A Performance Improvement Model for Cloud Computing Using Simulated Annealing Algorithm

Abstract

Cloud system has emerged as a fast computing technology wherein it delivers its services to users with minimum cost and time. The number of cloud users are also increasing too fast. With this increased number of users, there is a need of efficient algorithms which would be able to maximize the resource utilization, scheduling jobs in optimal manner leading to maximum profit and improved overall cloud performance. Research trends show that meta-heuristic optimization algorithms have been successfully applied to enhance the performance of cloud system. In this research, a simulated annealing based concept has been applied for job scheduling with the aim of minimizing the overall execution time of a job schedule selected from the job pool and balancing the loads in the available virtual machines. The algorithm has been simulated in CloudSim environment and it has been seen that it provides non-dominance optimal solution and is able to achieve reduced execution time of job schedule in comparison to other existing algorithms like FCFS, min-min algorithm and RR and Iterative Improvement.