Abstract
Cloud computing (CC) is fast-growing and frequently adopted in information technology (IT) environments due to the benefits it offers. Task scheduling and load balancing are amongst the hot topics in the realm of CC. To overcome the shortcomings of the existing task scheduling and load balancing approaches, we propose a novel approach that uses dominant sequence clustering (DSC) for task scheduling and a weighted least connection (WLC) algorithm for load balancing. First, users’ tasks are clustered using the DSC algorithm, which represents user tasks as graph of one or more clusters. After task clustering, each task is ranked using Modified Heterogeneous Earliest Finish Time (MHEFT) algorithm. where the highest priority task is scheduled first. Afterwards, virtual machines (VM) are clustered using a mean shift clustering (MSC) algorithm using kernel functions. Load balancing is subsequently performed using a WLC algorithm, which distributes the load based on server weight and capacity as well as client connectivity to server. A highly weighted or least connected server is selected for task allocation, which in turn increases the response time. Finally, we evaluate the proposed architecture using metrics such as response time, makespan, resource utilization, and service reliability.
Highlights
A growing number of organizations and industrial companies deploy their applications in cloud data centers due to the economy of scale provided by cloud computing [1]
This research proposes a novel approach for task scheduling and load balancing using the dominant sequence clustering (DSC) and mean shift clustering (MSC) algorithms to increase response time for user task
The weighted least connection (WLC) algorithm, which assigns weight to each virtual machines (VM) on the basis of its client connectivity, Central Processing Unit (CPU) idle rate, and CPU speed, is used for load balancing after clustering
Summary
A growing number of organizations and industrial companies deploy their applications in cloud data centers due to the economy of scale provided by cloud computing [1]. To support the increased user demand, cloud computing service providers support ubiquitous services with pay-as-you-go payment methods. Task scheduling and load balancing are among the major challenges that are being faced by cloud adopters and are investigated by academia, research and industry [2]. Scheduling is a balancing scenario in which operations or tasks are scheduled according to the specific requirements and algorithm used. The purpose of scheduling algorithms in distributed load deployment systems is to optimize the processors and minimize the time of execution of the task. The main purpose is to establish a schedule of posts on adaptable resources according to adaptable time, which includes the identification of an appropriate sequence in which functions can be implemented within the framework of transaction logic constraints [3].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have