• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2016.tde-19102016-144647
Document
Author
Full name
Zhang Yifei
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2016
Supervisor
Committee
Souza, Paulo Sergio Lopes de (President)
Estrella, Júlio Cezar
Marcondes, Cesar Augusto Cavalheiro
Title in Portuguese
Estudo e simulação de algoritmos de escalonamento para grades móveis voltados à conectividade dos dispositivos móveis
Keywords in Portuguese
Escalonamento
Grade móvel
Simulação
Tolerância a falha
Abstract in Portuguese
Este projeto apresenta o desenvolvimento de um conjunto de algoritmos que objetivam o escalonamento de tarefas em grades móveis, com foco no problema de conectividade e tolerância às falhas. Algoritmos de aprendizado de máquina e algoritmos estocásticos são aplicados na organização de recursos da grade durante o processo de escalonamento de tarefas. Além disso, uma tolerância a falhas foi considerada em conjunto ao algoritmo proposto e o desempenho do algoritmo foi avaliado por meio de simulação. Os resultados mostram que a queda da quantidade de falhas é significativa com a utilização dos algoritmos desenvolvidos, principalmente quando há uma grande quantidade de tarefas e poucos recursos disponíveis. O aumento do tempo de execução é inevitável neste caso, porém é controlável pelas variáveis definidas nos algoritmos.
Title in English
Study and simulation of scheduling algorithms for mobile grids focused on connectivity mobile devices
Keywords in English
Fault tolerancia
Mobile grid
Scheduling
Simulation
Abstract in English
This project presents the development of a set of algorithms for task scheduling in a mobile grid, focusing on connectivity problem and fault tolerance. Machine learning algorithms and stochastic algorithms are applied to organize the grid resources during the process of task scheduling. In addition, a technique of fault tolerance is considered in conjunction with the proposed algorithm, and the performance of algorithm is evaluated by simulation. The results show a substancial decrease in the failure rate due to the use of developed algorithms, mainly for the case of large amount of tasks with limited resources. The increase in execution time is inevitable in this case, but it is controllable by variables defined in the algorithms.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2016-10-19
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.