Task scheduling Survey in Cloud Computing

TASK SCHEDULING ALGORITHM-
A SURVEY
(LOAD BALANCING IN CLOUD COMPUTING)
Guided By: Prepared By:
Miss Shilpi Saxena Swati Singh
Assistant Professor M.Tech 2nd Year (CSE)
(Deptt. Of CS/IT)
1

CONTENTS
 What is Cloud
 Introduction to Cloud Computing
 Introduction to Load Balancing
 Literature Survey
 Terminology in Existing Algorithms
 Problem Statement
 References
2

WHAT IS CLOUD ?
“The Cloud” is simply the trendy term for a network or
remote servers that can be accessed via an Internet
connection store and manage information.
Deployment Model:
 Private Cloud
 Public Cloud
 Hybrid Cloud
Service Model:
 Software as a Service (SaaS)
 Platform as a Service (PaaS)
 Infrastructure as a Service (IaaS)
3

DEPLOYMENT MODEL
Private Cloud: Data center architecture owned by a single company. Eg: IBM’s
Blue Cloud, Sun Cloud, Window Azure.
Public Cloud: It is basically the internet. Service provider use internet to make
resource available to general people.
Eg: Gmail, Office 365, Dropbox.
Hybrid Cloud: For instance during peak periods individual applications, or
portion of applications can be migrate to the public cloud.
4

SERVICE MODEL
 Software as a Service (SaaS): Email, Online Games, Facebook.
 Platform as a Service (PaaS): Google Compute Engine, Apache Stratos
 Infrastructure as a Service (IaaS): Virtual Machine, Storage, Servers
5

INTRODUCTION TO CLOUD COMPUTING
 Cloud computing is Internet-based computing, whereby
shared resource, software, and information are provided to
computers and other devices on demand.
6

LOAD BALANCING
It is a process of assigning the total load over each node of the
collective system to make resource utilization effective and to
improve the response time of the job.
Goals of load balancing:
 1- to improve the performance substantially
 2- to have a backup plan in case the system fail even partially
 3- to maintain the system stability
7
T1
T2
T3 T4
R1 R2
T1 T3
T2 T4
R1 R2

LITERATURE SURVEY
 Traditional Min-Min Heuristic Algorithm[1]
 Based on the concept of Minimum Completion Time.
 It works in two phase:
 Expected Completion time is calculated for each task.
 Task with overall minimum completion time is scheduled.
Result: No longer waiting of processor for smaller tasks.
Problem: Starvation (For larger tasks).
 Unable to balance load when small task scheduled initially.
8

LITERATURE SURVEY
 Traditional Max-Min Heuristic Algorithm[1][2]
 Based on the concept of Maximum Completion Time.
 Task with overall minimum completion time is scheduled.
Result: No longer waiting of processor for larger tasks.
 Good load balancing when smaller task are more in number
then larger task.
Problem: Starvation (For smaller tasks).
 Unable to balance load when number of larger task increases.
9

LITERATURE SURVEY
 Resource Awareness Scheduling Algorithm[1][3]
 Hybrid algorithm (Max-Min & Min-Min) known as RASA.
 Based on the concept of Completion Time of each task.
 Max-min and Min-Min is applied alternatively to schedule task.
 If number of resources are odd, apply Min-Min strategy first
otherwise Max-Min strategy.
Result: No longer waiting of processor for larger or smaller tasks.
 Good load balancing.
Problem: Unable to balance load when number of larger task
increases.
10

LITERATURE SURVEY
 Qos Guided Min-Min Heuristic Algorithm[4]
 It adds a constraint of QoS (Quantitative QoS for
measuring bandwidth).
 Task are classified under high and low bandwidth.
 Task required high bandwidth are scheduled first.
Result: Task under lower and higher bandwidth are scheduled
parallel.
Problem: Unable balance load when all task satisfy low or high
bandwidth.
11

LITERATURE SURVEY
 Reliable RASA Scheduling Algorithm[7]

 It added a constraint of Resource Reliability in existing
Max-Min, Min-Min & RASA Algorithm (Qualitative Qos for
improving makespan and load balance).
 It works in three phase:
 Resource Reliability is provided in percentage.
 Resource manager sets a reliability criteria.
 An appropriate resource which fulfil the criteria is selected.
Result: Execution time decreases.
 Risk associated with job failure reduced.
Problem: Increase in reliability percentage, increase in execution
time.
 Increment in percentage will make only few resource available.
12

LITERATURE SURVEY
 Improved Max-Min Task Scheduling Algorithm[1][5]
 Task with maximum execution time is selected (Largest Task)
 Selected task is scheduled over resource with minimum
completion time (Slowest Resource).
Result: Makespan reduced
Problem: Task with largest execution time (greater then the sum of
smaller task) results in the increment of makespan.
13

LITERATURE SURVEY
 Enhanced Max-min Task Scheduling Algorithm[6]
 Average or nearest greater then average task is selected.
 Selected task is scheduled over resource with minimum
completion time (Slowest Resource).
Result: Makespan reduced.
 Better load balancing.
Problem: Unable to balance load when number of larger task
increases.
14

PROBLEM STATEMENT
 An optimized Task Scheduling Algorithm is need to
design which makes:
 Proper resource utilization.
 Reduces makespan.
 Reduces overhead from resource.
 Balance proper load over resource.
 Increase throughput and system performance.
 Better CPU utilization.
 Minimize turnaround, waiting and response time.
15

METHODOLOGY
 To be proposed …..
16

TOOL USED FOR SIMULATION
CloudSim: It is a simulation tool such as SimJava &
GridSim.
 It is used to calculate performance of the environment.
 It is the only simulator which support virtualization of
Cloud Computing.
 To guarantee Qos in CloudSim, we need to propose an
optimized Task Scheduling Algorithm.
NetBeans: It is a Software Development platform written in
Java.
 It allows applications to be developed from a set of
modular software components called modules. 17

CONCLUSION
 To be proposed …..
18

REFERENCES
[1] S. Devipriya & C. Ramesh, "Improved Max-Min Heuristic Model for Task Scheduling
in Cloud," International Conference on Green Computing, Communication and
Conservation of Energy (ICGCE), 978-1-4673-6126-2/13 2013 IEEE.
[2] Etminani .K, and Naghibzadeh. M, "A Min-min Max-min Selective Algorithm for
Grid Task Scheduling,“ Third IEEE/IFIP International Conference on Internet,
Uzbekistan, 2007
[3] SaeedParsa and Reza Entezari-Maleki, "RASA: A New Grid Task Scheduling
Algorithm," International Journal of Digital Content Technology and its
Applications,Vol. 3, pp. 91-99, 2009.
[4] He. X, X-He Sun, and Laszewski. G.V, "QoS Guided Min-min Heuristic for Grid
Task Scheduling," Journal of Computer Science and Technology, Vol. 18, pp. 442-
451, 2003
[5] O. M. Elzeki, M. Z. Reshad, M. A. Elsoud, "Improved Max-Min Algorithm in Cloud
Computing," International Journal of Computer Applications (0975 – 8887), Volume
50 – No.12, July 2012.
[6] Upendra Bhoi1, Purvi N. Ramanuj, “Enhanced Max-min Task Scheduling Algorithm
in Cloud Computing,” International Journal of Application or Innovation in
Engineering & Management on Volume 2, 2013. 19

REFERENCES
[7] Sunilkumar Nakum, C. Ramakrishna, Amit Lathigara, “Reliable RASA Scheduling
Algorithm for Grid Environment,” 2014 IEEE International Conference on Computer
Communication and Systems(ICCCS '14), Feb 20-21, 2014.
[8] Sung-Min Jung, Nam-Uk Kim, Tai-Myoung Chung, “Applying Scheduling
Algorithms with QoS in the Cloud Computing,” 978-1-4799-0604-8/13 2013 IEEE.
[9] Yash P. Dave, Avani S. Shelat, Dhara S. Patel, Rutvij H. Jhaveri, “Various Job
Scheduling Algorithms in Cloud Computing: A Survey,” ICICES2014 - S. A.
Engineering College, Chennai, ISBN No.978-1-4799-3834-6/14 2014 IEEE
20

Task scheduling Survey in Cloud Computing

More Related Content

What's hot (20)

Similar to Task scheduling Survey in Cloud Computing (20)

Recently uploaded (20)

Task scheduling Survey in Cloud Computing

Editor's Notes