www.ijecs.

in
International Journal Of Engineering And Computer Science ISSN:2319-7242
Volume 2 Issue 3 March 2013 Page No. 831-835


M.Karthi, IJECS Volume 2 Issue 3 March 2013 Page No. 831-835 Page 831

Survey on Resources Provisioning in Cloud Systems for Cost Benefits
M.Karthi
1
S.Nachiyappan
2

1
PGStudent, Computer Science and Engineering, Velammal College of Engineering and Technology Madurai, Tamil Nadu, India
Email:[email protected]
2
Assistant professor, Computer Science & Engineering, Velammal College of Engineering and Technology Madurai, Tamil Nadu
Email:[email protected]
Abstract In Cloud computing, the information is permanently stored in servers in the internet. From there,
the Cloud consumers utilize resources using Virtual Servers and they are charged based on pay-per-use basis.
For this, Cloud provider offer two type of provisioning plans, namely On-demand and Reservation plan. They
are also called as Short-term and Long-term planning. In general, the reservation plan has minimum cost than
on-demand plan. Although the reservation offers the discounted usage price, this option could result in over
provisioning and under provisioning problems due to demand uncertainty. There are many kinds of resource
provisioning options available in cloud environment to reduce the total paying cost and better utilizing cloud
resources. However, the best advance reservation of resources is difficult to be achieved due to uncertainty of
consumers future demand and providers resource prices. In this paper survey the different provisioning
options and algorithm. Compare the existing provisioning algorithms with analysis based on cost, availability,
uncertainty parameters.

Keywords: Cloud computing, Future Demand,
Integer programming, Resource Management,
Resource provisioning.

1. INTRODUCTION
Cloud computing is the utilization of computing
software and hardware resources. Those Resources
are delivered to cloud consumer as a service over a
network typically the Internet. There are three major
categories of cloud services is Infrastructure as a
service (IaaS),Platform as a service (PaaS) and
Software as a service (SaaS).The most basic cloud-
service model, providers of IaaS offer computers -
physical or virtual machines and some other
resources (images in a virtual-machine image-library,
file-based storage, raw (block) and firewalls, IP
addresses, load balancers, virtual local area networks
, and some of the software bundles). In the PaaS
model, cloud providers deliver a computing platform
typically including programming language execution
environment, database, operating system, and web
server. In the SaaS model cloud providers operate
application software in the cloud and cloud users
access the software from cloud clients. The cloud
users normally do not manage the cloud
infrastructure and platform on which the application
is running. To eliminate need to install and run the
application on the cloud user's own computers
simplifying maintenance and support.

In cloud computing a resource provisioning
mechanism is required to supply cloud consumers a
set of computing resources for processing the jobs
and storing the data and etc. Cloud providers can
offers to cloud consumers two resource provisioning
plans. That namely short-term on-demand and long-
term reservation plans. Amazon EC2 and Go Grid
are cloud providers which offer IaaS services with
both plans. In generally pricing in on-demand plan is
charged by pay-per-use basis (e.g., per 1 day, per 1
hour). Therefore purchasing this on-Demand plan,
the consumers can dynamically provisioning
resources at the moment when the resources are
needed to fit the fluctuated and unpredictable and
unexpected demands. For reservation plan, pricing is
charged by a onetime fee (e.g., 1 year, 3year)
typically before the computing resource will be

M.Karthi, IJECS Volume 2 Issue 3 March 2013 Page No. 831-835 Page 832

utilized by cloud consumer. In the reservation plan
the price to utilize resources is cheaper than that of
the on-demand plan. So the consumer can reduce the
cost of computing resource provisioning by using the
reservation plan. In the reservation plan offered by
Amazon EC2 can reduce the total provisioning cost
up to 50 percent approximately when the reserved
resource is fully utilized at steady-state usage. With
the reservation plan, the cloud consumers a priory
reserve the resources in advance. As a result the
under provisioning problem can occur when the
reserved resources are unable to fully meet the
demand due to its uncertainty. This problem can be
solved by provisioning more resources with on-
demand plan to fit the additional demand, the high
cost will be incurred due to more expensive price of
resource provisioning with on-demand plan. On the
other hand the over provisioning problem can occur
if the reserved resources are more than the actual
demand in which part of a resource pool will be
underutilized. This is an important for the cloud
consumer to minimize the total cost of resource
provisioning by reducing the on-demand cost and
oversubscribed cost of under provisioning and over
provisioning. To achieve this goal, the optimal
computing resource management is the critical issue.

2. LITERATURE SURVEY
2.1 Resource provisioning options for large-scale
scientific workflows
[1] Shows that, Advance reservations enable users to
allocate resources for their exclusive use for a given
period of time. This technique reduces queuing
delays by eliminating competition for shared
resources To avoid or minimize job delays, several
resource provisioning options are available to
workflow applications Multi-level scheduling is a
provisioning technique that enables user-level
resource managers to control jobs and resources.
This approach reduces queuing delays by reserving
resources, and reduces scheduling delays by allowing
scheduling policies to be managed at the application
level. It does not provide solution for complete
resource provisioning problem and also this
algorithm does not concentrate on security
management technique when resource provides to
the users on the cloud.

2.2 Autonomic provisioning of backend databases
in dynamic content web servers[2] Shows that, in
autonomic provisioning a resource manager will
allocate resources to an application, on-demand, e.g.,
during load spikes. Modeling-based approaches have
proved very successful for provisioning the web and
application server tiers in dynamic content servers.
On the other hand, accurately modeling the behavior
of the back-end database server tier is a daunting task
.novel pro-active scheme based on the classic K-
nearest-neighbors (KNN) machine learning approach
for adding database replicas to application
allocations in dynamic content web server clusters.
KNN algorithm uses lightweight monitoring of
essential system and application metrics in order to
decide how many databases it should allocate to a
given workload. KNN used to improve prediction
accuracy and avoid system oscillations. K-nearest-
neighbors (KNN) machine learning approach only,
so this approaches not suitable for all clients in the
cloud.
2.3 variety of science applications are integrated
with large-scale HPDC
[4] Shows that, HPDC resource management
paradigm named resource slot which defines a
network of logical machines across space and time.
A resource slot is not only a resource programming
target but also a virtualized resource provisioning
framework for a variety of resource management
paradigms by encapsulating the resource
management complexity. A resource provisioning
technique was guided redundant submission (GRS).It
probabilistically guarantees a timely resource slot
allocation. Guided redundant submission which
probabilistically secures the temporal resource
availability, based on a joint failure probability of
individual resources. This paper has not handle
techniques for reduce the cost of resource. This paper
follows the technique guided redundant
Submission (GRS) therefore we cannot give
complete surety for resource provides to the user in
grid.

2.4 risk-aware limited look ahead controls for
dynamic resource provisioning
[4] Shows that, in the resource provisioning problem
is posed as one of sequential decision making under
uncertainty and solved using a limited look a head

M.Karthi, IJECS Volume 2 Issue 3 March 2013 Page No. 831-835 Page 833

control scheme. The proposed approach used for the
switching costs incurred during resource
provisioning and explicitly encode risk in the
optimization problem. The LLC concept is adopted
from model predictive control, sometimes used to
solve optimal control problems for which classical
feedback solutions are extremely hard or impossible
to obtain. The LLC approach is a practical option for
enforcing self-managing behavior in resource
provisioning applications. This paper follows
dynamic approach for resource provisioning
therefore small users may wait long time for get
resource. No functionality for reduce the operating
cost and operating time.

2.5 Sla-aware virtual resource management for
cloud infrastructures
[5] Shows that, Ability to automate the dynamic
provisioning and placement of VMs taking into
account both application-level SLAs and resource
exploitation costs with high-level handles for the
administrator to specify trade-offs between the two.
Support for heterogeneous applications and
workloads including both enterprise online
applications with stringent QoS requirements and
batch-oriented CPU intensive applications. To
Support for arbitrary application topology: single
cluster, n-tier, monolithic and capacity to scale:
either in a scale-up fashion by adding more
resource to a single server or in a scale-out fashion
by adding more servers. It is not focused on
optimization problems that are NP-hard in their
general form.

2.6 A hybrid particle swarm optimization
algorithm for optimal task assignment in
distributed systems
[6] Shows that, in a computation system with a
number of distributed processors, it is desired to
assign application tasks to these processors such that
the resource demand of each task is satisfied and the
system throughput is increased. In a distributed
system, a number of application tasks may need to be
assigned to different processors such that the system
cost is minimized and the constraints with limited
resource are satisfied. The assignment of tasks will
also incur some costs such as the execution cost and
the communication cost. The task assignment
problem (TAP) is to find an assignment of tasks
which minimizes the incurred costs subject to the
resource constraint. Most of the existing
formulations for this problem have found to NP-
complete and thus finding the exact solutions is
computationally intractable for major large-scaled
problems. The Hybrid particle swarm optimization
algorithm used for finding the nearest optimal task
assignment with reasonable less time. The
experimental results manifest that the proposed
method is more effective and efficient than a genetic
algorithm. Our method converges at a fast rate and is
suited to large-scaled task assignment problem.

2.7 Optimal Virtual Machine Placement across
Multiple Cloud Providers
[7] Shows that, the under provisioning problem can
occur when the reserved resources are unable to fully
meet the demand due to its uncertainty. The over
provisioning problem can occur if the reserved
resources are more than the actual demand in which
part of a resource pool will be underutilized . To
solve this problem Optimal Virtual Machine
Placement (OVMP) algorithm is optimally allocating
VMs to multiple cloud providers and follows
optimally advance reservation. In OVMP consider
uncertainty of demand and price. This algorithm
achieved by stochastic integer programming with
two stage resources. Multiple VM class used each
VM class have a distinct type of resources. Each
virtual machine in VM class has different resource
requirement. The number of VMs in each VM class
depends on the demand from user. In first stage
reserve the cheaper resources by using advance
resource provisioning. In second stage consist of two
phase utilization phase and on demand phase. Pay
cost more to additional resources in on demand
phase. Formulating the integer programming and
solve it get optimal solution.

2.8 Optimization of Resource Provisioning Cost in
Cloud Computing
[8] Shows that, the advance reservation of resources
is difficult to be achieved optimized cost due to
uncertainty of consumers future demand and
providers resource prices. The under provisioning
problem can occur when the reserved Resources are
unable to fully meet the demand due to its

M.Karthi, IJECS Volume 2 Issue 3 March 2013 Page No. 831-835 Page 834

uncertainty. The over provisioning problem can
occur if the reserved resources are more than the
actual demand in which part of a resource pool will
be under utilized. To address this problem we use an
optimal cloud resource provisioning (OCRP)
algorithm is proposed by formulating a stochastic
programming model. The OCRP algorithms can
provisioning compute resources for being used in
multiple provisioning stages as well as in long-term
plan, e.g., three stages in a quarter plan and twelve
stages in a yearly plan. Different approaches used to
obtain the solution of the OCRP algorithm are
considered including sample-average approximation,
deterministic equivalent formulation and Benders
decomposition. Numerical studies are performed in
which the results clearly show that with the OCRP
algorithm, cloud consumer can able to successfully
minimize total cost of resource provisioning in cloud
computing environment.

3. COMPARISON OF PROVISIONING
ALGORITHM
The comparison between provisioning algorithms is
performed as follow. The algorithms include the
OCRP, expected-value of uncertainty provisioning
(EVU), no reservation provisioning (No Res) and
maximum advance reservation provisioning (Max
Res) algorithms. EVU uses the average values of
uncertainty parameters in cost and solves them by a
traditional deterministic program. In Max Res
reserves the maximum number of available VMs to
user he cloud resources. Both Max Res and No Res
also apply the traditional deterministic program for
allocating VMs to cloud providers. While No Res
does not reserve any resources to user for utilizing
the probabilistic distributions are applied to the
possible scenarios of price and demand respectively.
The solution obtained from each solved algorithm
yields the number of reserved VMs and the
allocation of VMs to providers. The provisioning
costs incurred by purchasing the provisioning plans
given by the solution of each algorithm are recorded.
Take sample input the costs include reservation cost
(R.C.), expending cost (E.C.), on-demand cost
(O.C.), oversubscribed cost (OS.C.), and total cost.
The OCRP achieves the lowest optimal total cost,
while No Res yields the highest total cost due to the
highest on-demand resource cost. The OCRP
algorithm reserves 60 VMs (including both classes I1
and I2). Although Max Res reserves 100 VMs (50
per VM class) to entirely have higher cost in the on-
demand plan, and incurs much higher cost than that
of OCRP. Additionally Max Res incurs the highest
over provisioning cost since the reserved resources
are unnecessarily over provisioned. EVU incurs the
total cost lower than those of Max Res due to take
average number of VMs and No Res algorithms.
Although the over provisioning cost of OCRP is
higher than that of EVU but the on-demand cost of
the OCRP algorithm is much lower than other
algorithms. Again, it is possible that the on demand
cost can increase due to the price uncertainty. As a
result the use of the on-demand cost is more
important. The result of this comparison shows the
balance between the number of provisioning
resources to be acquired in the first and next stages in
which OCRP can provide the most optimal cost.


4. FUTURE WORK
To address this problem we suggest Probabilistic
based cloud resource provisioning (PCRP) algorithm,
is proposed a probabilistic resource provisioning
approach
That can be exploited as the input of a dynamic
resource management scheme. Using this model we
can eliminate under provisioning and over
provisioning problems.

5. REFERENCES
1. G. juve and e. deelman, resource
provisioning options for large-scale scientific
workflows, proc. ieee fourth intl conf. e-
science, 2008
2. J.chen,g.soundararajan, and
c.amza,autonomic provisioning of backend
databases in dynamic content web servers,
proc. ieee intl conf. autonomic computing,
2006
3. Y.kee and c.kesselman,grid resource
abstraction, virtualization, and provisioning
for Time-target applications, proc. ieee intl
symp. Cluster computing and the grid, 2008.
4. D. kusic and n. kandasamy, risk-aware
limited look ahead control for dynamic
resource provisioning in enterprise

M.Karthi, IJECS Volume 2 Issue 3 March 2013 Page No. 831-835 Page 835

computing systems, proc. ieee intl conf.
autonomic computing, 2006
5. H.n. van, f.d. tran, and j.-m. menaud, sla-
aware virtual resource management for cloud
infrastructures, proc. ieee ninth intl conf.
computer and information technology, 2009.
6. Peng-yeng yin, shiuh-sheng yu, pei-peiwang
a hybrid particle swarm optimization
algorithm for optimal task assignment in
distributed systems journal computer
standards & interfaces archive volume 28
issue 4, april, 2006 pages 441-450
7. S.chaisiri, b.s.lee, and d.niyato, optimal
virtual machine placement across multiple
cloud providers, proc. ieeeasia- pacific
services computing conf. (apscc), 2009.
8. S.chaisiri, b.s.lee, and d. niyato optimization
of resource provisioning cost in cloud
computing,ieeetransactions on services
computing, vol. 5, no. 2, april-june 2012
9. Y. jie, q. jie, and l. ying, a profile-based
approach to just-in- time scalability for cloud
applications, proc. ieee intl conf. cloud
computing (cloud 09), 2009
10. K.miyashita, k.masuda, and f. higashitani,
coordinating service allocation through
flexible reservation, ieee trans. services
computing, vol. 1, no. 2, pp. 117-128, apr.-
june 2008.
11. N. bobroff, a. kochut, and k. beaty, dynamic
placement of virtual machines for managing
sla violations, proc. ifip/ieee intl symp.
Integrated network management (im 07), pp.
119-128, May 2007
12. WenjunWu ; Dichen Di ; Fei
Zhang ; Yizhou Yan ; Yaokuan Mao A
resource scheduling algorithm of cloud
computing based on energy efficient
optimization methods Green Computing
Conference (IGCC), 2012 InternationalJune
2012
13. Pradeep.RKavinya.R Resource Scheduling In
Cloud Using Bee Algorithm for
Heterogeneous Environment IOSR Journal of
Computer Engineering (IOSRJCE) (July-Aug.
2012)
14. Yong Beom Ma, Sung Ho Jang, Jong
SikLeeOntology-Based Resource
Management for Cloud Computing,Intelligent
Information and Database Systems Volume
6592, 2011, pp 343-352
15. PreetiAgrawal and
YogeshRathore,AnApproach for Effective
Resource Management in Cloud
Computing,Int. J. Tech. 2011; Vol. 1: Issue
2, Pg 121-124
16. BahmanJavadi, ParimalaThulasiraman and
RajkumarBuyya, Cloud Resource
Provisioning to Extend the Capacity of Local
Resources in the Presence of Failures, IEEE
14th International Conference on High
Performance Computing and
Communications in 2012
17. Thomas sandholm, kevinlai evaluating
demand prediction techniques for
computational markets proceedings in
gecon2006 may 21, 2007


Karthi.M received the B.Tech degree in
Information Technology from Anna
University Chennai, TamilNadu in 2009, he
is currently working towards the M.E
degree in Computer Science and
Engineering from the Velammal College of
Engineering and Technology/Anna
University Chennai.. His current research
interests include cloud computing,
distributed system.








Nachiappan.S received the B.E degree in
Computer science & engineering from
Madurai Kamaraj University, TamilNadu,
in 2002, and he received the M.E degree in
the Computer Science and Engineering
from the Anna University Chennai in 2004.
His current research interests include cloud
computing and Software Testing.