Title page for etd-0630113-110110


[Back to Results | New Search]

URN etd-0630113-110110
Author Wei-Cheng Huang
Author's Email Address No Public.
Statistics This thesis had been viewed 5584 times. Download 0 times.
Department Computer Science and Engineering
Year 2012
Semester 2
Degree Master
Type of Document
Language zh-TW.Big5 Chinese
Title Hyper-heuristic-based Workflow Scheduling: Using Cloud Workflow as a Case
Date of Defense 2013-07-03
Page Count 76
Keyword
  • workflow
  • workflow scheduling
  • hyper-heuristic
  • cloud computing
  • metaheuristic
  • cloudsim
  • Abstract None of the metaheuristics and the traditional algortihms ever proposed are perfect for all the cloud scheduling problems. In order to leverage the strengths of all the metaheuristics, the hyper-heuristic was proposed to analyze the features of the low-level metaheuristics
    and to decide the timing of using a particular low-level metaheuristic to do the global or local search. The interaction mechanism of high level strategies makes it easier for applying the hyper-heuristic to optimization problems. In this thesis, we propose a “hyper-heuristic-based workflow scheduling algorithm,” which uses two detection operators—the diversity detection and improvement detection operators—to dynamically decide when to change the low-level
    metaheuristic. At the time of the change, the solution obtained by the old low-level metaheuristic will be returned to the high level control center. Then, the high level perturbation method will use the evolution information to fine-tune the returned solution before passing it on to the new low-level metaheuristic. To evaluate the performance of the proposed method, we compare it with six state-of-the-art scheduling algorithms, by implementing all of them on cloudsim, a cloud simulator. The experimental results show that the proposed method is quite promising.
    Advisory Committee
  • Chu-Sing Yang - chair
  • Tzung-Pei Hong - co-chair
  • Chun-Wei Tsai - co-chair
  • Ming-Chao Chiang - advisor
  • Files
  • etd-0630113-110110.pdf
  • Indicate in-campus at 99 year and off-campus access at 99 year.
    Date of Submission 2013-08-07

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys