Nowadays, a power system failure can drastically affect the reliability and normal operation of power distribution grids. The preparation for these failure events is currently approached with post-event analysis to identify the area of the system that requires the most resources in order to prevent future failures. Nevertheless, the forecasting of such events can be useful to anticipate the failure and possibly avoid it. In this work, we employ several machine learning approaches to analyze historical failure data and predict power grid outages based on operational and meteorological data. The approach is tested with real failure data of a power distribution network in the South of Italy, demonstrating advantageous results also to determine areas requiring particular attention.
Effects of Heatwaves on the Failure of Power Distribution Grids: A Fault Prediction System Based on Machine Learning / Atrigna, M.; Buonanno, A.; Carli, R.; Cavone, G.; Scarabaggio, P.; Valenti, M.; Graditi, G.; Dotoli, M.. - (2021), pp. 1-5. (Intervento presentato al convegno 21st IEEE International Conference on Environment and Electrical Engineering and 2021 5th IEEE Industrial and Commercial Power System Europe, EEEIC / I and CPS Europe 2021 tenutosi a Via Edoardo Orabona, 4, ita nel 2021) [10.1109/EEEIC/ICPSEurope51590.2021.9584751].
Effects of Heatwaves on the Failure of Power Distribution Grids: A Fault Prediction System Based on Machine Learning
Carli R.;Cavone G.;Scarabaggio P.;Dotoli M.
2021-01-01
Abstract
Nowadays, a power system failure can drastically affect the reliability and normal operation of power distribution grids. The preparation for these failure events is currently approached with post-event analysis to identify the area of the system that requires the most resources in order to prevent future failures. Nevertheless, the forecasting of such events can be useful to anticipate the failure and possibly avoid it. In this work, we employ several machine learning approaches to analyze historical failure data and predict power grid outages based on operational and meteorological data. The approach is tested with real failure data of a power distribution network in the South of Italy, demonstrating advantageous results also to determine areas requiring particular attention.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.