A taxonomic survey on load balancing in cloud

Abstract

Cloud computing aims to provide seamless computing services to the millions of consumers across the world. Datacenter, the engine of cloud computing, hosts large scale computing resources (hardware and software) at the backend of cloud. In the recent years, the rising demand for cloud computing services is increasing the load on datacenters. Moreover, cloud computing environment is highly dynamic in terms of workload patterns and system behaviour, which often leads to load imbalance across the datacenter resources. Due to load imbalance, some of the datacenter resources may get overloaded/underloaded, which leads to performance degradation and resource wastage. Load balancing helps to maximize resource utilization and achieve desired Quality of Service (QoS) in cloud by employing optimal resource allocation and workload distribution approaches both at schedule time and runtime. Recognizing its relevance and importance, a great deal of research has been attributed to the issue of load balancing in cloud and many load balancing algorithms has been proposed in literature. This paper presents a systematic survey of the state-of-the-art load balancing algorithms proposed for cloud computing environment. The survey is systemized by proposing a novel taxonomy of load balancing algorithms in cloud. For the ready reference of the readers, a brief summary and a comparative analysis of various promising load balancing algorithms is also included in the survey. The survey also discusses various issues and challenges along with trail to their possible solutions.