الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 94 |  |  |
| | | from | 94 | | |
Abstract
Cloud computing (CC) has become one of the most required platforms in
Information Technology (IT) due to providing inexpensive services with
scalability and high availability. Most of large companies move toward cloud
computing companies to host the platforms of different services due to their
flexibility and scalability features. CC reacts faster to the needs of business and
the resources can be scaled up/down according to the load beaks. The dynamic
nature of the cloud computing systems makes scheduling of workflow tasks
which is an important issue. Task scheduling is the allocation of the incoming
tasks to the available resources virtual machines (VMs) aiming to reduce the
overall time to finish the tasks. Task scheduling algorithms are broadly
classified into two categories namely; static and dynamic task scheduling
algorithms. In static task scheduling, all information regarding the state of the
resources and the tasks are known before the execution. While in the dynamic
scheduling, all information of the tasks are not known beforehand. Thus,
execution time of the task may not be known, and the allocation of the tasks is
done during run time.
The main objective of this thesis is to develop an algorithm that schedules
applications’ tasks of customers to the virtual machines of the cloud with the
objective of minimizing both time and monetary costs. This objective
represents a major challenge because of the competition between the two
objectives.
In this thesis, we presented evaluate a proposed algorithm, called Improved
Cost Task Scheduling (ICTS) algorithm, for scheduling tasks in cloud
computing environment. The algorithm considers minimizing both the time and
monetary cost when using cloud resources. The algorithm contains three
phases: level sorting, task-prioritizing and VM selection. from the
experimental results, it is concluded that the ICTS algorithm provides an
improvement in scheduling length as well as significant monetary cost saving.
iii
It minimizes make-span by about 28.94 % and decreasing the monetary cost by
about 16.2 %.