Mestrado em Engenharia Elétrica

URI Permanente para esta coleção

http://repositorio.ufes.br/handle/10/17619

Nível: Mestrado Acadêmico
Ano de início:
Conceito atual na CAPES:
Ato normativo:
Periodicidade de seleção:
Área(s) de concentração:
Url do curso:

Navegar

Navegando Mestrado em Engenharia Elétrica por Autor "Alves, Rogerio José Menezes"

Agora exibindo 1 - 1 de 1
  • Nenhuma Miniatura disponível
    Item
    Graph machine learning models applied on the identification of critical transmission lines in electrical power systems
    (Universidade Federal do Espírito Santo, 2022-04-04) Alves, Rogerio José Menezes; Paiva, Marcia Helena Moreira; https://orcid.org/0000-0002-7314-6129; http://lattes.cnpq.br/8026444214173343; Samatelo, Jorge Leonid Aching; Lourenço, Elizete Maria
    When the operation of electric power systems is concerned, one may associate security with predicting a future event, and then be always ready to what may happen in the future. The number of possible events increases even further when not only single contingencies are evaluated, but also multiple contingencies. Therefore, one must seek for the balance between desired security level and practical cost-efectiveness. A critical event that is not mapped will not be analyzed and might represent an issue in the system’s event response mechanisms. On the other hand, the screening is vital because the number of possible contingency scenarios turns impractical to make an exhaustive detailed simulation approach. One alternative approach to make analyses on power systems is to consider topological aspects instead of, or even together with electrical information from the systems. In this case, graph models of the power systems can be constructed and evaluated. In this dissertation, Graph Machine Learning techniques are evaluated on graph models constructed from the system data, aiming to classify critical and non-critical transmission lines. First, a literature review is made, highlighting the main models and methods, which are then adapted and applied. Then, a set of test systems that are commonly used in benchmarks is selected for the evaluation step. Three approaches for learning architectures are proposed, given that the formulated learning problem is not directly treated in the known literature. The learning approaches are trained for reproducing a known criticality index for transmission lines in a graph model, and the obtained results are analyzed. Finnaly, conclusion about the obtained results are made and possible future research themes are proposed.