Indian Journal of Science and Technology

Abstract

Objectives: The load balancing becomes an important point for performance and stability of the system. Therefore, it is needed an algorithm for enhancing the system performance by balancing workload among VMs. Methods: Task scheduling algorithms are used to achieve the load balancing and QoS. The proposed Load Balancing Decision Algorithm(LBDA) to manage and balance the load between the virtual machines in a datacenter along with reducing the completion time (Makespan) and Response time. Findings: The mechanism of LBDA is based on three stages, first calculates the VM capacity and VM load to categorize the VMs’ states (Under loaded VM, Balanced VM, High Balance VM, Overloaded). Second, calculate the time required to execute the task in each VM. Finally, makes a decision to distribute the tasks among the VMs based on VM state and task time required. Improvements: We compared the result of our proposed LBDA with MaxMin, Shortest Job Firstand Round Robin. The results showed that the proposed LBDA is more efficient than the existing algorithms.

Keywords: Cloud Computing, LBDA, Load Balancing, Makespan, Response Time, Task Scheduling