Virtual Machine Replication on Achieving Energy-Efficiency in a Cloud

Abstract

Abstract:The rapid growth in cloud service demand has led to the establishment of large-scale virtualized data centers in which virtual machines (VMs) are used to handle user requests for service. A user's request cannot be completed if the VM fails. Replication mechanisms can be used to mitigate the impact of failures. Further, data centers consume a large amount of energy resulting in high operating costs and contributing to significant greenhouse gas (GHG) emissions. In this paper, we focus on Infrastructure as a Service (IaaS) cloud where user job requests are processed by VMs and analyze the effectiveness of VM replications in terms of job completion time performance as well as energy consumption. Three different schemes: cold, warm, and hot replications are considered. The trade-offs between job completion time and energy consumption in different replication schemes are characterized through comprehensive analytical models which capture VM state transitions and associated power consumption patterns. The effectiveness of replication schemes are demonstrated through experimental results. To verify the validity of the proposed analytical models, we extend the widely used cloud simulator CloudSim and compare the simulation results with analytical solutions.

Optimal Virtual Machine Placement Based on Grey Wolf Optimization

“…After all wolves have updated their positions, not all solutions are feasible according to the constraints in Equations (2)- (6). Each infeasible solution must be transformed into a feasible solution before α, β, and δ are chosen.…”

“…Each infeasible solution must be transformed into a feasible solution before α, β, and δ are chosen. We propose an approach, namely, RIS, for correcting the updated positions according to the constraints of Equations (2)- (6). RIS consists of three procedures: (1) eliminating the duplicate assignments, (2) obviating the overload assignments, and (3) reassigning the unallocated VMs.…”

“…This operation is used to determine whether the load of a PM satisfies the constraints in Equations (5) and (6). For each overloaded PM i, we decrease the load by moving some of the VMs that are assigned to PM i to another PM.…”

“…In IaaS, cloud computing offers an unlimited amount of heterogeneous resources with high elasticity of use via a virtualization technique [4]. A virtual machine (VM) is created to host an application according to the customer requirements for resources such as CPU, memory, storage, and bandwidth [5,6]. The virtualization technique enables multiple VMs to share the physical resources on the same physical machine (PM).…”

Energy Saving in Data Centers

“…In "Virtual Machine Replication on Achieving Energy-Efficiency in a Cloud," Mondal et al [7] take on the issue of virtualization, as growth in cloud service demand has led to the establishment of large-scale virtualized data centers in which virtual machines are used to handle user requests for service. To mitigate failures, replication techniques are used.…”