Contribution to a conference proceedings

FZJ-2025-05278

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Distribution Grid Voltage Estimation by Correlated Gaussian Processes

Buechel, M. (Corresponding author)FZJ* ; Zimmer, M.FZJ* ; Carta, D.FZJ* ; Benigni, A.FZJ*

2025
IEEE

This record in other databases:  

Please use a persistent id in citations: doi:10.1109/AMPS66841.2025.11219969

Abstract: Modern power distribution grids are facing significant monitoring challenges from renewable energy volatility and persistent measurement scarcity. In this paper, we propose a data-driven approach for voltage magnitude estimation in distribution systems using correlated Gaussian processes. We demonstrate that the proposed approach can be applied to a variety of monitoring configurations. Comparable accuracies are achieved even when the number of monitoring units is significantly reduced. Moreover, the results are obtained with the help of small training sets, allowing for short observation periods to generate training data. The proposed approach offers flexibility in terms of monitoring configurations and provides reliable voltage estimation in poorly monitored distribution networks.

---

Contributing Institute(s):

1. Modellierung von Energiesystemen (ICE-1)

Research Program(s):

1. 1121 - Digitalization and Systems Technology for Flexibility Solutions (POF4-112) (POF4-112)
2. 1122 - Design, Operation and Digitalization of the Future Energy Grids (POF4-112) (POF4-112)
3. 1123 - Smart Areas and Research Platforms (POF4-112) (POF4-112)

Appears in the scientific report 2025

---