Threshold Based Multi-Objective Memetic Optimized Round Robin Scheduling for Resource Efficient Load Balancing in Cloud

Abstract

Task scheduling is a significant problem to be resolved for balancing the workload on a cloud server. One of the key problems that affect the scheduling performance is burstiness workloads. Few research studies have been introduced to schedule tasks and balancing loads in the cloud. However, scheduling performance of existing technique was not effective in burstiness workload’s conditions. Thus, there is a need for a novel task scheduling technique to handle bursty user demands and provide high-quality cloud services. Therefore, Threshold Based Multi-Objective Memetic Optimized Round Robin Scheduling (T-MMORRS) Technique is proposed in this research work. At first, user requests are sent to the cloud server. After that, T-MMORRS Technique employs burst detector to determine the workload condition as normal or that which is bursty. Based on burst detector result, then T-MMORRS Technique adapts the two different load balancing algorithms for efficiently scheduling the user tasks. The T-MMORRS Technique chooses Threshold Multi-Objective Memetic Optimization (TMMO) in normal workload situation and Weighted Multi-Objective Memetic Optimized Round Robin Scheduling (WMMORRS) in burstiness workload state. Finally, the selected load balancing algorithm in MMORRS Technique schedules the user request task to a resource-efficient virtual machine with higher efficiency and lower time consumption. As a result, T-MMORRS Technique enhances the task scheduling performance to balance the both bursty and non-bursty workloads of virtual machines in the cloud. The experimental evaluation of T-MMORRS Technique is conducted using factors such as scheduling efficiency, scheduling time and energy consumption with respect to the number of user requests. The experimental result shows that the T-MMORRS Technique can enhance the scheduling efficiency and also minimizes the energy usage in the cloud as compared to state-of-the-art works.