Fundamentals of the C-DEEPSO Algorithm and its Application to the Reactive Power Optimization of Wind Farms

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2016

Autores

Marcelino, CG (Autor) Outra; Almeida, PEM (Autor) Outra; Wanner, EF (Autor) Outra; Leonel Carvalho (Autor) Outra; Vladimiro Miranda (Autor) FEUP

Ata de Conferência Internacional

Título: 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)

Páginas: 1547-1554

IEEE Congress on Evolutionary Computation (CEC) held as part of IEEE World Congress on Computational Intelligence (IEEE WCCI)

Vancouver, CANADA, JUL 24-29, 2016

Indexação

ISI Web of Knowledge - 4 Citações

Outras Informações

ID Authenticus: P-00M-7K6

DOI: 10.1109/CEC.2016.7743973

Abstract (EN): In this paper, a novel hybrid single-objective metaheuristic, the so called C-DEEPSO (Canonical Differential Evolutionary Particle Swarm Optimization), is proposed and tested. C-DEEPSO can be viewed as an evolutionary algorithm with recombination rules borrowed from PSO, or a swarm optimization method with selection and self-adaptiveness properties proper from DE. A case study on the problem of optimal control for reactive sources in energy production by Wind Power Plants (WPP), solved by means of Optimal Power Flow (OPF-like), is used to test the new hybrid algorithm and to evaluate its performance. C-DEEPSO is compared to the baseline algorithm, DEEPSO, and to a reference algorithm, Mean-Variance Mapping Optimization (MVMO). The experiments indicate that the proposed algorithm is efficient and competitive, capable to tackle this large-scale problem. The results also show that the new approach exhibits better results, when compared to MVMO.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 8