A Taxonomy of Load Balancing Techniques in Cloud Computing

Abstract

Nowadays cloud computing is considered as the latest network infrastructure that supports large-scale decentralized computing. Its components rely on different design aspect of multiple mature networks structures (cluster commodity, utility computing, virtualization, Datacenters, and grid structure). The ultimate goal of cloud technology is to efficiently afford services to the users using the concept (Pay-for- Use) which implies cutting down the infrastructure costs when setting up a new business. It also makes the data that users need available and accessible in a way that does not require any kind of knowledge of the underlying infrastructure and meets the Service Level Agreement (SLA) requirements. One of the key problems in cloud computing is load balancing since it should ensure fair and dynamic distribution of loads among all computation nodes and harnesses the minimum power consumption. Load balancing facilitates resources utilization, sustains the minimum response time and guarantees data availability. This paper first, discusses and criticizes the strategies and policies of load balancing in cloud computing environment, then it compares them using different parameters such as throughput, availability, resources utilization, scalability etc. It also illustrates the multiple tools that have been used to implement and simulate these techniques under various experiments and environments.