DYNAMIC LOAD BALANCING TECHNIQUE IN CLOUD

PARTITION COMPUTING

Manjunatha Swamy C
Dept. of Computer Science and Engineering
ATME College of Engineering
Mysore, India
[email protected]


Abstract - A dynamic load balancing system is used for flexibility. Load balancing is depending on the system
dynamics that is static or dynamic which is important in performance. This system can change the status as and when
nodes status updated. A dynamic load balancing is used with cloud division rule which do the partition then the load
balancing is taken place to assign the incoming job for the right partition to do fast processing. Once the partition is
created the load balancing then starts by verifying the status of each and every node by the balancer in the system.
This system has main controller and balancers to gather and analyze the information or status on each node. Thus the
dynamic control have a great inuence on other working nodes. Based on the system status we select the right load
balancing strategy.

Keywords - Cloud Division Rule; Switch mechanism; Main Controller and Balancer; Hash Table

I. INTRODUCTION
Cloud computing is efficient and scalable but maintaining
the stability of processing so many jobs in the cloud
computing environment is a very complex problem with
load balancing receiving much attention for researchers.
Since the job arrival pattern is not predictable and the
capacities of each node in the cloud differ, for load
balancing problem, workload control is crucial to improve
system performance and maintain stability. Load balancing
schemes depending on whether the system dynamics are
important can be either static or dynamic. Static schemes do
not use the system information and are less complex while
dynamic schemes will bring additional costs for the system
but can change as the system status changes. A dynamic
scheme is used here for its flexibility. The model has a main
controller and balancers to gather and analyze the
information. Thus the dynamic control has little influence on
the other working nodes. The system status then provides a
basis for choosing the right dynamic load balancing strategy.
The dynamic load balancing model is aimed at the public
cloud which has numerous nodes with distributed computing
resources in many different geographic locations. Thus this
model divides the public cloud into several cloud partitions
using Cloud Division Rule (CDR).

II. EASE OF USE
When the environment is very large and complex and these
divisions simplify the load balancing. The cloud has a main
controller is key component which controls all the balancers
in a large and complex environment which is divided into
number of partitions. Each partition will have one balancer
each. Main controller chooses the suitable partitions for
arriving jobs while the Balancer for each cloud partition
chooses the best load balancing strategy. Balancer will
maintain a table or cache to keep track nodes information.
Status of each node will differs it may be in normal state,
Idle state or busy state. Normal state is always preferred than
idle and busy state. However load balancing in a cloud is
still a new problem that needs new architectures to adapt too
many changes also described the role that load balancing
plays in improving the performance and maintaining
stability. Every cloud will have specific range or boundary
number of nodes present with in the area may be tracked and
the status of each node can be monitored if any node present
outside the range of the cloud that will not be considered but
in the proposed we also monitor a node which is available
outside the specific range by deploying a balancer between
existing system to that node. In the proposed system also
take care of ordering of the user requests or packets so that
whenever there is congestion it will select other route to
deliver the packets successfully to end nodes available in
specific partition. Balancer for each cloud partition chooses
the best load balancing strategy. Each balancer maintains a
cache or table to keep track the status of each node in a
partition. to keep track the status of each node in a partition.
III. RELATED WORK
A. Proposed System
In the proposed system shown below Fig.1 where computing
is done efficiently using cloud division rule based on
geographic locations nodes in the cluster may be far from
other nodes and others are in same cluster based on this
services are accessed dynamically to increase the
performance. For efficient cloud computing and also how to
manage load in a cloud and how to use the concept of cloud
division strategies for the efficiency. Load balancing
describes in the cloud computing environment has an
important impact on the performance. Good load balancing
makes cloud computing more efficient and improves user
satisfaction. This system introduces a better load balance
model for the public cloud based on the cloud partitioning
concept with a switch mechanism to choose different
strategies for different situations. After creating the cloud
partitions the load balancing starts. When a job arrives at the
system with the main controller deciding which cloud
partition should receive the job. The partition load balancer
then decides how to assign the jobs to the nodes. When the
load status of a cloud partition is normal this partitioning can
be accomplished locally. If the cloud partition load status is
not normal this job should be transferred to another partition.

B. Figures


Fig. 1. System Architecture.

The proposed system will initiate CDR rule in such a way
that if the geographical area selected are too big and
complex. The division rule can be continued till that lead to
proper load balance in a system, if the selected partition is
still complex it can undergo further division so that system
leads to performance stability using switch concept[2]. This
dynamic load balancing system will enhance the
performance by doing efficient balancing. The balancer will
look for the status of each and every node in a partition so it
maintains a table which is refreshing quite often and often. If
any node is not working or idle can be easily keep tracked so
that it can be replaced or selects other path to deliver the
response for a request. Delay can also be reduced by
Threshold setup by the balancer and switching concept
maintains the order delivery and quick responses to service
the customer request. Proposed system ensures best current
status about the system anywhere and anytime which
provide efficient and flexible load balancing by utilizing the
resources available within the cloud environment.
Load Balancing is a method to distribute workload across
one or more servers, network interfaces, hard drives, or other
computing resources[3]. Typical datacenter implementations
rely on large, powerful (and expensive) computing hardware
and network infrastructure, which are subject to the usual
risks associated with any physical device, including
hardware failure, power and/or network interruptions, and
resource limitations in times of high demand
A proper Load balancing in the cloud computing
environment [1] has an important impact on the performance
and efficiency will improves user satisfaction. Selecting best
strategies is also crucial for different situations.
IV. CONCLUSION
Load balancing in cloud computing environment has an
important impact on the performance. Good load balancing
will make computing efficient and improves the user
satisfaction. Efficient and flexible load balancing model
improves in accessing resources or functionalities in the
cloud environment.
V. FUTURE WORK
How to set the refresh period in the table is itself challenging
since balancer is maintaining a table to keep track status of
each and every node to assign incoming job to the right
partition. Use of better load status evaluation techniques and
also choosing better load balancing strategies are other key
research areas.
ACKNOWLDEGMENT
I would like to thank Prof. Vanishree Arun, Dept. of IS&E,
SJCE, Mysore and faculty members for their valuable
comments and helpful suggestions throughout my work.
REFERENCES
[1] N. G. Shivaratri, P. Krueger, and M. Singhal, Load
distributing for locally distributed systems Computer, vol.
25, No. 12, pp. 33-44, Dec. 1992.
[2] K. Nishant, P. Sharma, V. Krishna, C. Gupta, K. P.
Singh,N. Nitin, and R. Rastogi, Load balancing of nodesin
cloud using ant colony optimization in Proc. 14
th

International Conference on Computer Modelling and
Simulation (UKSim), Cambridgeshire, United Kingdom,
Mar. 2012, pp. 28-30.
[3] B. Adler, Load balancing in the cloud: Tools, tips and
techniques, http://www.rightscale. com/info center/
whitepapers/ Load-Balancing-in-the-Cloud.pdf, 2012.
[4] R. Hunter, The why of cloud,
http://www.gartner.com/ DisplayDocument?doc
cd=226469&ref= g noreg, 2012.

[5] S. Penmatsa and A. T. Chronopoulos, Game-theoretic
static load balancing for distributed systems, Journal of
Parallel and Distributed Computing, vol. 71, no. 4, pp. 537-
555, Apr. 2011.

[6] Microsoft Academic Research, Cloud computing, http://
libra.msra.cn/Keyword/6051/cloud
computing?query=cloud%20computing, 2012.