Banca de DEFESA: HENRIQUE DO NASCIMENTO CAMELO

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
DISCENTE : HENRIQUE DO NASCIMENTO CAMELO
DATA : 23/11/2018
HORA: 14:00
LOCAL: Mestrado Acadêmico em Ciências Físicas Aplicadas da UECE
TÍTULO:
PALAVRAS-CHAVES:

Time series; Box-Jenkins; Holt-Winters; Artificial intelligence.

PÁGINAS: 127
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Geociências
RESUMO:

At present it is possible to identify greater insertions of renewable resources of energies for generation of electricity in the national energy matrix, as is the case of wind generation. This can be justified in several respects, for example, in relation to the wind power source, it can play an important role in the matrix by providing a financially viable alternative to the main electricity generator in the country that is the hydro source. Another point in favor of wind power is the environmental issue, the use of this resource must be seen in this aspect. The amount of work on wind generation in the country grows each day bringing benefits to the particular sector providing guarantees of exploitation of the local winds. In this sense, the objective of this work is to present two innovative hybrid models which can help in the wind sector by being able to perform predictions of wind speeds with good accuracy. The models were elaborated from the mathematical combinations of classical models of time series with models of artificial intelligence. In the comparisons between the time series (observed and adjusted) it is possible to identify, for example, Nash-Sutcliffe efficiency coefficient (NS) of approximately 98%, and also a percentage error value of around 4.5%, which according to the literature, confirm the good accuracy of the models. A large differential of the proposed hybrid models when compared to other traditional ones is that they can incorporate both linear and nonlinear characteristics, which are often found in time series, being this important condition to provide greater precision of the velocities of the predicted winds thus providing greater reductions in statistical error measures when compared to the classical models that compose them. The proposed hybrid models may represent important tools for decision-makers in the wind generation sector in terms of wind exploitation, however, other areas of interest can be analyzed for their feasibility. For example, as will be shown proposal of article in marine sciences from the forecasts of speed and direction of the auxiliary winds in the containment of oil spilled into the sea.

MEMBROS DA BANCA:
Externo à Instituição - JOSÉ MARIA BRABO ALVES - UECE
Externo à Instituição - JOÃO BOSCO VERÇOSA LEAL JUNIOR - UECE
Externo à Instituição - MEIRY SAYURI SAKAMOTO - FUNCEME
Externo à Instituição - PAULO CESAR MARQUES DE CARVALHO - UFC
Presidente - 320597 - PAULO SERGIO LUCIO