A Model Based Load-Balancing Method in IaaS Cloud

Infrastructure as a Service (IaaS) is important in Cloud Computing, which provides on-demand virtual machines (VMs) to users. Proper deployment of the virtual machine onto available hosts plays an important role on the load-balancing of modern data center. At present, many load-balancing methods are based on the load forecasting model, that could predict the resource requirements of the virtual machine. However, the resource requirement of virtual machine in IaaS Cloud is hard to predict because there will be variety of load types in IaaS cloud. Moreover, a variety of heterogeneous hardware environments and virtualization technologies make it hard to predict the requirement of virtual machine based on the workloads. To address the problem, we propose a model based method to predict and calculate the resource requirement of each virtual machine, and using this model to design a load-balancing framework in IaaS Cloud. The contribution of this paper includes: (1) A model that forecast the load and estimate the resource requirement of virtual machines in IaaS Cloud, (2) A scalable framework for load-balancing which uses our resource requirement forecasting model. Experiments show that our method can accurately estimate the resource requirements of virtual machines, and work well in our load-balancing framework.