Computing Grid Scheduling Algorithm Research

Along with the rapid evolution of network computing technologies, grids can be built on geographically distributed resources. In the past, high-performance computing is confined to one administration domain. Now, computational grids can improve the job execution performance by balancing the job loads of administration domains, and solve some large-scale complicated problems by coordinating computation resources in multiple domains. So, computational grids are considered as the prevailing platform for future high-performance computing. As a new computing infrastructure, computational grids have not yet been investigated well in many aspects, including, but not limited to, architecture, security, resource management and scheduling, and programming environment, which become the discussion topics of many international computer-related conferences recently.Grid system consists of a wide variety of geographically distributed resources and these resources are heterogeneous,geographically distributed and dynamically available.High scheduling algorithm would be able to increase thtoughput,maximize system utilization,and fulfill economical system and user constraints,Min-min algorithm is a simple and fast algorithm,and able to deliver good performance,but with the drawback of limitation of load balance.In this paper the transmission and execution of jobs were analyzed first. Then the completion time of the Min-min algorithm was computed and improved based on the schedule model. Furthermore, in order to improve the load balance of the Min-min algorithm, priority was assigned to the jobs according to different schedule limitations, and jobs were scheduled based on these priorities. Finally the OTE Min-min algorithm was proposed based on the analysis.Through the use of network simulation tools GridSim to test the simulation data which has been improved by the Min-min algorithm.The results show,when the task number and computing number of nodes higher,the performances of Min-min improved algorithm has been enhanced the the Min-min algorithm.At this point,a computing node are assigned a number of tasks. Min-min improved algorithm make the transmission time and execution time overlapped which were distributioned in the same computing nodes,thereby reducing the total task completion time.So the improvements of Min-min algorithm are feasible.