Task scheduling algorithms using algorithms like ACO PSO and MBO Optimization of Task Scheduling in Cloud Computing Environments
Introduction
Over the period in past few years, cloud computing has been changing in order to traditional cloud computing by providing benefits like on-demand services and broad access mobile services. Scheduling provides optimal allocation of resources among given tasks in a finite time to achieve a desired quality of service. The aim of the scheduling process to build a algorithm that specifies when and on which resource each task will be executed. In recent years, distributed computing has gained much attention due to high scalability, reliability, information sharing and low-cost than single processors standalone machines. Cloud computing has emerged the most popular distributed computing paradigm out of all other in the current environment. Cloud computing guarantees quality of service (QoS) to the users. To provide Quality of Service to the users, it is very important that jobs should be efficiently allocated to given resources. If the desired performance is not achieved, the users will hesitate to pay. Therefore the scheduling process is considered as the most important part in the cloud computing systems. The problems of mapping tasks on unlimited computing resources in cloud computing it is known as a category of problems called as NP-hard problems. There are no algorithm is made to give optimal solution to a task allocation and scheduling problem within a polynomial time. Solution based on a very large search are not feasible because the cost of generating scheduling is very high. Metaheuristic techniques like MBO, ACO and PSO deals with these problems by providing near optimal solution within a reasonable time. These techniques has gained huge popularity due to its effectiveness to solve large complex problems in a short span of time. In this paper, an extensive review is presented on two metaheuristic techniques namely Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO) and Monarch Butterfly Optimization (MBO). Scheduling algorithms differs on dependency among the tasks to be scheduled. If there is some precedence in the existing tasks, the task only can be scheduled after the parent task is completed, but in this case tasks are independent to each other, they can be scheduled in any sequence.