Scribd
Upload
43 views

Load Balancing On Heterogenous Systems Using Evolutionary Techniques

This document discusses using evolutionary techniques like particle swarm optimization (PSO) and hybrid PSO to perform load balancing on heterogeneous systems. The objectives are to distribute workload evenly across servers to optimize resource utilization and minimize response time. PSO is introduced which models load balancing as optimizing particle movements based on personal and neighborhood experiences. A hybrid PSO approach combines PSO with other algorithms like simulated annealing to improve solution quality. The proposed approach, flowcharts, and applications of PSO and hybrid PSO for load balancing are described over 3 sentences.

Uploaded by

Aastha Mediratta
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
43 views

Load Balancing On Heterogenous Systems Using Evolutionary Techniques

This document discusses using evolutionary techniques like particle swarm optimization (PSO) and hybrid PSO to perform load balancing on heterogeneous systems. The objectives are to distribute workload evenly across servers to optimize resource utilization and minimize response time. PSO is introduced which models load balancing as optimizing particle movements based on personal and neighborhood experiences. A hybrid PSO approach combines PSO with other algorithms like simulated annealing to improve solution quality. The proposed approach, flowcharts, and applications of PSO and hybrid PSO for load balancing are described over 3 sentences.

Uploaded by

Aastha Mediratta
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

LOAD BALANCING ON HETEROGENOUS

SYSTEMS USING
EVOLUTIONARY TECHNIQUES

SUBMITTED BY :-
AASTHA MEDIRATTA (0709110001)
ABHINAV BHATNAGAR (0709110002)
ABHISHEK KANAUJIA (0709110004)
KHUSHBU SRIVASTAVA (0709110050)
INTRODUCTION

LOAD BALANCING is a process by which inbound IP traffic


can be distributed across multiple servers.

It is a technique to distribute workload evenly across two or more


computers, network links, CPUs, hard drives, or other resources
and does the following :-

• Enhances the performance of the servers


• Leads to their optimal utilization
• Ensures no single server is overwhelmed
In general, the process is very straight-forward

• A webpage request is sent to the server

• It transfers further request to the most optimal


server
• The server sends the response to the end user

The use of Evolutionary Computation Techniques are more


robust than traditional methods based on formal logics or
mathematical programming for many real world problems.
PROJECT OBJECTIVE
To design evolutionary optimization Algorithms to equally
 
spread the load on servers and maximize their resources
utilization while minimizing the total response time.

To dynamically schedule the requests in a heterogeneous


environment.

To present a scheduling strategy which uses PSO (Particle


Swarm Optimization) .

To implement a hybridized approach for load balancing,


namely Hybrid PSO.

Comparison of the two different approaches i.e. PSO and


HPSO.
SCOPE OF THE PROJECT
 Understanding load balancing problem faced by web
servers in a heterogeneous environment.

 Study of various evolutionary optimization algorithms.

 Implementation of Particle Swarm Optimization algorithm .

a. Generation of initial swarm.

b. Evaluation of Initial swarm using Fitness Function.

c. Re-evaluation of the swarm to achieve the best solution


using the fitness function, repeating the above process
for fixed number of iterations.
 Implementation of Hybrid Particle Swarm Algorithm by
the hybridization of the features of PSO and other
Optimization algorithm like hill climbing algorithm or
stimulated annealing algorithm.

a) Generation of initial swarm.

b) Evaluation of Initial swarm using Fitness Function.

c) Re-evaluation of the swarm to achieve the best solution


using the hybridized fitness function, repeating the above
process for fixed number of iterations.

 Comparison of the results of the PSO and Hybridized


PSO algorithms.
PROPOSED APPROACH
Particle Swarm Algorithm
o PSO is a stochastic optimization technique which operates
on the principle of swarm intelligence.

o Swarm intelligence is artificial intelligence, based on the


collective behavior of decentralized, self-organized systems.

o PSO is based on the principle of social behavior like bird


flocking or fish schooling.

o The position of a particle is influenced by the best position


visited by itself i.e. its own experience and the position of the
best particle in its neighborhood
Evaluate new particles positions
Generate the initial Swarm

Evaluate the initial Swarm using Re-evaluate the original swarm and
the fitness function find the new personal best and
global best

Initialize the personal best of NO


each particle and the global best Has maximum
of the entire swarm iteration reached?

Update the particle velocity using YES


personal best or local best
Get the best individual from
the last
Apply velocities to the
particles positions

PSO FLOWCHART
The following equations and are used for the velocity
COGNITIVE
updation and the position updation.
COMPONENT

v[k+1] = v[k] + c1 * rand() * (pbest[k] - s[k]) SOCIAL

+ COMPONENT
c2 * rand() * (gbest[k] - s[k]) ……..(a)

s[k+1]=s[k]+v[k+1] ……(b)

where , v[] is the particle velocity s[] is


the current particle solution rand () is a
random number between (0,1). c1, c2
are learning factors. usually c1 = c2 = 2. 
Hybrid Particle Swarm Algorithm

 PSO proved to have good exploration performance,


but has problems with the exploitation in a promising area
of the search space.
 The PSO technique can be combined with some other
evolutionary optimization techniques to yield an even
better performance. The Algorithm thus implemented is
known as hybrid PSO.
 Basically PSO is implemented along with some other
algorithm to improve the quality of the solution obtained
from PSO.
Improve solution quality using
simulated annealing

PSO Has maximum


APPROACH iteration reached?

Get the best individual from


the last

HYBRID PSO FLOWCHART


GANTT CHART
PERT CHART
REFERENCES

[1] P Visalakshi , S N Sivanandam, “Dynamic Task Scheduling with Load Balancing using
Hybrid Particle Swarm Optimization”, Int. J. Open Problems Compt. Math., Vol. 2, No. 3,
September 2009,ISSN 1998-6262.
[2] Aly E. El-Abd, Mohamed I. El-Bendary, “A Neural Network Approach for Dynamic
Load Balancing In Homogeneous Distributed Systems”, IEEE Trans. Parallel and distributed
systems, Vol 9, No.6, June 1997.
[3] Albert Y. Zomaya, Senior Member, IEEE, and Yee-Hwei The, “Observations on Using
Genetic Algorithms for Dynamic Load-Balancing”, IEEE Transactions On Parallel And
Distributed Systems, Vol. 12, No. 9, September 2001.
[4] Swagatam Das, Ajith Abraham, and Amit Konar, “Particle Swarm Optimization and
Differential Evolution Algorithms: Technical Analysis, Applications and Hybridization
Perspectives”.
[5] Chunming Yang, Simon D, “A new particle swarm optimization technique”,
Proceedings of the International Conference on Systems Engineering (2005),pp.164-169.
[6] Parsopoulos K.E, and Vrahatis M.N, “Recent approaches to global optimization
problems through particle swarm optimization”, Natural Computing , Vol.1(2002),
pp. 235 – 306.
THANK YOU !!

You might also like