Introduction pay per use basis. Cloud Computing has

 

Introduction

Cloud computing is the best ever
developed technology in the IT industry and a new delivery technique for the
services on pay per use basis. Cloud Computing has
become one of the current technologies adopted by both industry and academic.
It provides a flexible and efficient way to store and retrieve the data. The
main problem is to schedule the incoming request in a way that it should take
least response time, efficient resource utilization and at the same time
resources should not be underutilized. It delivers all services through the
internet dynamically when user demands, such as operating system, network,
storage, software, hardware and resources. These services are classified into
these types: Software as a Service (SaaS), Platform as a Service (PaaS),
Infrastructure as a Service (IaaS), and Everything as a Service (Xaas). The Cloud computing domain is divided into three categories
such as Public, Private and Hybrid cloud. Public Cloud: A cloud is called a “public cloud” when the services are rendered
over a network that is open for public use. Private Cloud: This cloud infrastructure operated solely
for a single organization, whether managed internally or by a third-party, and
hosted either internally or externally. Hybrid Cloud: It is a combination of both public as well as
private cloud. Hybrid cloud
is a composition of two or more clouds (private, community or public) 1

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

 

This paper has been orchestrated as follows.
Section I gives introduction on cloud computing. Section II specifies the load
balancing in cloud computing. Section III illustrates the literature study on
relevant load balancing algorithms. Section IV describes performance analysis
of load balancing algorithms. Section V gives the conclusion.

 

II. LOAD BALANCING IN CLOUD COMPUTING

 

Load balancing is a new technique that provides high
resource time and effective resource utilization by assigning the total load
among the various cloud nodes, side by side it solves the problem of overutilization
and underutilization of virtual machines. Load balancing resolves the problem
of overloading and focuses on maximum throughput, optimizing resource
utilization and minimize response time. It is the pre requirements for
maximizing the cloud performance and utilizing the resources efficiently. The utilization
of clouds has been improved by a resource allocation method which has pre-emptible
task execution. The load balancing is an efficient and critical concept in
cloud computing and it helps to utilize the resources optimally, thereby
minimizing the consumption of resources. Thus load needs to be distributed over
the nodes in cloud-based architecture, so that each resource does the equal
amount of work at any point of time that is allocated by a load balancer. The
load balancer determines the various request allocation to different servers. The
load balancer uses various algorithm to determine the server which has to
handle the request.1

In cloud computing, different load balancing algorithms
have been proposed. The ultimate aim of all these proposals is to achieve high
throughput and minimizing the response time.

 

III- RELATED WORK

 

Round Robin Virtual Machine Load Balancing Algorithm

It is a very
simple load balancing algorithm that places the newly coming cloudlets on the
available virtual machines in a circular manner. The major advantage of this
algorithm is simplicity and easy implementation. The main drawbacks are prior
knowledge of user tasks and system resources. Further, it does not make use of
current state of the system. 2

 

Throttled Virtual Machine Load Balancing Algorithm

In this dynamic approach a user submits request to the Data Center
Controller (DCC). Then, Data Center Controller asks the VM Load Balancer to
determine the appropriate virtual machine that can handle the given workload
easily. Throttled VM Load Balancer keeps a virtual machine list and their
status (available/busy). If a suitable VM is found on memory space, cores or
availability basis, then throttled VM Load Balancer accept the cloudlet request
and allot the cloudlet request over that virtual machine. Otherwise, client has
to wait in the queue until a suitable VM becomes available. Among all, it is
best approach for load balancing, since it maintains the present state of all
VMs in data center. But the major drawback is that it works properly only if
all VMs in a data center have same hardware configuration. 2

 

ESCE Virtual Machine load Balancing Algorithm

ESCE stands
for Equally Spread Current Execution. It is also called as Active VM Load
Balancing algorithm. This algorithm is based on spread spectrum technique. It
equally distributes the workload among VMs in data center. A job queue keeps
all the cloudlet requests that need the VM for their execution. ESCE VM Load
Balancer (VMLB) also maintains a list of virtual machines. The VM Load Balancer
continuously checks the job queue and VM list. If a VM is found free, then
cloudlet request will be allotted over that VM. At the same time, VMLB inspect
the overloaded VMs. If any virtual machine is found overloaded, then VMLB move
some load to an idle or an under loaded virtual machine, so as to reduce some
load of overloaded VM. The main drawback is high computational overhead. 2  

 

An enhanced priority based HTV load balancing algorithm

This algorithm
performs an effective and reliable resource allocation of the tasks on the
servers in cloud computing environment. This algorithm considers the three
parameters such as load on the server, current performance of server and time
limit of the tasks. This algorithm computes the load and performance factor of
each virtual machine and then allocates the incoming task to various virtual
machines according to their time limit and stand-by time to increase the
throughput and performance. 3

 

Virtual Machine
and Physical Machine Categorization Algorithm

 

In general, load balancing approach that amplify the
physical resource utilization and curtail the energy consumption. To calculate
the performance of the approach it is compared with the existing load balancing
approach and judged against the number of migration and energy consumption.
Experiment results say that this approach gives better result while it is
compared with the existing load balancing methods. 4

 

Composite algorithm

Load Balancing is required to properly manage the resources of the
service contributor. Load balancing is a technique to distribute the workload
among many virtual machines in a Server over
the network to achieve optimal resource consumption, decrease in data
processing time, decrease in average response time, and avoid overload. The
objective of effective, efficient and enhanced composite scheduling algorithm
is used to maintain the load and provides efficient resource allocation
techniques. This Composite approach is applied for load balancing using Equally
Spread Current Execution (ESCE) and Throttled algorithms. 5

 

Distributed dynamic priority based algorithm

It is used for
balancing the load on instances effectively, improves the system consistency,
minimizes response time and increases the throughput. Allocating the resources
on virtual machines based on priority achieves the better response time and
processing time. Load balancing ensures all instances in a node in the networks
to do the equal amount of work at any instant of time. Priority based resource
provision to improve the utilization of resources and reducing response time of
cloud services. 6

Burstness-aware load
balancing algorithm

This algorithm can adapt to the variation in
the request rate by adopting two load balancing algorithms: RR in burst and
Random in non-burst state. Fuzzy logic is used in order to assign the received
request to a balanced VM. This algorithm has been evaluated and compared with
other algorithms using Cloud Analyst simulator. Experimental results show that
the algorithm improves the average response time and average processing time in
comparison with other algorithms. 7

 

Honey Behavior Load
Balancing Technique

In this Technique the high priority tasks are removed from
overloaded virtual machine and they are allocated to under loaded virtual
machine by considering least numbers of same priorities to those tasks, cost
effective virtual machine, and least expected completion time which also
balances the loads of dependent tasks in pre-emptive manner. The least expected
completion time, cost and priority at submission time of that task helps to
produce minimum completion time, reduces waiting time of the tasks and
eventually achieves better resource utilization. 8

 

Weighted based optimized load balancing

This approach
is for distributing of incoming jobs uniformly among the servers or virtual
machines. The performance is analyzed using Cloud simulator and compared with
existing Round Robin and EIPR algorithms. Simulation results have demonstrated
that this algorithm has distributed the load uniformly among virtual machines.
9

 

New enhanced load balancing
algorithm

First an adaptive strategy
has been devised for load balancing according to the quality of the solutions
founded by Genetic. Secondly, the enhanced load balancing strategy is combined
with the setting of other parameters like fitness and the selection of the
initial resource pool provides the significant impact on the performance of the
algorithm. In this paper the new enhanced load balancing algorithm gives the
better result than the existing genetic algorithm. 10

 

Tow –level global load
balancing framework

A framework for global server load
balancing of the Web sites in a cloud with two-level load balancing model. This
framework is intended for adapting an open-source load-balancing system and the
framework allows the network service provider to deploy a load balancer in
different data centers dynamically while the customers need more load balancers
for increasing the availability. 11

 

Dynamic load balancing algorithms

 

Load balancing algorithms play important role in equalizing
load among data centers and in efficient use of computing resources. In this
paper, performance of a dynamic load balancing algorithm has been evaluated by
dividing data-centers in different zones. It has been shown that the proposed
algorithm improves the computing efficiency of data-centers and minimizes the
response time of user’s applications. 12

 

 

IV- PERFORMANCE ANALYSIS
OF LOAD BALANCING ALGORITHMS

The forthcoming part discusses various load balancing
algorithms and shows the results comparatively.

 

Min- min Load Balancing Algorithm

 

Min-Min is a simple and fast algorithm capable of
providing improved performance. Min-Min is use the ideal tasks at first which
results in best and improve the overall makespan. Assigning small task first is
its drawback. Thus, smaller tasks will get executed first, while the larger
tasks keep on in the waiting stage, which will finally result in poor machine
use. Min-Min exhibits minimum completion time for jobs which are unassigned and
later allocating the jobs with minimum completion time (hence min-min) to a
node that is capable of handling it. 13

 

Max-min Load Balancing Algorithm

 

This algorithm first for all the available tasks are
submitted to the system and minimum completion time for all of them are
calculated, then among these tasks the one which is having the completion time,
the maximum is chosen and that is allocated to the corresponding machine. If in
a task set only a single long task is presented then, Max-Min algorithm runs
short tasks concurrently along with the long task. Max-Min is almost identical
to Min-Min, except it selects the task having the maximum completion time and
allocates to the corresponding machine. The algorithm suffers from starvation
where the tasks having the maximum completion time will get executed first
while leaving behind the tasks having the minimum completion time. 13

 

RASA Algorithm

 

RASA is Resource Aware Scheduling Algorithm it combines
Min-Min and Max-Min algorithm alternatively in order to achieve better
performance. In RASA resource completion time is calculated and then Min-Min
and Max –Min algorithms are applied alternatively. 13

 

Minimum Makespan algorithm

 

This algorithm first checks the no-more task left then
minimum makespan taks first selected and it compare with the task and migrated.
The two tasks are produces the same makespan time it choose the node with
higher computational resources. 13

 

PA-LBIMM Algorithm

 

PA-LBIMM priority aware load balancing improved min min
algorithm separate the tasks into G1 and G2groups. The tasks submitted by VIP
user’s or high priority users are considered as group G1 and tasks submitted by
low priority users are considered as group G2. Tasks are scheduled to the
resources on the priority basis. Firstly, for all the tasks in G1, each task is
assigned to the VIP category resource by using Min-Min. Then each task in G2
group is assigned to all the resources by using Min-Min. Now, load balancing
function of LBIMM algorithm is executed to load balance all the resources. 14

 

RPA-LBIMM Algorithm

 

This algorithm RPA-LBIMM recovery priority aware load balancing improved min
min algorithm is also similar to the priority aware load balancing improved min
min algorithm. Here use the recovery policy which helps the cloud scheduler to
reschedule the tasks if a resource fails at the time of execution to achieve
the minimum makespan. According to this policy, First of all, scheduler looks
for the failed resource. All the tasks that were scheduled by PA-LBIMM to
execute on will be considered as a task set. 14

 

TABLE 1. List of Load balancing Algorithms in Cloud computing

 

S. No.

Load balancing alg.

Parameters Used

1

Min Min

Makespan, Resource utilization

2

MaxMin

Maekspan, Resource utilization

3

RASA

 Maekspan
, Resource utilization

4

Minimum Makespan

Maekspan , Resource utilization

5

PA-LBIMM

 Maekspan

6

RPA-LBIMM

Maekspan

 

Table 1 lists out the various load
balancing algorithms and the parameters used in the algorithms. All these
algorithms use the parameters completion time and resources utilization in
cloud environment. These algorithms distribute the load based on the number of
user request and number of available resource in cloud and also considering the
proper utilization of resource.

 

TABLE 2. Task Completion Time makespoan (sec.) of the given
algorithms

 

S. No.

Load balancing alg.

Completion time Makespan  (sec.)

1

Min Min

30.35

2

MaxMin

20.03

3

RASA

11.45

4

Minimum Makespan

10.8

5

PA-LBIMM

38.37

6

RPA-LBIMM

35

 

Table 2 represents the
completion time of the task based on the number of nodes in the simulation
area. The makespan of the different algorithms are given.

 

TABLE 3. Resource utilization of the algorithms

 

S. No.

Load balancing alg.

Resource utilization (%)

1

Min Min

43.09

2

MaxMin

79.32

3

RASA

88.72

4

Minimum Makespan

91.01

5

PA-LBIMM

6

RPA-LBIMM

 

Table 3 represents the resource
utilization of various load balancing algorithms. The average resource
utilization of the different algorithms is given.

V –  conclusion

The study
deals with various load balancing algorithms. The existing algorithms are
static, dynamic, composite, and prioritized. The ultimate purpose of those
algorithms is to reduce the response time and maximize the resource
utilization.  The results of the existing
algorithms are confined to give better result. Still there is plenty of space
to improve the results to extract best service from cloud service providers.
This study also shows the comparative results of the existing load balancing
algorithms based on the parameters such as makespan and resource
utilization. 

 References

1           Reena Panwar Bhawna Mallick, “A Comparative Study of Load Balancing
Algorithms in Cloud Computing”, International Journal of
Computer Applications (0975 – 8887) Volume 117 – No. 24, May 2015.

2           Mamta Khanchi, Sanjay Tyagi, “An Efficient
Algorithm for Load Balancing in Cloud Computing” International Journal of Engineering Sciences & Research Technology,
June, 2016.

3           Divya
Garg, Urvashi Saxena,” Dynamic Queue
Based Enhanced HTV Dynamic Load Balancing Algorithm in Cloud Computing”,
International Journal of Innovative Research in Science, Engineering and
Technology, Vol. 5, Issue 1, January 2016.

4           Sachin Soni, Praveen Yadav, “A Load
Balancing Approach to Minimize the Resource Wastage in Cloud Computing”, International
Advanced Research Journal in Science, Engineering and Technology, Vol. 3, Issue 3, March 2016.

5           Navtej Singh Ghumman, Rajesh Sachdeva,” an
efficient approach for load balancing in cloud computing using composite
techniques”, International Journal of Research in Engineering and Applied
Sciences, volume 6, issue 2 February, 2016.

6           G.Suryadevi,
D.Vijayakumar, R.SabariMuthuKumar, Dr. K .G. Srinivasagan, “An Efficient Distributed Dynamic Load Balancing
Algorithm for Private Cloud Environment”, International Journal of Innovative
Research in Science, Engineering and Technology, Volume 3, Special Issue 3, March 2014.

7           Sally
F. Issawi,     Alaa Al Halees, Alaa Al
Halees, “An Efficient Adaptive Load Balancing Algorithm for Cloud Computing
Under Bursty Workloads”, Engineering, Technology & Applied Science Research Vol. 5, No. 3,
2015.

8           Khushbu Zalavadiya,Dinesh Vaghela , “Honey Bee Behavior Load Balancing of
Tasks in Cloud Computing”,
International Journal of Computer Applications (0975 – 8887), Volume 139 –
No.1, April 2016.

9           B. Nithya Nandhalakshmi , Mahalingam,
“Efficient Load Balancing in Cloud
Computing Using Weighted Throttled Algorithm”, International Journal of
Innovative Research in Computer and Communication Engineering ,Vol. 3, Issue 6,
June 2015.

10         Er.
Pooja Er. Vivek Thapar,”An Enhanced Virtual Machine Load Balancing Algorithm
for Cloud Environment”, , International
Journal of Emerging Research in Management &Technology, ISSN: 2278-9359 (Volume-5,
Issue-5),May 2016.

11         Po-Huei Liang1 and Jiann-Min Yang. “Evaluation
of two-level Global Load Balancing Framework in cloud environment” International
Journal of Computer Science & Information Technology (IJCSIT) Vol 7, No 2,
April 2015.

12         Navtej Singh Ghumman, Rajesh Sachdeva,” an
efficient approach for load balancing in cloud computing using composite
techniques”, International Journal of Research in Engineering and Applied
Sciences, volume 6, issue 2 February, 2016.

13         Er. Rajeev Mangla, Er.
Harpreet Singh,” Recovery and user priority based load
balancing in cloud computing”, International Journal of Engineering and Science
and Research, February 2015. 

14         Harish Chandra, Pradeep Semwal, Sandeep
Chopra,” load balancing in cloud computing using

a novel minimum makespan
algorithm”, International Journal of
Advanced Research in Computer Engineering & Technology ,Volume 5, Issue 4,
April 2016.

 

 

Abstract: Cloud computing is a new technology now a days for providing different
kind of services to the end users. It focuses mainly the dynamic services using
very large scalable and virtualized resources over the Internet. The allocation of the group
of resources may start a problem of availability of these resources and distributing
the workload of all the VMs among themselves called as load balancing. Load balancing is a main
challenge in cloud environment. It helps to distribute the dynamic workload
across multiple nodes to ensure that no single node is overloaded. It helps in
proper utilization of resources .It also improves the performance of the
system. Load balancing is the process of finding overloaded nodes and then
transferring the extra load to other nodes. Due to novelty of cloud
computing field, there is no many standard load balancing algorithm used in
cloud environment. Hence efficient utilization of resources must be important
and for that load balancing plays a major role to get maximum benefit from the
resources. Having understood the vital role of load balancing, this paper
covers various load balancing algorithms related to cloud computing and shows a
comparative study on load balancing algorithms.

 

Keywords: Cloud Computing,
Load Balancing, Virtual Machine

 

 

D. Suresh Kumar, Research Scholar

School of Computer Science, Engineering
and Applications Bharathidasan University

Tiruchirappalli, Tamil Nadu, India

[email protected]

Dr. E. George Dharma Prakash Raj,Asst.Professor

School of Computer Science, Engineering
and Applications

Bharathhidasan University

Tiruchirappalli, Tamil Nadu, India

[email protected]

x

Hi!
I'm Morris!

Would you like to get a custom essay? How about receiving a customized one?

Check it out