Banca de DEFESA: Marcelo Augusto da Cruz Motta

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : Marcelo Augusto da Cruz Motta
DATE: 21/06/2024
TIME: 08:00
LOCAL: Remoto via Teams
TITLE:

Private Cloud FaaS for Optimizing Computational Resource Consumption in Storage Operations

KEY WORDS:

FaaS, Function-as-a-Service, Private Cloud, Dataprev, OpenWhisk

PAGES: 82
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Sistemas de Computação
SPECIALTY: Arquitetura de Sistemas de Computação
SUMMARY:

Since its emergence in mid-2014, the Function-as-a-cloud service model Service (FaaS) has experienced notable growth in its user adoption. This model offers some significant benefits, including cost savings, automatic scalability, and agile development based on microservices. Before the wide range of cloud service models available, this work proposes an approach to FaaS adoption, focusing on assessing, selecting, and providing open-source FaaS platforms. Therefore, this proposal aims to implement FaaS in the private cloud environment of a large public company. The central objective is to deploy the FaaS service model in a real private cloud, allowing meaningful comparisons in storage-related infrastructure operations and handling large volumes of data. Specifically, the study focuses on use cases related to interacting with object storage, such as Dell ECS S3, from the company in question. Initial experiments demonstrated promising results, especially concerning the availability of the elasticity resource and the saving of computational resources. This work represents a significant step in the direction of optimization and efficiency of document storage operations on a large scale within a corporate private cloud context.

COMMITTEE MEMBERS:
Presidente - 1706731 - ALETEIA PATRICIA FAVACHO DE ARAUJO VON PAUMGARTTEN
Interna - 1713597 - MARISTELA TERTO DE HOLANDA
Externo à Instituição - GERALDO PEREIRA ROCHA FILHO - UESB
Externa à Instituição - MARIA CLICIA STELLING DE CASTRO - UERJ