Name: João Carlos de Jesus Monteiro
Type: MSc dissertation
Publication date: 17/06/2021

Namesort descending Role
Helder Roberto de Oliveira Rocha Co-advisor *
Jussara Farias Fardin Advisor *

Examining board:

Namesort descending Role
Helder Roberto de Oliveira Rocha Co advisor *
Jussara Farias Fardin Advisor *
Lucas Frizera Encarnação External Examiner *
Wanderley Cardoso Celeste External Examiner *

Summary: The insertion of renewable distributed sources of energy in distribution and transmission networks has generated technical analyzes of the impact of the insertion, on the different aspects of the functioning of these networks. The Black Start process (recovery of the network after total stop without external reference) is among the procedures that can be changed as the networks are modified, due to the fact that the new sources inserted can change the dynamics of this procedure. In this work, it is proposed to obtain, using a prediction system of atmospheric data based on ELM neural networks (Extreme
Learning Machine) and the multi-objective optimizer MOGWO (Multiobjective Gray Wolf Optimizer), Pareto curves with the optimized sequences switching loads and sources for feeders 13 and 34 IEEE nodes modified to act as microgrids. The ELM neural network was used to obtain the values of wind speed and solar irradiation, 24 hours in advance, values that will be used as input data in the models of generators, wind and photovoltaic, inserted in the microgrids. The objective function used by the optimization algorithm seeks to obtain the connection sequence of the elements to the microgrid with the least
disturbance in the voltage and frequency signal during recovery. Two indicators were used to analyze the disturbances: IAE (Integral Absolute Error) and ITAE (Integral of Time Multiplied by absolute error). The periods of highest and lowest generation for a random day were simulated and their results were analyzed.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910