Artificial Bee Colony Algorithm for Cloud Task Scheduling

Abstract

Cloud computing services are becoming ubiquitous, and are becoming the primary source of computing power for both enterprises and personal computing applications. One of the fundamental issues in this environment is related to task scheduling. The scheduler should do the scheduling process efficiently in order to utilize the available resources. In this paper a cloud task scheduling policy based on artificial bee colony algorithm compared with different scheduling algorithms has been proposed. The main goal of the proposed algorithm is minimizing the makespan of a given tasks set. Artificial bee colony algorithm models the behavior of honey bees and can be used to find solutions for difficult or impossible combinatorial problems. Algorithms have been simulated using Cloudsim toolkit package. Experimental results showed that the artificial bee colony algorithm outperformed ACO, FPLTF and FCFS algorithms.

Hybrid Algorithm Based on Swarm Intelligence Techniques for Dynamic Tasks Scheduling in Cloud Computing

“…The cloud task scheduling algorithms to be compared in the experiments of this subsection include ABC algorith m in [9], PSO in [8], ACO in [7] and the proposed hybrid algorith m. The parameter settings of ABC algorith m are as follo ws. Number_of_Bees=100, Number_of_active=75,Number_of_Scout=15,Number_of _Inactive=10,Max_number_of_Vists=70, Prob_Mistake= 0.1, Prob_Presuasion=0.90 and t max =100 as in [9]. The parameter settings of PSO algorith m are as fo llo ws.…”

“…After that, sites that have the highest fitness are selected for a neighborhood search. Then, the algorithm continues searching for the selected sites by assigning more act ive bees to search in the neighborhood of these sites [9]. The co lony will contain after iterat ion two groups for its new population, the solutions from each selected sites and the scout bees assigned to generate random solutions.…”

“…The co lony will contain after iterat ion two groups for its new population, the solutions from each selected sites and the scout bees assigned to generate random solutions. This process is repeated until meeting a given stopping criterion [9].…”

“…Cloud task scheduling based on artificial bee colony algorith m has been proposed in [9]. It simulates the behavior of foraging bees to the cloud scheduling problem.…”

“…This hybrid algorith m merges the behaviors of A CO, ABC and PSO techniques. The simulation based experiments using CloudSim in [6], studies the performance of proposed hybrid algorith m co mpared to ACO in [7], PSO in [8], and ABC in [9]. The results fro m experiments show that the proposed hybrid algorith m can obtain better VMs utilizat ion and remarkably outperforms the co mpared methods on the basis of makespan and degree of imbalance.…”