Performance analysis of an energy efficient virtual machine consolidation algorithm in cloud computing

International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print),
ISSN 0976 - 6375(Online), Volume 6, Issue 5, May (2015), pp. 24-35© IAEME
24
PERFORMANCE ANALYSIS OF AN ENERGY EFFICIENT
VIRTUAL MACHINE CONSOLIDATION ALGORITHM IN
CLOUD COMPUTING
Ms Jayshri Damodar Pagare
Research Scholar, Sant Gadge Baba Amravati University, Amravati, India
Dr. Nitin A Koli
Head, Computer centre, Sant Gadge Baba Amravati University, Amravati, India
ABSTRACT
VM consolidation has been shown as a one of the promising technique for saving energy
costs of a data center, it is an effective way to improve the utilization of resources and energy
efficiency in cloud data centers. In this paper, for cloud environments, a VMs consolidation approach
is proposed as energy efficiency is becoming a very important issue in Cloud Computing
environments and can be achieved using virtual machine consolidation. Proposed algorithms have
been implemented and evaluated using CloudSim simulator. Simulation results show improvement
in energy consumption which leads to energy efficiency.
Keywords: Energy Efficiency, Data Center, Cloud Computing, Virtual Machine Consolidation.
1. INTRODUCTION
The use of virtualization allows providers to run multiple workloads from different customers
on the same computing infrastructure which makes Cloud Computing as a promising approach to
improve resources utilization. With adoption of virtualization services, cloud computing platforms
are becoming more popular. However, Cloud providers rely on large and power-consuming data
centers. The wide adoption of virtualization and cloud computing has added another layer of
complexity to enabling an energy-efficient use of computing power in large-scale settings[1].Energy
consumption has always been a major concern in the design and cost of datacenters.
Energy-efficient Cloud environments need to deal not only with energy consumption but also
with increasing demand, high QoS expectations and sustainable services [2]. However, a large
INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING &
TECHNOLOGY (IJCET)
ISSN 0976 – 6367(Print)
ISSN 0976 – 6375(Online)
Volume 6, Issue 5, May (2015), pp. 24-35
© IAEME: www.iaeme.com/IJCET.asp
Journal Impact Factor (2015): 8.9958 (Calculated by GISI)
www.jifactor.com
IJCET
© I A E M E

25
number of cloud servers consume massive energy and produce huge pollution. The Smart2020
analysis shows that cloud-based computing data center and the telecommunication network will
generate emission about 7% and 5% each year in 2002 and 2020, respectively.[3]
Power consumption is one of the most critical problems in data centers. One effective way to
reduce power consumption is to consolidate the hosting workloads and shut down physical machines
which become idle after consolidation.[4]
The solution to this issue is to migrate and consolidate VMs in data center. Although it can
greatly reduce energy consumption, it will result in SLA violation. Obviously, we cannot eliminate
the SLA violation by this way, but we can reduce SLA violation as much as possible while reducing
energy consumption, which is called energy-consumption trade off and also the focus of this article.
VM consolidation can be loosely classified into dynamic, semi-static and static. Dynamic
consolidation requires a runtime placement manager to migrate VM automatically according to
workload variations or sudden burst. On the other hand, in static consolidation, once a VM is placed
on a physical server, it will not get migrated for a long time period, such as months or years. Finally,
semi-static consolidation migrates VMs in a hourly or daily basis according to the statistics of
historical workload measurements.[5]
The main focus of this work is to introduce an efficient SLA-aware algorithm (i.e., to avoid
SLA violation as much as possible). The proposed algorithms consider the trade-off between energy
consumption and performance. The most important contributions of this paper are as follows:
– Proposing an efficient algorithm which finds and decides overloaded host with SLA violation
– Proposing an efficient algorithm for finding underutilized hosts.
– Combine two proposed algorithms as virtual machine consolidation algorithm to get better results
in both power consumption and SLA violation.
The overload detection finds overload host and get the status of Overload host whether it
result in SLA Violation or not. If there is no SLA violation then no migration of virtual machines
reqiured which saves power required to migrate VMs. But if there is SLA violation then place all the
VMs from this host to other hosts until the host becomes Underload.
The underload detection algorithm finds the host with the minimum utilization compared to
the other hosts, and tries to place all the VMs from this host to other hosts keeping them not
overloaded. If this can be done, the VMs are set for migration to the determined destination hosts,
and the source host is switched to the sleep mode once all the migrations have been completed. If all
the VMs from the source host cannot be allocated, the host is kept active. This algorithm is repeated
for all hosts that have not been considered as being overloaded.
The paper is organized as follows. In Sect. II the related work is discussed. In Sect. III
consolidation algorithm is introduced. In Sects. IV mehodology and metrics are discussed. In Sect
V the experimental setup and their results are discussed and in Sect. VI the system model is
introduced that has been used in our work. Finally Sect. VII concludes the paper.
2. RELATED WORK
The first work in large-scale virtualized data centers to manage power efficiently, in which
power management has been applied in the context of virtualized data centers, has been done by
Nathuji and Schwan [6]. The authors have proposed an architecture of a data center’s resource
management system where the resource management is split into local and global managers. At the
local level the system leverages the guest OS’s power management strategies. The global manager
gets the information on the current resource allocation from the local managers and applies its policy
to decide whether the VM placement needs to be adapted. Local manager coordinates power
management methods of VMs in each host because the authors assumed that VM guests have a

26
power aware OS. Global manager monitors the performance of multiple hosts and selects the
appropriate host for requested VM migration.
The authors [7] have proposed a method for energy efficient resource allocation, in the
context of a networked cloud environment. The method employs dynamic server consolidation by
periodic VM migration.
H. Goudarzi et al.[8] presented an approach that first creates multiple copies of VMs and then
uses dynamic programming and local search to place these copies on the physical servers.
In this the authors [9] present two novel approaches for virtual machines (VMs) placement
consolidation. which aim to maximize the placed VMs on a host and minimize the number of hosts
used on a cloud computing environment. The first proposed approach is based on the Knapsack
problem and the second one is based on an Evolutionary Computation heuristic.
The work in[10] aims to proactively prevent VM migration for semi-static VM consolidation
by proposing a deadline driven VM placement strategy based on the awareness of the server turn-off
time and job execution time using a real HPC cluster trace as well as a set of synthetic generated
workloads.
Beloglazov et al. [11] use “live-migration” and VM consolidation, but only focus on the QoS
of such an approach even in heterogeneous infrastructure containing heterogeneous VMs. An attempt
is made to solve both the traditional bin packing problem as well as the “intermediate state” data
center optimization problem and four heuristics are proposed for choosing which VM to migrate.
Anton et al. [12] have defined an architectural framework and principles for energy-aware Cloud
computing and has developed algorithms for energy-aware mapping of VMs, they have used the
concept of dynamic consolidation of VM resource partitions.
The fixed threshold in [12] for vm consolidation is not suitable for virtual environment with
variable workloads. Therefore, they [13] illustrate that VM consolidation for variability of
workloads. Then they propose novel adaptive heuristics for dynamic consolidation of VMs. Results
show that the allocation and selection algorithms save energy consumption. However, the SLA
violation and energy consumption produced by the framework has a scope of improvement.
The framework selects VMs from an Overload host until the host becomes Underload. If the
Overload host does not generate SLA violation, then the migration will be in vain and result in high
energy consumption. Therefore, we require a appropriate method to decide the VM selection in this
step. By considering above problem, we propose another VM consolidation algorithm in CloudSim,
[14] which performs better .
3. ENERGY EFFICIENT CONSOLIDATION ALGORITHM
Following flowchart shows the flow of proposed virtual machine consolidation algorithm
which is a combination of two proposed algorithm mentioned above with existing algorithm in [13]
for finding new VMs placements.

27
Figure1: Flowchart of virtual machine consolidation algorithm.
The proposed virtual machine consolidation is shown in Algorithm 1 has following
Step I: First, the algorithm ee the list of hosts and by applying the proposed overload detection
algorithm checks
Whether a host is overloaded. If the host is overloaded, the algorithm applies the VM
selection policy to select VMs that need to be migrated from the host. If the Overload host does not
generate SLA violation, then the migration will result in higher energy consumption. Therefore, we
need a method to decide the status of Overload host whether it result in SLA Violation or not.

28
Step II: Once the list of VMs to be migrated from the overloaded hosts is built, the VM placement
algorithm in [13] is invoked to find a new placement for the VMs to be migrated.
Step III: Finding underloaded hosts and a placement of the VMs from these hosts.
The consolidation algorithm returns the combined migration map that contains the
information on the new VM placement of the VM selected to be migrated from both overloaded and
underloaded hosts. The complexity of the algorithm is 2N, where N is the number of hosts.
3.1 Overloaded host detection with status of SLA Violation
For step 4 in algorithm 1 above we have proposed an algorithm that finds and decides the
status of overloaded host with SLA Violation as given in algorithm 2. Here we have used the
parameters OverSLAV for the overloaded host with SLA violation, OverNSLAV for the overloaded
with no SLA violation, Over for overloaded host, Under for underloaded host, Idle for the Idle host,
Saturated for the host which does not send or receive any migration. According to [13], when the
total request utilization of the VMs exceeds the allocated utilization of them on host Hi , Hi will
generate SLA violation. If they are equal, it will be assumed to generate no SLA violation. The total
allocated utilization of the VMs on host Hi can never exceed the maximum utilization of the host. It
means that if the request utilization of the VMs on Hi exceeds the maximum utilization, the host will
definitely generate SLA violation.
Once it has been decided that a host is overloaded and got its status, the next step is to select
particular VMs to migrate from this host. Here we have used four policies for VM selection .The
policies are applied iteratively. After a selection of a VM to migrate, the host is checked again for
being overloaded. If it is still considered as being overloaded, the VM selection policy is applied
again to select another VM to migrate from the host. This is repeated until the host is considered as
being not overloaded. The complexity of the algorithm is nm2
, where n is the number of host and m
is the number of VMs that is to be migrated.

29
Here select VMs from the OverSLAV hosts until they become OverNSLAV or Saturated,
and put the VMs into the VmsToMigrate. Finally, select VMs from the OverNS hosts using the
proposed SLA violation decision algorithm until they become Saturated, and put the VMs into the
VmsToMigrate.
3.2 VM placement
Here for step 6and 11in algorithm 1 we have used an existing PABFD algorithm in[13] for
finding new virtual machine placement
3.3 Underloaded host detection
For step 9 in algorithm 1 above we have proposed an algorithm that find underloaded host
which is given in algorithm 3 below. First find the CPU utilization of each host then sort in decreasing
order so as to find the minimum utilization host as underloaded host to migrate all VMs from this host
to other host by applying VM placement algorithm in[13] without overloading the other host. The
complexity of the algorithm is nm, where n is the number of host and m is the number of VMs that is
to be migrated.

30
The advantage of proposed algorithm is that it reduces no of migrations and hence reduces
SLA violation and energy consumption, second a host with least number of VMs has a better chance
to be switched to sleep mode in comparison with a host with more VMs.
4 METHODOLOGY AND METRICS
Energy efficiency metrics focus on advancing energy efficiency in data centers and
computing ecosystems.
4.1 The overload decision algorithm
For ease, the algorithm can be abbreviated to ODA, which intent to decide a host Overloaded
or not. Five ODAs have been implemented in CloudSim, i.e. Interquartile Range (IQR), Static
Theshold (THR), Local Regression (LR), Robust Local Regression (LRR) and Median Absolute
Deviation (MAD).
4.2 The VM selection algorithm
For ease, the algorithm can be abbreviated to VMSA, which aims to select VMs from Over
hosts and prevent them from being over. Four VMSAs have been implemented in CloudSim, i.e.
Minimum Migration Time (MMT), Minimum Utilization (MU), Random Selection (RS) and
Maximum Correlation (MC).
4.3 SLA Violation Metrics
Meeting QoS requirements is very important for Cloud computing. QoS requirements are
commonly formalized as SLAs, which can be determined in terms of characteristics such as
minimum throughput, maximum response time or minimum bandwidth and so on. These
characteristics are workload or application dependent. However,the algorithm framework belongs to
IaaS layer in Cloud computing and should be workload independent. Therefore, we use those SLA-
related metrics defined in [13] to evaluate the proposed algorithm in our experiments.
Simultaneously, we also use some other metrics including energy consumption, migrations and
execution time.
(a) SLATAH (SLA violation Time per Active Host): The percentage of time, during which active
hosts have experienced the CPU utilization of 100 %. When a host experiences 100 % utilization, it
will not be able to allocate enough CPU to the VMs on it, so it will generate SLA violation. The
SLATAH can be calculated using Eq. (1), where Tsi is the SLA violation time and Tai is the active
time for Hi.

31
(1)
(b) SLAV (SLA Violation) and ESV (Energy and SLA Violation): The SLATAH is used to evaluate
host-level SLA violation due to host overloading. And the PDM is used to evaluate VM-level SLA
violation due to the VM migration. Since the two metrics are independent, a combined metric is
needed to evaluate the two SLA violations. As a result, the SLAV is proposed to evaluate the two
SLA violations, which can be calculated using Eq. (2). Since the Energy and the SLAV are two main
metrics, the ESV is proposed to combine the two metrics, which can be calculated using Eq. (3).
SLAV = SLATAH ・ PDM (2)
ESV = SLAV ・ Energy (3)
5 PERFORMANCE EVALUATION
As the targeted system is an IaaS in cloud computing, it’s better to evaluate the proposed
algorithm on a large-scale virtualized data center infrastructure. However, it’s very difficult to
conduct repeatable large-scale experiments on a real infrastructure, which is required to evaluate and
compare the proposed algorithm. Therefore, to ensure the repeatability of the experiments,
simulations have been chosen as a suitable way to evaluate the performance of the proposed
algorithm.
For our experiments, the CloudSim toolkit [14] has been chosen as a simulation framework.
The toolkit has been developed by the Cloud Computing and Distributed Systems (CLOUDS)
Laboratory, University of Melbourne. It supports both system and behavior modeling of cloud
system components such as data centers, virtual machines (VMs) and resource provisioning policies.
Currently, it supports modeling and simulation of Cloud computing environments consisting of both
single and inter-networked clouds (federation of clouds), and also supports energy-efficient
management of datacenter resources. Apart from the energy consumption modeling and accounting,
the ability to simulate service applications with dynamic workloads has been incorporated.
5.1 Experimental Setup
We have simulated a data center that comprises 800 heterogeneous physical nodes, half of
which are HP ProLiant ML110 G4 servers, and the other half consists of HP ProLiant ML110 G5
servers.
The characteristics of the servers and data on their power consumption are given in 6.1 next.
The frequency of the servers’ CPUs are mapped onto MIPS ratings: 1860 MIPS each core of theHP
ProLiant ML110 G5 server, and 2660 MIPS each core of the HP ProLiant ML110 G5 server. Each
server is modeled to have 1 GB/s network bandwidth. The characteristics of the VM types
correspond to Amazon EC2 instance types with the only exception that all the VMs are single-core,
which is explained by the fact that the workload data used for the simulations come from single-core
VMs (Section 6.1). For the same reason the amount of RAM is divided by the number of cores for
each VM type: High-CPU Medium Instance (2500 MIPS, 0.85 GB); Extra Large Instance
(2000MIPS, 3.75 GB); Small Instance (1000 MIPS, 1.7 GB); and Micro Instance (500 MIPS, 613
MB).
Initially the VMs are allocated according to the resource requirements defined by the VM
types. However, during the lifetime, VMs utilize less resources according to the workload data,
creating opportunities for dynamic consolidation.

32
5.2 Workload Data
In order to make the results more convincing, we need to use workload data obtained from
real system. For our experiments, we have used data provided as a part of part of CoMon project, a
monitoring infrastructure for PlanetLab [15], and it is about CPU utilization by more than a thousand
VMs from servers located at more than 500places around the world. The interval of utilization
measurements for the data is 5 minutes. There are 10-day CPU utilization records during March and
April 2011 in the data. Table II from the literature [13], gives brief analysis about the workload.
5.3 Result Analysis
In the experiment, we use four-type ODAs (THR, LR, LRR and MAD) and four-type
VMSAs (MC, MU, MMT, RS). Therefore, there are 16-type combinations policies for the ODA and
the VMSA. According to the simulation results from reference [13], we set a suitable constant
parameter for each ODA, and they are 0.8 for THR, 1.2 for LR, 1.2 for LRR and 2.5 for MAD
respectively. The combination are THR_MC_0.8,THR_MU_0.8,THR_MMT_0.8, THR_RS_0.8,
LR_MC_1.2, LR_MU_1.2, LR_MMT_1.2, LR_RS_1.2, LRR_MC_1.2, LRR_MU_1.2,
LRR_MMT_1.2,LRR_RS_1.2,MAD_MC_2.5,MAD_MU_2.5,MAD_MMT_2.5, MAD_RS_2.5.
In fig 2, we use the 10-day workload to evaluate the proposed algorithm for the 16-type
combination policies. In each subfigure of the figure, each candlestick represents results from the 10-
day workload. For better comparison, we use the average of the results as an evaluation value.
1) The SLATAH evaluation
The minimum and the maximum evaluation values for the Origin are 5.5% and 7.87%
respectively in fig 2.1(a). For the proposed algorithm, the values are 3.29% and 5.57% respectively
as in fig 2.1(b).Compared with the Origin, the proposed algorithm has 40.18%~58.19% decrease for
the 16-type combinations for the SLATAH respectively.
Figure 2.1 The SLATAH evaluation
2) The Energy evaluation: In fig 2.2(a), for the Origin, the minimum and maximum evaluation
values are 141.933 kWh and 171.444 kWh respectively. In fig 2.2(b) for the proposed algorithm, the
values are 125.03 kWh and 128.29 kWh respectively. Compared with the Origin, the proposed
algorithm has 11.9%~27.07%decrease for energy consumption for the 16-type combinations
respectively.

33
Figure 2.2 The Energy evaluation
3) The SLAV evaluation: In fig 2.3(a), for the Origin, the minimum and maximum evaluation
values are 0.707% and 1.379%respectively. In fig 2.3(b) for the proposed algorithm, the values are
0.137% and 0.598% respectively. Compared with the Origin, the proposed algorithm has
80.62%~90% decrease for the 16-type combinations for the SLAV respectively.
Figure 2.3 The SLAV evaluation
4) The ESV evaluation: In fig 2.4(a), for the Origin, the minimum and maximum evaluation values
are 10.06% and 23.25% respectively .In fig2.4 (b) for the proposed algorithm, the values are 2.87%
and 6.98% respectively. Compared with the Origin, the proposed algorithm has 72.92%~87.65%
decrease for the 16-type combinations for the ESV respectively.
Figure 2.4 The ESV evaluation
In a nutshell, the proposed consolidation algorithm outperform the origin for the all above metrics.

34
6 SYSTEM MODEL
6.1 CPU architecture and power model
In this paper, it is assumed that each CPU has c cores and each core has m MIPS, so total
MIPS of a CPU is c × m.
The servers used in this paper are: HP ProLiant ML110 G4, HP ProLiant ML110 G5. Tables
I and II show the configuration and power consumption, respectively.
Table I configuration of servers
The reason why we have not chosen servers with more cores is that it is important to simulate
a large number of servers to evaluate the effect of VM consolidation. Thus, simulating less powerful
CPUs is advantageous, as less workload is required to overload a server. Nevertheless, dual-core
CPUs are sufficient to evaluate resource management algorithms designed for multi-core CPU
architectures.
Table II Power consumption of server at different load levels in watts
7 CONCLUSION
To obtain quick ROI (Return On Investment), Cloud providers should reduce energy
consumption as much as possible while keeping a low-level SLA violation in data center, which is
also called energy-performance tradeoff. Using energy-efficient resource management policies will
lead to increase in their revenues. This can be done by consolidating VMs and switching idle servers
to sleep modes. However, improper consolidation may lead to SLAV.
In this paper, we have proposed an energy-efficient algorithm for VM consolidation which can
reduce energy consumption and at the same time the SLAV. The simulations show that the proposed
algorithms significantly reduce number of VM migration, SLAV in comparison with current
algorithms [13].
We have evaluated proposed algorithm and the Origin framework through simulation on
large-scale experiments driven by workload traces collected from more than a thousand PlanetLab
VMs, and the results show that our proposed algorithm gets a better energy-performance. It
guarantees 11.9–27.07 % decrease in energy consumption, 80.62–90 % decrease in SLA violation.

35
8 REFERENCES
[1] A. Carpen-Amarie, A.-C. Orgerie, and C. Morin, “Experimental Study on the Energy
Consumption in IaaS Cloud Environments,” 2013 IEEE/ACM 6th International Conference
on Utility Clou Computing, pp. 42–49, Dec. 2013.
[2] I. S. Moreno and J. Xu, “Customer-Aware Resource Overallocation to Improve Energy
Efficiency in Real- Time Cloud Computing Data Centers.”
[3] Z. Wang and Y.-Q. Zhang, “Energy-Efficient Task Scheduling Algorithms with Human
Intelligence Based Task Shuffling and Task Relocation,” 2011 IEEE/ACM Int. Conf. Green
Comput. Commun., pp. 38–43, Aug. 2011.
[4] C.-C. Lin, P. Liu, and J.-J. Wu, “Energy-efficient Virtua Machine Provision Algorithms for
Cloud Systems,” 2011 Fourth IEEE Int. Conf. Util. Cloud Comput, pp. 81–88, Dec. 2011.
[5] M.-H. Tsai, J. Chou, and J. Chen, “Prevent VM Migration in Virtualized Clusters via
Deadline Driven Placement Policy,” 2013 IEEE 5th Int. Conf. Cloud Comput. Technol. Sci.,
pp. 599–606, Dec. 2013.
[6] Nathuji R, Schwan K. Virtual power: Coordinated power management in virtualized
enterprise systems. ACMSIGOPS Operating Systems Review 2007; 41(6):265–278.
[7] A. Leivadeas, C. Papagianni, and S. Papavassiliou, “Energy Aware Networked Cloud
Mapping,” 2013 IEEE 12th Int. Symp. Netw. Comput. Appl., pp. 195–202, Aug. 2013.
[8] H. Goudarzi and M. Pedram, “Energy-Efficient Virtual Machine Replication and Placement
in a Cloud Computing System,” 2012 IEEE Fifth Int. Conf. Cloud Comput, pp. 750–757, Jun.
2012.
[9] A. P. M. D. L. F. Vigliotti and D. M. Batista, “Energy-Efficient Virtual Machines
Placement,” 2014 Brazilian Symp. Comput. Networks Distrib. Syst., pp. 1–8, May 2014.
[10] M.-H. Tsai, J. Chou, and J. Chen, “Prevent VM Migration in Virtualized Clusters via
Deadline Driven Placement Policy,” 2013 IEEE 5th Int. Conf. Cloud Comput. Technol. Sci.,
pp. 599–606, Dec. 2013.
[11] A. Beloglazov and R. Buyya, “Energy efficient allocation of virtual machines in cloud data
centers,” in 10th IEEE/ACM Int. Symp. on Cluster Computing and the Grid, CCGrid 2010,
Melbourne, Australia,May 2010, pp. 577–578.
[12] A. Beloglazov, J. Abawajy, R. Buyya, Energy-Aware Resource Allocation Heuristics for
Efficient Management of Data Centers for Cloud Computing, Future Generation Computer
Systems (FGCS),Elsevier Science, Amsterdam, May 2012, 28(5): 755-768.
[13] Beloglazov A, Buyya R (2011) Optimal online deterministic algorithms and adaptive
heuristics for energy and performance efficient dynamic consolidation of virtual machines in
cloud data centers.Concurr Comput Pract Exp 24(13):1397–1420.
[14] R. N. Calheiros, R. Ranjan, A. Beloglazov, C. A. F. D. Rose, R. Buyya, CloudSim: a toolkit
for modeling and simulation of cloud computing environments and evaluation of resource
provisioning algorithms, Software: Practice and Experience,2011, 41 (1):23-50.
[15] K.S. Park, V.S. Pai, CoMon: a mostly-scalable monitoring system for PlanetLab.ACM
SIGOPS Operating SystemsReview2006, 40(1):74.
[16] Kuldeep Mishra, Ravi Rai Chaudhary and Dheresh Soni, “A Premeditated CDM Algorithm
In Cloud Computing Environment For FPM” International journal of Computer Engineering
& Technology (IJCET), Volume 4, Issue 4, 2013, pp. 213 - 223, ISSN Print: 0976 – 6367,
ISSN Online: 0976 – 6375.
[17] Supriya Mandhare, Dr.A.K.Sen and Rajkumar Shende, “A Proposal on Protecting Data
Leakages In Cloud Computing” International journal of Computer Engineering &
Technology (IJCET), Volume 6, Issue 2, 2015, pp. 213 - 223, ISSN Print: 0976 – 6367, ISSN
Online: 0976 – 6375.

Performance analysis of an energy efficient virtual machine consolidation algorithm in cloud computing

Recommended

More Related Content

What's hot (20)

Viewers also liked (15)

Similar to Performance analysis of an energy efficient virtual machine consolidation algorithm in cloud computing (20)

More from IAEME Publication (20)

Recently uploaded (20)

Performance analysis of an energy efficient virtual machine consolidation algorithm in cloud computing