Task Severance and Task Parceling Based Ant Algorithm for Grid Scheduling”, International journal of computational cognition (http://www.ijcc.us

Abstract — Grid computing is one of the latest technologies to solve very complex problems like scientific applications, using the resource sharing concept in the dynamic virtual organizations. Integrating, coordinating, managing of resources, job allocation and scheduling play a very important role in achieving a high performance in the grid environment. It is clear that grid scheduling plays a vital role in the grid environment. To produce guaranteed quality of service (QoS) in such environments is a challenging task. In recent times, QoS based grid scheduling algorithm has become a hot research topic. To get an optimal scheduling in the grid environment is an NP-complete problem. Heuristic and approximate solution is possible to solve the NP-complete problem. So, a heuristic algorithm that includes QoS parameters is a very good choice for grid scheduling. This paper proposes two algorithms namely Task severance and Task Parceling. The proposed algorithms consider the QoS parameter of the job and the resources. The free time, CPU speed of the resources, Communication delay of the Network and the execution time of jobs are taken into account by the proposed algorithms in order to scale better utilization of resources and better scheduling of jobs. The simulation results show that the proposed algorithms namely, Task severance and Task parceling can effectively produce better results than the existing algorithm. The proposed algorithm can also reduce the makespan and improve the resource utilization rate in addition to meeting the QoS requirement of tasks with its best efforts