Wednesday, September 30, 2020 Home   | Search
Viewing Abstract

Page: 1-6 ------------------------------> Last_modified :7/11/2017 12:11:00 PM

Title: Comparison of Ant Colony Optimization & Particle Swarm Optimization in Grid Scheduling
Authors: B.Booba ; T.V.Gopal
Aff: University, Chennai, Tamil Nadu, India
Author Email:
Keywords: Grid Computing; Job Scheduling; ACO; PSO; Grid Scheduling
Abstract:Background:Computational Grids are a modern trend in distributed computing applications includes searching and sharing of resources for a particular job in geographically distributed heterogeneous computing systems. Grid computing allows finding efficient allocation of resources to jobs submitted by users by making appropriate scheduling decisions.Objective: In a grid environment an important issue associated with efficient utilization of resources can be done by job scheduling. As per the demand of scheduling the job scheduling is implemented as an integrated part of parallel and distributed computing. It selects the correct match of resource for a particular job providing an increase in job throughput and performance. It is often difficult to find an exact resource for a defined job to make the scheduling of job efficiently an ant colony algorithm is proposed for allocating optimal resources to each job at a minimal execution time. Result:In this paper Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) is proposed to solve and find an exact resource allocation by choosing shortest and the optimal path for a required specific job, minimizing the schedule of length of jobs with minimum make span and execution time. This paper distinguishes both optimization methods and concluded it with its best performance.Conclusion:PSO is considered as best optimization with low computational cost. The stimulated annealing method is used as global optimization so search the optimal solution compared with ACO.lass=st