8326

7724

كارشناسي ارشد

نرم افزار

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1392

دوازده،114ص.: مصور،جدول،نمودار

ص.ع.به فارسي و انگليسي

علي فانيان

3/10/92

محمدعلي منتظري، ناصر قديري مدرس

مهندسي برق و كامپيوتر

ID7724

به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي

Abstract Grid computing is a high performance computing environment to solve larger scale computational demands This technology which is now considered as an alternative to supercomputers contains different issues such as resource management job scheduling security problems and information management However job scheduling is a fundamental issue in achieving high performance in grid computing systems Most of the applications are a set of interdependent tasks Complete execution of all tasks with a applications is known as workflow By developing workflow management systems the grids become able to design manage and execute different type of the workflows One of the important issues in this system is to find workflow scheduling solutions and assign tasks to grid resources Scheduling solution has an important effect on system performance and should have optimal execution time and cost In this thesis a new workflow scheduling method in grid environment is proposed that it is able to generate a set of optimal scheduling solutions with low consumed time The proposed method is based on multi objective genetic algorithm to optimize workflow execution time and cost simultaneously In this model workflows are divided to some sequential levels that can help to remove checking workflow dependencies during the scheduling process New definitions and operators for this model are proposed and implemented Then the proposed method in different aspects is widely compared with similar methods The simulation results clearly show that the proposed method has a good performance in comparison to the other well known methods Keywords grid computing scheduling multi objective genetic algorithm workflow PDF created with pdfFactory trial version www pdffactory com

علي فانيان

محمدعلي منتظري، ناصر قديري مدرس