Characterizing Dynamic Load Balancing in Cloud Environments Using Virtual Machine Deployment Models

Abstract

The ever growing computational demands of users call for efficient cloud resource management to avoid service-level agreement (SLA) violation. Virtualization co-locates multiple virtual machines (VMs) on a single physical server to share the underlying resources for efficient resource management. However, the decision about ''what'' and ''where'' to place workloads significantly impacts performance of hosted workloads. Existing cloud schedulers consider a single resource (RAM) to co-locate workloads that as a result lead to SLA violation due to non-optimal VM placement. To handle this issue, current study has updated nova scheduler to propose a multi-resource based VM placement approach to improve application performance in terms of central processing unit (CPU) utilization and execution time. Experimentally we have shown that our proposed method has lessened application execution time by 50% when compared with one of the well-known technique.

A Predictive Priority-Based Dynamic Resource Provisioning Scheme With Load Balancing in Heterogeneous Cloud Computing

“…After checking the condition LN==0. In our proposed model we calculate the user request load according to the emergencies that will be calculated by LP(j) using equation (2).…”

“…When cloud consideration takes place, usually load balancing technique highly requires to distribute the task load among different VMs. Without it, the unequal burdens in server formation may cause asset wastage, execution corruption, and SLA violation [2]. Accordingly, using the right load balancing strategy can improve servers' usage and give better assurance of Quality of Service (QoS) [3].…”

TMaR: a two-stage MapReduce scheduler for heterogeneous environments

“…Liaqat et al [32] extended the Nova scheduler to propose a multi-resource based VM placement approach to improving application performance in terms of the central processing unit (CPU) utilization and execution time in the heterogeneous environments. The authors have designed three modules, including, Compute Load (CL), Load Analyzer (LA), and Load Filter (LF) for implementing their VM placement architecture.…”

Balanced Energy-Aware and Fault-Tolerant Data Center Scheduling

“…Data centers are being extensively used for internal operations and Information Technology (IT) services of government organization, Internet service providers (ISP), commercial IT services providers, cloud computing service providers, industrial units, and educational institutions. Two types of application are common in data centers, (a) outward web content, e.g., video streams, web pages, and (b) internal processing, e.g., indexing, jobs scheduling [1,2].…”