LiveZilla Live Chat Software

Constellation, le dépôt institutionnel de l'Université du Québec à Chicoutimi

Security risk modeling in smart grid critical infrastructures in the era of big data and artificial intelligence

Chehri Abdellah, Fofana Issouf et Yang Xiaomin. (2021). Security risk modeling in smart grid critical infrastructures in the era of big data and artificial intelligence. Sustainability, 13, (6), p. 3196.

[img]
Prévisualisation
PDF - Version publiée
Disponible sous licence Creative Commons Attribution.

9MB

URL officielle: http://dx.doi.org/doi:10.3390/su13063196

Résumé

Smart grids (SG) emerged as a response to the need to modernize the electricity grid. The current security tools are almost perfect when it comes to identifying and preventing known attacks in the smart grid. Still, unfortunately, they do not quite meet the requirements of advanced cybersecurity. Adequate protection against cyber threats requires a whole set of processes and tools. Therefore, a more flexible mechanism is needed to examine data sets holistically and detect otherwise unknown threats. This is possible with big modern data analyses based on deep learning, machine learning, and artificial intelligence. Machine learning, which can rely on adaptive baseline behavior models, effectively detects new, unknown attacks. Combined known and unknown data sets based on predictive analytics and machine intelligence will decisively change the security landscape. This paper identifies the trends, problems, and challenges of cybersecurity in smart grid critical infrastructures in big data and artificial intelligence. We present an overview of the SG with its architectures and functionalities and confirm how technology has configured the modern electricity grid. A qualitative risk assessment method is presented. The most significant contributions to the reliability, safety, and efficiency of the electrical network are described. We expose levels while proposing suitable security countermeasures. Finally, the smart grid’s cybersecurity risk assessment methods for supervisory control and data acquisition are presented.

Type de document:Article publié dans une revue avec comité d'évaluation
Volume:13
Numéro:6
Pages:p. 3196
Version évaluée par les pairs:Oui
Date:15 Mars 2021
Sujets:Sciences naturelles et génie > Génie
Sciences naturelles et génie > Génie > Génie électrique et génie électronique
Sciences naturelles et génie > Sciences appliquées
Département, module, service et unité de recherche:Départements et modules > Département des sciences appliquées > Module d'ingénierie
Mots-clés:smart grid, cybersecurity, machine learning, optimization, deep learning, cybersecurity risks, automated distribution network, grille intelligente, cybersécurité, optimisation, risques cybersécurité, réseau de distribution automatisé
Déposé le:17 mars 2021 23:05
Dernière modification:17 mars 2021 23:05
Afficher les statistiques de telechargements

Éditer le document (administrateurs uniquement)

Creative Commons LicenseSauf indication contraire, les documents archivés dans Constellation sont rendus disponibles selon les termes de la licence Creative Commons "Paternité, pas d'utilisation commerciale, pas de modification" 2.5 Canada.

Bibliothèque Paul-Émile-Boulet, UQAC
555, boulevard de l'Université
Chicoutimi (Québec)  CANADA G7H 2B1
418 545-5011, poste 5630