Dynamic Load Balancing Approach for Minimizing the Response Time Using An Enhanced Throttled Load Balancer in Cloud Computing

Abstract

Cloud computing covers a broad range of cloud-based service models such as SaaS: Software as a Service, PaaS: Platform as a Service, IaaS: Infrastructure as a Service, XaaS: Everything as a Service, NaaS: Network as a Service and RaaS: Recovery as a Service. Whether the users are looking at SaaS, PaaS, IaaS, XaaS, NaaS or RaaS, the estimations are the same; fast development of the workloads placed on the VMs in the cloud and a maximized percentage of the IT budget moving toward cloud computing. Therefore, there is a need for an enhanced VM level load balancer to balance the VM level load. In this research, different dynamic load-balancing methods and enhanced algorithms are analyzed to develop a load balancer for allocating the workloads evenly to the VMs and to migrate the excess tasks from the overloaded VMs to the underloaded VMs. The motivation of our research is to propose an Enhanced Throttled Load Balancer for allocating the workloads evenly to all VMs and for minimizing the delay time and response time of the service. The proposed load balancer distributes the arriving requests evenly to all VMs and allocates the resources dynamically. Using the threshold value, the proposed load balancer categorizes the VMs as overloaded VMs, underloaded VMs and balanced VMs. If there is an overloaded VM then the proposed Enhanced Throttled Load Balancer finds out the suitable underloaded VM and automatically begins the task migration process to migrate the task to the underloaded VM from the overloaded VM thereby balance the load on VMs. The main use of the proposed load balancer is to balance the load on VMs and to control the overhead of the VM. This paper presents a dynamic load balancing approach using Enhanced Throttled Load Balancer that aids to reduce the delay time and the response time of the service.