Banca de QUALIFICAÇÃO: LEONARDO AUGUSTO DE AQUINO MARQUES

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : LEONARDO AUGUSTO DE AQUINO MARQUES
DATE: 05/12/2023
TIME: 09:00
LOCAL: meet.google.com/dwn-mggv-pce
TITLE:

Intelligent Management of Electrical Power Quality in Data Center Assets

KEY WORDS:

Data center, Smart Grid, Machine Learning, IoT.

PAGES: 100
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Sistemas de Computação
SPECIALTY: Teleinformática
SUMMARY:

The monitoring of electrical power quality, particularly in the context of Information Technology (IT) and Data Centers (DCs), is gaining increasing relevance. This significance is intricately linked to the continuous advancement of IT activities, where DCs play a pivotal role by serving as solid foundations for this ongoing growth. Power quality plays a crucial role in ensuring the reliable operation of servers and IT equipment. Given that these components are essential to sustain critical applications, services, and data for both businesses and daily life, power quality-related issues can have detrimental effects on the operation of these assets. In this scenario, the implementation of Smart Grids (SG) emerges as a viable solution to enhance the quality of electricity supply. SG not only enables the swift detection and correction of power quality-related issues but also contributes to stability and efficiency in energy delivery. The integration of Smart Meters (SMs) in this context is a key element that aligns seamlessly with the concept of SG. These advanced devices allow real-time monitoring of
electrical consumption and provide detailed information about the quality of the supplied energy. The present work aims to provide an intelligent monitoring and management solution for power quality in individualized assets within DCs. This will be achieved through a comprehensive architecture spanning the Internet of Things
(IoT) spectrum, from edge to cloud. This will enable the application of Machine Learning (ML) techniques to ensure device integrity and continuous operation. The emphasis will be placed on creating a framework that enables proactive
detection of power quality-related issues, thus providing a stable and reliable operating environment for DC assets.

COMMITTEE MEMBERS:
Presidente - 1699087 - AUGUSTO JOSE VENANCIO NETO
Interno - 1694485 - MARCIO EDUARDO KREUTZ
Externo ao Programa - 2143852 - EDUARDO NOGUEIRA CUNHA - UFRNExterno à Instituição - LEANDRO BUSS BECKER - UFSC