limited real-time measurements
A1 Gómez de la Varga, J.
A1 Pineda-Morente, Salvador
A1 Morales-González, Juan Miguel
A1 Porras, A.
K1 Aprendizaje automático
K1 Ingeniería eléctrica
AB The task of state estimation in active distribution systems faces a major challenge due to the integrationof different measurements with multiple reporting rates. As a result, distribution systems are essentiallyunobservable in real time, indicating the existence of multiple states that result in identical values forthe available measurements. Certain existing approaches utilize historical data to infer the relationshipbetween real-time available measurements and the state. Other learning-based methods aim to estimate themeasurements acquired with a delay, generating pseudo-measurements. Our paper presents a methodologythat utilizes the outcome of an underdetermined state estimator of an unobservable network state estimator toexploit information on the joint probability distribution between real-time available measurements and delayedones to generate new physics-informed interpretable features. Through numerical simulations conducted on tworealistic distribution grids of different size with insufficient real-time measurements, the proposed procedureshowcases superior performance compared to existing state forecasting approaches and those relying oninferred pseudo-measurements
PB Elsevier
YR 2025
FD 2025-04
LK https://hdl.handle.net/10630/35408
UL https://hdl.handle.net/10630/35408
LA eng
NO Funding for open access charge: Universidad de Málaga/CBUA
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 4 mar 2026