A Task Scheduling Algorithm with Efficient Number of Tasks in Distributed Systems

Often, cloud computing is used synonymously with such terms as utility computing (or on-demand computing),software as a service (SaaS), and grid computing. However, as we will show, utility computing and SaaS can bepresented as two of several forms of services that cloud computing can provide. In a distributed system, timing andmapping the priority of tasks among processors are of great importance. This consists of mapping a Directed AcyclicGraph (DAG) to a set of tasks on a number of parallel processors and its purpose is allocating tasks to the availableprocessors, in order to satisfy the needs of priority and decency of tasks, and also to minimize the execution time in thegraph totally. In this paper, we’ll propose a task scheduling algorithm by employing additional lambda value parameter.To evaluate the proposed method, it is compared to the schedule list algorithm. Simulations show that our approachoutperforms the benchmark schedule list algorithm.

Keywords:

task scheduling , cloud computing , distributed systems