Conclusion And Future Work
This paper elaborated the major problem of load scheduling in the cloud computing environment between cloudlets and VMs. The meta-heuristic based swarm intelligence technique for load scheduling in the cloud is discussed. The concepts of load scheduling algorithms with proposed Cloudy-GSA on load scheduling has been explained. The proposed Cloudy-GSA approach reduces the transfer time and total cost of the system along with maximum utilization of VMs. This has been achieved using the fitness values of particles and force acting on the particles in search space. At a bigger context, proposed approach provides higher cost optimization than the existing Segmented Min-Min, Tabu Search, Genetic Algorithm, Simulated Annealing, Genetic Simulated Annealing, FCFS, Min-Min and Particle Swarm Optimization scheduling algorithms. The results of the proposed approach have been compared with the existing discussed scheduling algorithms which are heuristic and non-heuristic in nature in a detailed manner on a large set of iterations. Thus, the proposed CloudyGSA optimization method generates far better results in terms of transfer time and total cost of execution time based on the convergence statistical analysis. The future work aims to minimize the total cost by using improved fitness function considering other parameters for better minimized results in the cloud computing environment, based on swarm intelligence to further reduce the total cost.
