A machine learning approach for real‐time selection of preventive actions improving power network resilience

Abstract Power outages due to cascading failures which are triggered by extreme weather pose an increasing risk to modern societies and draw attention to an emerging need for power network resilience. Machine learning (ML) is used for a real‐time selection process on preventive actions, such as topo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Matthias Noebels, Robin Preece, Mathaios Panteli
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2022
Materias:	Distribution or transmission of electric power TK3001-3521 Production of electric energy or power. Powerplants. Central stations TK1001-1841
Acceso en línea:	https://doaj.org/article/b7816791492a4616b047123e11591993
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b7816791492a4616b047123e11591993
record_format	dspace
spelling	oai:doaj.org-article:b7816791492a4616b047123e115919932021-12-02T14:01:24ZA machine learning approach for real‐time selection of preventive actions improving power network resilience1751-86951751-868710.1049/gtd2.12287https://doaj.org/article/b7816791492a4616b047123e115919932022-01-01T00:00:00Zhttps://doi.org/10.1049/gtd2.12287https://doaj.org/toc/1751-8687https://doaj.org/toc/1751-8695Abstract Power outages due to cascading failures which are triggered by extreme weather pose an increasing risk to modern societies and draw attention to an emerging need for power network resilience. Machine learning (ML) is used for a real‐time selection process on preventive actions, such as topology reconfiguration and islanding, aiming to reduce the risk of cascading failures. Training data is obtained from Monte Carlo simulations of cascading failures triggered by extreme events. The trained ML‐based decision‐making process uses only predictors that are readily available prior to an extreme event, such as event location and intensity, network topology and load, and requires no further time‐consuming simulations.The proposed decision‐making process is compared to time‐consuming but ideal decision‐making and fast but trivial decision‐making. Demonstrations on the German transmission network show that the proposed ML‐based selection process efficiently prevents the uncontrolled propagation of cascading failures and performs similarly to an ideal decision‐making process whilst being computationally three orders of magnitude faster.Matthias NoebelsRobin PreeceMathaios PanteliWileyarticleDistribution or transmission of electric powerTK3001-3521Production of electric energy or power. Powerplants. Central stationsTK1001-1841ENIET Generation, Transmission & Distribution, Vol 16, Iss 1, Pp 181-192 (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Distribution or transmission of electric power TK3001-3521 Production of electric energy or power. Powerplants. Central stations TK1001-1841
spellingShingle	Distribution or transmission of electric power TK3001-3521 Production of electric energy or power. Powerplants. Central stations TK1001-1841 Matthias Noebels Robin Preece Mathaios Panteli A machine learning approach for real‐time selection of preventive actions improving power network resilience
description	Abstract Power outages due to cascading failures which are triggered by extreme weather pose an increasing risk to modern societies and draw attention to an emerging need for power network resilience. Machine learning (ML) is used for a real‐time selection process on preventive actions, such as topology reconfiguration and islanding, aiming to reduce the risk of cascading failures. Training data is obtained from Monte Carlo simulations of cascading failures triggered by extreme events. The trained ML‐based decision‐making process uses only predictors that are readily available prior to an extreme event, such as event location and intensity, network topology and load, and requires no further time‐consuming simulations.The proposed decision‐making process is compared to time‐consuming but ideal decision‐making and fast but trivial decision‐making. Demonstrations on the German transmission network show that the proposed ML‐based selection process efficiently prevents the uncontrolled propagation of cascading failures and performs similarly to an ideal decision‐making process whilst being computationally three orders of magnitude faster.
format	article
author	Matthias Noebels Robin Preece Mathaios Panteli
author_facet	Matthias Noebels Robin Preece Mathaios Panteli
author_sort	Matthias Noebels
title	A machine learning approach for real‐time selection of preventive actions improving power network resilience
title_short	A machine learning approach for real‐time selection of preventive actions improving power network resilience
title_full	A machine learning approach for real‐time selection of preventive actions improving power network resilience
title_fullStr	A machine learning approach for real‐time selection of preventive actions improving power network resilience
title_full_unstemmed	A machine learning approach for real‐time selection of preventive actions improving power network resilience
title_sort	machine learning approach for real‐time selection of preventive actions improving power network resilience
publisher	Wiley
publishDate	2022
url	https://doaj.org/article/b7816791492a4616b047123e11591993
work_keys_str_mv	AT matthiasnoebels amachinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience AT robinpreece amachinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience AT mathaiospanteli amachinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience AT matthiasnoebels machinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience AT robinpreece machinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience AT mathaiospanteli machinelearningapproachforrealtimeselectionofpreventiveactionsimprovingpowernetworkresilience
_version_	1718392164349640704

A machine learning approach for real‐time selection of preventive actions improving power network resilience

Ejemplares similares