VM Consolidation for energy

efficient cloud computing

I.G.HEMANANDHINI
M.E.(CSE) Final year
Sri Ramakrishna Engineering College

What is cloud computing???

Internet based
on-demand computing
pay as you use model
accessing the computing
resources of third parties

Virtualization !!!

Cloud
computing
is
possible
because
of
virtualization
Virtualization is a technique of abstracting physical
resources and making them appear as logical
resources and it may be implemented at compute,
storage, and network
For a layman, virtualization can be mentioned as
making the hardware resources appear as software
resources
The hardware architecture of a system can be
either X34 or X32 or X86. These architectures can
run or host only one application so we go for
virtualization which can host many applications

Data centers are becoming

warmer!!

Modern data centers in the cloud computing

environment host a variety of applications that run
from few seconds to longer periods
By 2014, energy costs contribute 75% by the data
centers because of insufficient hardware usage
and inefficient resource usage
Consequently, energy costs for operating and
cooling the equipment of data centers have
increased significantly up to a point where they are
able to surpass the hardware acquisition costs


For each watt consumed by the computing
resources an additional 0.5-1 watt is required by
the cooling systems and CO2 emission also
contribute to significant Greenhouse effect

Energy !! Energy !!

According to McKinsey report on Revolutionizing

Data Center Energy Efficiency:
A typical data center uses as much energy as
25,000 households uses. The total energy bill for
data centers in 2010 was over $11 billion and
energy costs in a typical data center doubles every
five years
About 50% of power in the data center is
consumed by the servers/storage and computer AC
room consumes about 34% of power

Solution -

The solution is green computing !!!!

Techniques to Improve
Energy Efficiency of Data
Centers

IT Infrastructure Improvements
Servers and Storages
Network Equipment

Power Distribution
Smart Cooling and Thermal Management
Power Management Techniques
Provisioning
Consolidation
Virtualization

others

VM Consolidation

VM Consolidation is a technique to reduce the

number of active PMs by migrating and
consolidating the VMs into reduced number of
physical machines
Consolidation includes
two strategies
VM Placement
VM Migration

 VM Placement

VM Placement is the process of selecting the

appropriate host for the given VM
For the efficient utilization of the physical
resources, VM should be placed on to the suitable
host
The VM placement can be either saving energy by
shutting down some severs or it can be
maximizing the resources utilization and the next
is VM Migration

Types of VM Placement

Power based approach

Application QOS based approach
Power based approach is for energy conservation
by shutting down some servers
Application based approach is for maximizing the
resource utilization and also maximizing QOS
delivery by provider

 VM Migration

VM Migration is carried out after the initial VM

placement in order to reduce the number of running
physical machines by migration of few VMs and
consolidate them into reduced number of PMs
Four steps are involved in the VM machine migration
process
1.
2.
3.
4.

select the PM which is overload or under loaded

select one or more VMs from overloaded or under loaded
server
select the appropriate destination PM where selected
VMs can be placed and
transfer/ migrate the VMs to destination PM


Selecting the suitable host is one of the
challenging task in the migration process, because
wrong selection of host can increased the number
of migration, resource wastage and energy
consumption

Types of consolidation

VM Consolidation is of two types:

Static and
Dynamic consolidation

In static consolidation a new VM is placed to

PMs for processing and no migration takes
place here
In dynamic consolidation the VMs are
migrated from one PM to another whenever a
necessity occurs

Advantages of consolidation

Reduce the amount of hardware,

Reduce the data center footprints,
Indirectly reduce power consumption,
Cost reduction and
Reduce staffing needs

Challenge in consolidation :How accurately to

characterise an applications resource requirements
and resource usage over a time period

References

Cloud Computing Infrastructure and Services Copyright 2011 EMC

Corporation
B. Benita Jacinth Suseela, A Survey on VM Placement on Cloud
International Journal of Engineering Trends and Technology (IJETT)
Volume 6 Number 7- Dec 2013-A
Huaglory Tianfield PhD, Professor of Distributed Systems Glasgow
Caledonian University, United Kingdom E-mail: h.tianfield@gcu.ac.ukA
vision on VM consolidation for green cloud computing
Anton Beloglazov and Rajkumar Buyya, Optimal Online Deterministic
Algorithms and Adaptive Heuristics for Energy and Performance
Efficient Dynamic Consolidation of Virtual Machines in Cloud Data
Centers, CONCURRENCY AND COMPUTATION: PRACTICE AND
EXPERIENCE Concurrency Computat.: Pract. Exper. 2012; 24:13971420
Published online in Wiley InterScience (www.interscience.wiley.com)
DOI: 10.1002/cpe.1867


Thank you for your
attention !!!