Banca de QUALIFICAÇÃO: GERFFESON ALMEIDA MOURA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : GERFFESON ALMEIDA MOURA
DATE: 10/08/2023
TIME: 14:30
LOCAL: Online
TITLE:

Smart Meter for Electric Energy Consumption and Quality with Embedded Neural Network for Consumption Prediction and Process Control

KEY WORDS:

Smart Meter, Smart Grid, Electricity Quality, Electricity Consumption Prediction, Artificial Neural Networks, Deep Learning

PAGES: 70
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

Currently, the consumption of electricity in the world is growing rapidly.However, a concern arises in relation to measures of rational use of energy, mainly with regard to the environment and sustainability.Thus, providing electricity in a rational way is one of the greatest challenges of modern society.In addition, momentary failures can cause high losses, therefore, the quality of electrical energy is also a major concern.On the other hand, with the growth of smart grids, consumers and utilities are gaining new measurement technologies and remote operation, bringing improvements in terms of quality of service.Studies indicate that the increase in energy efficiency is related to changes in consumption habits, and that consumer involvement in new technologies that give access to detailed information makes them aware of rational use.This work proposes the development of a Smart Meter capable of determining the parameters of quality and consumption of electric energy in the short term, registering the occurrence of disturbances related to voltage, current and frequency.The device is implemented through algorithms optimized for embedded systems using comparative analysis methodologies focused on accuracy and reliability of measurements.The results are generated based on studies developed with the function of defining the most suitable models and mathematical tools for load forecasting and process control.With the use of Fourier, Wavelet, Laplace transforms, models of artificial neural networks and deep learning (Deep Learning) it is possible to obtain a safe measurement system that meets the concepts of a Smart Grid.

COMMITTEE MEMBERS:
Presidente - 2140683 - DIOMADSON RODRIGUES BELFORT
Interno - 1284113 - SEBASTIAN YURI CAVALCANTI CATUNDA
Externo ao Programa - 3157135 - ANTONIO WALLACE ANTUNES SOARES - UFRN