“Survey on Various Performance Improvement Policies for Cloud Computing”

Abstract

Abstract-Cloud computing technology serves "computing resources as a service" to cloud users. Cloud users can "Pay and use" computing service from cloud service provides. Cloud computing mainly based on virtualization technology and main idea of the cloud is "sharing of computing resources", which attract users to utilizes cloud services. Most of the IT companies are working on cloud, which increases cloud users. Higher growth of cloud services and cloud consumers results in a delay in services. So it is necessary for cloud service provider to get optimum utilization of computing resources for better performance. In cloud computing system performance totally depends on efficient and optimistic utilization of computing resources. That can be achieved by efficient load distribution policies. Load balancing is the process of apportioning the load among various working nodes of a distributed system to improve both resource utilization and job response time while avoiding a situation where some of the nodes are heavily loaded while others are underloaded. Load balancing ensures that every node in the system does the approximately equal amount of work as per their capacity at any instant of time. Various cloud researchers are working on cloud load balancing methods and suggest different algorithms. This survey paper presents a detailed study of different load balancing policies available for cloud computing and also performs a comparative analysis based on various parameters.