Metaheuristic task scheduling in cloud computing

In recent years, cloud computing has attracted attention due to its high scalability, reliability, information sharing and low cost. Cloud computing has the advantage of providing a flexible, high-performance, pay as you use and on-demand service. The cloud service provider must adhere to the Service Level Agreement to provide user satisfaction. Makespan should not be too long and dynamic load balancing between servers is required to increase resource usage. Therefore, scheduling tasks dynamically and effectively is a critical issue that needs to be solved. In this thesis, task scheduling algorithms based on meta-heuristic algorithms, have been developed for tasks running in cloud environment. In this thesis, it is aimed to improve the load balancing of the independent tasks on the machines and to reduce the completion time of the process by using dynamic and static task scheduling techniques for the tasks in cloud. These approaches have been compared with the methods known in the literature. In various cases, it has been found that the developed approaches outperformed than the compared methods. Keywords: Cloud computing, Cloudsim, static task scheduling, dynamic task scheduling, meta heuristic algorithms, genetic algorithm, simulated annealing, greedy approach, differential evolution algorithm.