International journal of computer technology and applications
Paginering:
Jaargang 01 (2010) nr. 01 pagina's 43-53
Jaar:
2010
Inhoud:
Grid computing is to make multiple machines that may be in different physical locations, behave like they are one large virtual machine. Grid scheduling environment is a arranging the machines in the course of find it fast called the Ant algorithm. The find for resource in the collection of geographically distributed heterogeneous computing systems and making scheduling decisions, taking into consideration eminence of service. Allocation of resources to a large number of jobs in a grid computing environment presents more difficulty than in network computational environments. Resource and job will have been allocating by resource discovery and filtering, composed of the selection of resources and idea specific scheduling and job submission. This algorithm is evaluated using the simulated execution times for a grid environment. Before starting the grid scheduling, the expected execution time for each task on each machine must be estimated and represented by an Expected Time calculation. The proposed scheduler allocates adopt the system environment freely at runtime. This resource optimally and adaptively in the scalable, dynamic and distribute controlled environment. Conclude of this propose depending upon the performance of the grid systems. Key words: Grid Computing, Job Scheduling, Heuristic Algorithm, Load Balancing, scheduling algorithm simulation, ant algorithm
Tijdschrift beschrijving