Detalhes bibliográficos
Ano de defesa: |
2017 |
Autor(a) principal: |
SILVA, Josival dos Santos
 |
Orientador(a): |
LINS, Fernando Antonio Aires |
Banca de defesa: |
CYSNEIROS FILHO, Gilberto Amado de Azevedo,
MEDEIROS, Robson Wagner Albuquerque de,
ROSA, Nelson Souto |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Federal Rural de Pernambuco
|
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Informática Aplicada
|
Departamento: |
Departamento de Estatística e Informática
|
País: |
Brasil
|
Palavras-chave em Português: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/7866
|
Resumo: |
The increase in the use of mobile devices from the first decade of this century has enabled users to perform several activities previously only possible through personal computers. However, the use of these devices is impacted by their known computational limitations, such as data processing, RAM memory, storage and low power autonomy. Considering this context, to measure the impact of the energy consumption of mobile devices applications is considered a relevant activity. In this context, this work presents a measurement methodology that can be applied to scenarios involving Mobile Cloud Computing (MCC). This measurement methodology allows evaluating the energy consumption of applications in MCC environments using different workloads. In addition to the energy consumption, this work of dissertation takes into account the execution time metric, deriving in an indirect metric, allowing to evaluate the impact of different factors like types of cloud (public and private) and the type of connection (3G, 4G and Wi-Fi) running on the system. It was possible through the use of the proposed measurement methodology to verify and quantify the impact of MCC use to reduce the energy consumption of a smartphone. Furthermore, to perform a measurement in applications involving mobile cloud computing, applying a strategy that does not interfere with the analyzed system, through a non-invasive measurement tool, besides presenting how to select and collect the metrics, and treat the data for an evaluation of system performance. |