Genetic Algorithm for task scheduling in Cloud Computing Environment

BY
SWAPNIL S. SHAHADE
1
Guided By
Mrs. RUPALI GANGARDE

1.Introduction
2.Related Works
3.Problem Formulation
4.Algorithm Description
5. Implementation & Results
6. Conclusion
2

 A cloud is a type of parallel and distributed system. A
collection of interconnected and virtualized computer that
are dynamically presented as one or more unified
computing resources based on service level agreements
established through negotiation between the service
providers and consumers.
3

 It provides virtual resources that are dynamically scalable
 It describes virtualized resources, software, platforms,
applications, computations and storage to be scalable and
provided to users instantly on payment for only what they
use.
 Cloud ecosystem comprises of three main entities:
Cloud consumers
Cloud service providers
Cloud services.
4

 It provides three service models which are- Cloud
Infrastructure as a Service (IaaS), Cloud Platform as
Service (PaaS) and Cloud Software as a Service (SaaS).
 Cloud IaaS provides consumer the processing, storage,
networks and other fundamental computing resources where
the consumer is able to run arbitrary software, which can
include operating system and applications.
5

 Cloud PaaS service facilitate developers with provider
specific programming language and tools to develop the
applications.
 Cloud SaaS provides the capability to users to use the
provider’s application running on cloud infrastructures.
 Google Apps is an example of SaaS.
6

Fig. 1: Service Models
7
Cloud computing
Server
Desktop
Tablet
Laptop
Phones

 Cloud technology is still not developed. There are some areas that
are needed to be focused on.
1.Resource management
2.Task scheduling
8

 In 2008, A heuristic method to schedule bag-of-tasks (tasks
with short execution time and no dependencies) in a cloud
is presented in so that the number of virtual machines to
execute all the tasks within the budget, is minimum and the
same time speed up.
9

 There are many algorithms like Min-Min, Max-Min,
Suffrage, Shortest Cloudlet to Fastest Processor (SCFP),
Longest Cloudlet to Fastest Processor (LCFP) and some
meta-heuristics like Genetic Algorithm (GA), Particle
Swarm Optimization (PSO), Ant-Colony Optimization
(ACO) and Simulated Annealing (SA) already existing for
task scheduling.
10

 There are so many algorithms are given by various
researchers for clouds, But, none of the above existing
algorithms have considered the
-Computational complexity(job length, processing power)
- Computing cost(processor cost)
 The two task Scheduling algorithms of Cloud LCFP &
SCFP takes the computational complexity and processing
power of resource into consideration.
11

 Our main purpose is to schedule tasks which involves
finding out a proper sequence in which all the tasks can be
executed such that execution time and execution cost can be
minimized.
 A Genetic algorithm (GA) is a search heuristic that
mimics the process of natural evolution.
 Inspired by natural evolution, such as inheritance, mutation,
selection, and crossover.
12

 Those individuals most successful in each 'competition' will
produce offspring than those individuals that perform
poorly.
 Genes from `good' individuals propagate throughout the
population so that two good parents will sometimes produce
offspring that are better than either parent.
 Time minimization will give profit to service provider and
less maintenance cost to the resources.
 It will also provide benefit to cloud’s service users as their
application will be executed at reduced cost.
13

 Standard Genetic Algorithm (SGA)
1.Produce an initial population by randomly generated
individuals
2.Evaluate the fitness of all individuals
3.while termination condition not met do
- select fitter individuals for reproduction
- crossover between individuals
- mutate individuals
- evaluate the fitness of the modified individuals
- Generate a new population
4. End while
14

 Modified Genetic Algorithm (MGA)
Step1 :- Generate an initial population of individuals with output
schedules of algorithms Longest Cloudlet to Fastest Processor
(LCFP), Smallest Cloudlet to Fastest Processor (SCFP) and
Random Schedules.
Step2 :- Evaluate the fitness of all individuals
Step3 :- While termination condition not met do
17

 We have merged LCFP and SCFP to generate the initial
population of meta-heuristic which encode candidate
solutions to an optimization problem, evolves toward better
solutions.
19

Fig: Chromosome Representation
20

A) LCFP (Longest Cloudlet to Fastest Processor)
1. Sort the cloudlets in descending order of length.
2. Sort the processors in descending order of processing
power.
3. Map the cloudlets from sorted list to the sorted list of
processors on one-to-one mapping basis.
21

B) SCFP (Smallest Cloudlet to Fastest Processor)
1. Sort the cloudlets in ascending order of length.
2. Sort the processors in descending order of processing
power.
3. Map the jobs from sorted list to the sorted list of
processors on one-to-one mapping basis.
22

 The crossover operators are the most important ingredient
of any evolutionary-like algorithm. Indeed, by selecting
individuals from the parental generation and interchanging
their genes, new individuals (descendants) are obtained.
 The aim is to obtain descendants of better quality that will
feed the next generation and enable the search to explore
new regions of solution space not explored yet.
23

There are several mutation operators based on the
permutation based representation of the schedule like
Move, Swap, Move & Swap and Rebalancing.
25
Evaluation
Evaluation is based on the execution time and
execution cost. Those schedules will be selected for next
generation whose makespan( execution time of all
cloudlets) and execution cost is less than thestandard
genetic algorithm (SGA)

 The two algorithms are implemented on Intel core i5
machine with 500 GB HDD and 4 GB RAM on Windows 7
OS, Eclipse with Java version 1.6, with the help of JGAP
(Java based Genetic Algorithm Package)
1. Standard Genetic Algorithm (SGA)
2. Modified Genetic Algorithm (MGA)
26

 A good scheduling algorithm is that which leads to better
resource utilization, less average Make-span and better
system throughput.
 Make-span refers to the completion time of all cloudlets in
the list. To formulate the problem we considered cloudlets (
C1, C2,C3…..Cn) run on processors (P1, P2, P3…..Pn).
 The speed of processors is expressed in MIPS (Million
instructions per second) and length of job can be expressed
as number of instructions to be executed.
27

 All the algorithms are tested by
-Varying the number of cloudlets.
-Randomly varying the length of cloudlets.
 Experimental results show that under heavy loads our
proposed algorithm that is modified Genetic Algorithm
exhibits a very good performance.
28

 The figure shows the Makespan refers to execution time
calculated in seconds of all cloudlets in each of two
algorithms.
 Experimental resulting values show that our proposed
algorithm takes less execution time as compared to existing
SGA which is based on the random generation of schedules.
29

0
100
200
300
400
500
600
10 15 20 25 30
SGA
MGA
30
MAKESPAN
Number of
Cloudlets

0
2000
4000
6000
8000
10000
12000
10 15 20 25 30
SGA
MGA
31
Cost(Rs)

 Above figure compared the execution cost of two
algorithms. Resulting values show that performance of
proposed algorithm is better than the existing algorithm and
keep on increasing with increase in workloads.
32

 Experimental results show that, under the heavy loads, the
proposed algorithm exhibits a good performance.
33

 [1] Kaur, P.D., Chana, I. ―Unfolding the distributed
computing paradigm‖ ,In: International Conference on
Advances in Computer Engineering, pp. 339-342 (2010)
 [2] Mei, L., Chan, W.K., Tse, T.H., ―A Tale of Clouds:
Paradigm Comparisons and Some Thoughts on Research
Issues‖, In: APSCC 2008, pp. 464-469 (2008)
 [3] Silva, J.N., Veiga, L., Ferreira, P.: ―Heuristics for
Resource Allocation on Utility Computating Infrastructures.
In: 6th International Workshop on Middleware for Grid
Computing, New York (2008)
 [4] Mell, P., Grance, T., ―The NIST Definition of Cloud
Computing‖, Version 15, 10-7-09. National Institute of
Standard and Technology, Information technology Laboratory
(2009)
34

Genetic Algorithm for task scheduling in Cloud Computing Environment

Recommended

More Related Content

What's hot (20)

Similar to Genetic Algorithm for task scheduling in Cloud Computing Environment (20)

More from Swapnil Shahade (8)

Recently uploaded (20)

Genetic Algorithm for task scheduling in Cloud Computing Environment