Scheduling jobs on grid computing using firefly algorithm

Abstract

Scheduling jobs on computational grids is identified as NP-complete problem due to the heterogeneity of resources; the resources belong to different administrative domains and apply different management policies. This paper presents a novel metaheuristics method based on Firefly Algorithm (FA) for scheduling jobs on grid computing. The proposed method is to dynamically create an optimal schedule to complete the jobs within minimum makespan. The proposed method is compared with other heuristic methods using simple and different simulation scenarios. Each firefly represents a candidate solution of the grid scheduling problem in a vector form, with n elements; where n is the number of jobs to be scheduled. Firefly[i] specifies the resource to which the job number i is allocated. Therefore, the vector values are natural numbers. Also we note that the vector values are the resource IDs and hence the resource ID may appear more than one time in the firefly vector. This comes about because more than one job may be allocated to the same resource. To evaluate the effectiveness and the efficiency of job scheduling algorithms on computational grid, it is difficult and impractical to achieve performance assessment experimentally in such large scale heterogeneous system and to repeat and control the experiments to perform different scenarios. To encounter this limitation this research used mathematical modeling and simulation to model and evaluate the proposed mechanism. The results demonstrated that, the firefly scheduling mechanism achieved less makespan time than Min-Min and Max- Min heuristics in several scheduling scenarios. The results in this paper showed that the FA is promising method that can be used to optimize scheduling jobs on grid computing.