PRIMENA NEURALNIH MREŽA ZA UNAPREĐENЈE ROBUSNOSTI NADZEMNIH VODOVA

37. саветовање CIGRE Србија (2025) СИГУРНОСТ, СТАБИЛНОСТ, ПОУЗДАНОСТ И RESILIENCE ЕЛЕКТРОЕНЕРГЕТСКОГ СИСТЕМА МУЛТИСЕКТОРСКО ПОВЕЗИВАЊЕ У ЕНЕРГЕТИЦИ И ПРИВРЕДИ – B2.11

АУТОР(И) / AUTHOR(S): Aleksandar Terzić, Mileta Žarković, Boško Nikolić

 

Download Full Pdf   

DOI:  10.46793/CIGRE37.B2.11

САЖЕТАК / ABSTRACT:

The global transition to carbon-neutral energy necessitates a fundamental transformation of power grids, requiring innovative strategies to enhance system resilience. Overhead transmission lines (OHLs), a critical component of power infrastructure, face increasing operational challenges due to extreme weather conditions. This paper presents a novel approach to improving OHL resilience by integrating a coupled mechanical-meteorological model with an artificial neural network (ANN)-based event detection system. Building upon the OHL Multiphysics Modelling framework (CIGRE Paris 2024, session B2-10884), which simulates OHL behavior under dynamic weather conditions, this research bridges the gap between theoretical modeling and real-world operational data. The proposed system leverages the predictive capabilities of multiphysics simulations and the learning capacity of ANNs to identify critical grid events, such as conductor galloping, excessive tensile loads due to ice accretion, and adverse weather impacts on OHL performance. The methodology includes data acquisition from transmission system operators (TSOs), ANN training for pattern recognition, real-time event detection, and performance validation to ensure accuracy and adaptability. The expected contributions of this research include enhanced grid resilience, optimized asset management, and data-driven decision-making for TSOs. By integrating advanced modeling with AI, this paper provides a solution for ensuring power grid stability in the era of extreme weather conditions.

КЉУЧНЕ РЕЧИ / KEYWORDS:

Asset Management, Artificial Neural Networks, Overhead Transmission Lines (OHLs), Weather Modeling

ПРОЈЕКАТ / ACKNOWLEDGEMENT:

ЛИТЕРАТУРА / REFERENCES:

  • A. Terzic, „OHL Multiphysics modelling B2-10884,“ CIGRE 2024, 2024.
  • Geopandas, „geopandas,“ geopandas, 08 04 2025. [Na mreži]. Available: https://geopandas.org/en/stable/. [Poslednji pristup 08 04 2025].
  • Copernicus Climate Change Service, „Climate Data Store,“ Copernicus, 08 April 2024. [Na mreži]. Available: https://cds.climate.copernicus.eu/#!/home. [Poslednji pristup 08 April 2024].
  • ECMWF, „ECMWF reanalysis,“ ECMWF, 08 04 2024. [Na mreži]. Available: https://www.ecmwf.int/en/forecasts/dataset/ecmwf-reanalysis-v5. [Poslednji pristup 08 04 2024].
  • ESA, „ESA land cover,“ ESA, 08 04 2025. [Na mreži]. Available: https://climate.esa.int/en/projects/land-cover/. [Poslednji pristup 08 04 2025].
  • CENELEC, EN 50341-1:2012 – Overhead electrical lines exceeding AC 1 kV – Part 1: General requirements – Common specifications, CENELEC, 2012.
  • QGIS, „QGIS project,“ QGIS, 08 April 2024. [Na mreži]. Available: https://qgis.org/en/site/. [Poslednji pristup 08 April 2024].
  • scikit learn, „scikit learn nearest neighbors documentation,“ scikit learn developers, 08 April 2024. [Na mreži]. Available: https://scikit-learn.org/stable/modules/neighbors.html. [Poslednji pristup 08 April 2024].
  • K. V. M. Đurić, „Comparison of the equation of catenary state for mid-length spans and a mathematical model that is more accurate and intended for computer application,“ u CIGRE Yugoslavia 25th session, Herceg Novi, 2001.