Burst‐aware virtual machine migration for improving performance in the cloud

Abstract

Burst is a common pattern in the user's requirements, which suddenly increases the workload of virtual machines (VMs) and reduces the performance and energy efficiency of cloud computing systems (CCS). Virtualization technology with the ability to migrate VMs attempts to solve this problem. By migration, VMs can be dynamically consolidated to the users' requests. Burst temporarily increases the workload. Ignoring this issue will lead to incorrect decisions regarding the migration of VMs. It increases the number of migrations and Service Level Agreement Violations (SLAVs) due to overload. This may cause waste of resources, increase in energy consumption, and misplaced VMs. Therefore, a burst-aware method for these issues is proposed in this paper. The method consists of two algorithms: one for determining the migration time and the other for the placement of VMs. We use the PlanetLab real dataset and CloudSim simulator to evaluate the performance of the proposed method. The results confirm the advantages of the method regarding performance compared to benchmark methods.

DBSHD: Dynamic Burst-aware Source Host Detection in the Cloud

“…Table 1 contains a comparison of the related literature and underlines the characteristics of the current research. As it is shown, there are few studies such as [7,17,34,42], which, detection of underloaded and overloaded hosts is not sensitive to the workload explosions. Detection of these hosts, while considering the bursts, plays a key role in energy saving and performance improvement in the cloud computing systems.…”

“…The goal is to provide services for different users with the least energy consumption, violations of the SLA and consolidation ratios. For this purpose we have used the ESC metric suggested in [17]. Consequently, the objective function is defined as follows min ESC Subject to:…”

“…To evaluate the performance of cloud computing systems, we used the ESC criterion according to equation( 22), which we defined in our previous work [17]. As can be seen, the effective criteria in ESC include energy consumption, SLAV and CR.…”

“…However, this situation might occur due to workload explosions or bursts, which are transient and only last for a small amount of time. These bursts reduce the performance and the energy efficiency of the system by increasing the migration counts, SLA violation, and Consolidation Ratio (CR) [17]. The CR is the percentage of the hosts which are turned off during the VM consolidation.…”

“…The CR is the percentage of the hosts which are turned off during the VM consolidation. In a previous effort [17], we proposed a static burst-aware algorithm called Random Early Detection of the Migration Time (REDMT) to identify the source hosts. In this study, we present a dynamic burstiness-aware method to identify source hosts.…”