© 2020 February 2020, Volume 7, Issue 2 www.jetir.

org (ISSN-2349-5162)

RESOURCE SCHEDULING IN CLOUD

ENVIRONMENT: A SURVEY
Meenakshi Saini1, Dr. Neeraj Mangla2
1
Ph.D. Research Scholar, Maharishi Markandeshwar (Deemed to be University) Mullana, Ambala, India,
2
Associate Professor, Maharishi Markandeshwar (Deemed to be University) Mullana, Ambala, India.

Abstract: Cloud computing offers the innovative facilities at a stretch that area unit too engaging for any Cloud user to ignore. With
its rising application and popularization, IT firm’s area unit are quickly deploying distributed information centres internationally,
sitting varied challenges in terms of programming of resources beneath completely different body domains. This viewpoint brings
out absolute essential components for economical programming of resources providing a large genre of characteristics, diversity in
context of level of service agreements which too with user contingent snap. During this paper, a comprehensive survey of analysis
associated with varied aspects of Cloud Resource programming is provided with parameters like Energy potency, Virtual Machine
allocation and migration, Cost-effectiveness and Service-Level Agreement is additionally conferred.

IndexTerms: Resource Scheduling, Cloud Computing, Quality of Service (QoS), Service-Level Agreement (SLA).

1. INTRODUCTION Cloud Computing is that the new cost-effective computing customary that delivers on-demand access to
services on pay-per-usage basis [1]. The unwavering services offered by Cloud Computing area unit accomplished through its
innovative world information centres that area unit firmed on virtualized cypher and storage technologies [2]. it's supposed for the
Cloud users to multifold the prospects by accessing hired infrastructure and software system ap-plications ubiquitously and non-
restrictive in time. The ideology is firmed on the grounds of ‘re-usability of IT capabilities. the standard computing archetypes
become ex by Cloud Computing thanks to its expansive horizons across structure boundaries.
The Cloud Computing paradigm offers varied advantages to each cloud customers and repair suppliers. The aim of service supplier
is to maximise the profit by economical usage of its datacentre resources through virtualization technology [3] and effective
programming among the constraint of Service-Level Agreement with cloud users and restricted power budget. From the angle of
Cloud’s user, the main focus is on application performance, handiness of services, cost-effectiveness [4]and adaptableness to the
dynamical needs.
The resource programming in Cloud setting is often a sophisticated task thanks to geographical distribution of resources having
variable load conditions, completely different user’s needs and worth models [5]. plenty of analysis work coping with the Cloud
resource programming drawback has been sliced by several researchers [6]. This paper provides a close survey of the prevailing
resource programming techniques specializing in the promising options and challenges of Cloud Computing.

2. LITERATURE REVIEW
Resource provisioning counsel that the choice of deployment, and run-time management of package (e.g., direction servers, load
balancers) and hardware resources (e.g., CPU, storage, and network) for creating given certain action for applications. This resource
provisioning takes Service Level Agreement (SLA) into thought for providing service to the Cloud users. this is often associate
degree initial agreement between the Cloud users and Cloud service suppliers that ensures Quality of Service (QoS) parameters like
performance, handiness, dependability, time interval etc. within the consequent sections, a classification of the resource
programming drawback in Cloud setting as shown in Fig. 1. and its existing accessible solutions are reviewed in short.

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1218
© 2020 February 2020, Volume 7, Issue 2 www.jetir.org (ISSN-2349-5162)

Energy
Based
Scheduling

Cloud
SLA Based Cost Based
Resource
Scheduling Schdeuling
Scheduling

QoS Based
Scheduling

Fig. 1. Resource Scheduling problem in Cloud Computing

Table 1.Comparative Study of Various Cost based Resource Scheduling Techniques
Algorithm & Parameters of Tools Findings Environ
Technique Scheduling Used ment
Job grouping based Cost, CloudSim The projected strategy will cut back the Cloud
dynamic scheduling Resource Utilization, Version 3.0 time interval further as price.
strategy [10] Computation Ratio
List scheduling algorithm Cost, CloudSim The planned formula balances the load Cloud
for heterogeneous Makespan, and minimize the entire financial value.
computing system [11] Load balance
A task scheduling Cost, Solve the slow convergence and improve Cloud
algorithm based on genetic Performance, MATLAB the looking potency of algorithmic
algorithm and Ant Colony Execution Time program.
Optimization in Cloud
Computing [12]
Credit based scheduling Task length, Simulator The results show that projected Not
using cost in Cloud Task cost algorithmic program works expeditiously Mentione
Computing [13] Makespan than the others. Makespan of the task is d
lesser than the value of the task is
additionally decreasing.
Scheduling cost approach Cost, CloudSim Proposed algorithmic program improves Cloud
(SCA) in Cloud Resource Utilization the load balance and cut back the value of
environment [14] processor, RAM, bandwidth, storage
compared to FCFS & SJF algorithmic
program.
Cost based task scheduling Cost factor, CloudSim The result shows that projected theme Cloud
in Cloud Computing [15] Execution time maximize the performance with less price
issue (234.21) as compared to the basic
principle rule (358.13).
Improved cost-based Cost, Performance CloudSim 1. Measures each resource price and Cloud
algorithm for task computation performance.
scheduling [16] 2. Improve thecomputational-l ratio
A PSO based scheduling Makespan, CloudSim provides higher performance than the Cloud
of workflow on Iaas Cost opposite similar approaches in terms of
Clouds [17] meeting applications point in time and
generating schedules with lower
execution value.

2.1 COST BASED SCHEDULING

In Cloud Computing, service suppliers need to attenuate resource rental prices whereas still meeting employment demands and
Cloud users forestall to very cheap doable costs for the resources they lease. it's worthy to say that enhance the performance of the
Cloud Computing and attain higher turnout in less time by mistreatment correct theright the correct utilization of its virtual
machines (VM) residing on information centres and moreover as proper allocation of tasks on them [7]. the kind of allocation of
task to VM is static. The performance is measured in terms of value. In [8], authors will highlight the schedule task teams in Cloud
Computing platform, wherever resources have completely different resource prices and computation performance. thanks to job
grouping, communication of coarse-grained jobs and resources optimizes computation/communication quantitative relation. For this
purpose, associate degree algorithmic program supported each price with user task grouping is planned. The planned programming
approach in Cloud employs associate degree improved cost-based programming algorithmic program for creating economical

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1219
© 2020 February 2020, Volume 7, Issue 2 www.jetir.org (ISSN-2349-5162)

mapping of tasks to offered resources in Cloud. This programming algorithmic program measures each resource value and
computation performance, it additionally improves the computation and communication quantitative relation by grouping the user
tasks in line with a specific Cloud resource’s process capability and sends the sorted jobs to the resource. In [9], authors conferred a
unique hybrid algorithmic program, known as Chemical Reaction – Ant Colony (CR-AC), combining each the Chemical Reaction
Optimization (CRO) and Ant Colony Optimization (ACO) algorithms to resolve the workflow-scheduling drawback. The planned
CR-AC algorithmic program is enforced within the CloudSim toolkit and evaluated by mistreatment real applications and Amazon
EC2 evaluation model. Moreover, the results area unit compared with the foremost recent algorithms: modified Particle Swarm
Optimization (PSO) and Cost-Efficient Genetic Algorithmic program (CEGA). The experimental results indicate that the CR-AC
algorithmic program achieves higher results than the standard CRO, the ACO, the modified PSO and CEGA algorithms, in terms of
total value, time quality, and schedule length. Table 1.Elucidates a comparative study of various Cost based Scheduling Techniques.
Table 2. Comparison of Various QoS based Resource Scheduling Techniques
Algorithm & Technique Parameters of Tools Used Findings Environment
Scheduling
A novel QoS guided task scheduling algorithm QoS, Simulator Results shows that the new Not Mentioned
for grid computing [21] Performance, approach will result in
Resource Utilization, important performance gain for
Makespan a range of applications.
A QoS based scheduling algorithm for instance- QoS, CloudSim Simulation results shows that, Cloud
intensive workflows in Cloud environment [22] Workflow, Deadline QDA algorithmic rule will
allocation higher meets the various
necessities from users and
additionally encompasses a far
better load equalisation rate.
QoS based task scheduling algorithm in Cloud QoS, Improves the potency of the Cloud
Computing [23] Execution time, QoS considering factors
Makespan, inbound time of the task, time
Resource Utilization taken by the task to execute on
the resource and therefore the
value in use for the
communication.
QoS – Driven task scheduling [24] Makespan, CloudSim Uses many QoS parameters to Cloud
Average Latency assign priority to tasks on
resources that take minimum
time as possible.
QoS aware workflow scheduling QoS, WorkflowSim The result shows the varied Cloud
(WFS) in Cloud Computing [25] Optimization, aspects of progress sorts, QoS
Workflow constraints, WFS schemes still
as their categorization into
heuristic, meta-heuristic and
hybrid schemes.
A deadline constrained scheduling algorithm for Deadline, MATLAB Proposed resolution providing Cloud
Cloud Computing system based on the driver of Cost lower time complexness and
dynamic essential path [26] also the performance of the
planned formula is much better.
Cost based multi QoS job scheduling [27] Cost, Numerical The planned approach equally Cloud
Time Simulation distributing the load among the
present machine. So that, the
full completion time of tasks is
reduced.

2.2 QoS BASED SCHEDULING

The Cloud service suppliers unceasingly attempt to enhance Cloud management tools to ensure the specified QoS and supply users
the services with prime quality. one in all the foremost necessary management tools that play an important role in enhancing QoS is
programming. programming is that the method assignment users’ tasks into offered Virtual Machines (VMs). In [18], authors
planned a multi-layer QOS primarily based Task programming algorithmic program for Cloud computing. Firstly, so as to replicate
the precedence relation of tasks, the planned algorithmic program computes the priority of tasks in line with the special attributes of
tasks by native programming agent, then kinds tasks by priority. Secondly, the algorithmic program evaluates the completion time
of every task on completely different services, and schedules every task onto a service which may complete the task as shortly as
doable in line with the sorted task queue. In [19], authors planned a unique Network aware QoS advancement programming
methodology for Grid Services. The planned programming algorithmic program considers network and QoS constraints. The goal of

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1220
© 2020 February 2020, Volume 7, Issue 2 www.jetir.org (ISSN-2349-5162)

the planned programming algorithmic program is to implement the advancement schedule so it reduces execution time and resource
value and nonetheless meets the point in time obligatory by the user. The experimental result shows that the planned algorithmic
program improves the success quantitative relation of tasks and turnout of resources whereas reducing makespan and advancement
execution value. In [20], authors devised differing kinds of task programming algorithms with QoS facility and problems associated
with them in Cloud Computing. These programming algorithms specialise in resource management, time interval, load balancing
and performance. Comparison of various QoS based Resource scheduling Techniques is presented in Table2.

2.3 SLA BASED SCHEDULING

In Cloud setting, the services area unit provided by Cloud service supplier or by Cloud vendors. To access the resource the tip user
and also the Cloud service supplier should build a covenant with one another. Service Level Agreement (SLA) could be a legal
agreement signed between the client and also the service supplier that ensures the Quality of Service (QoS) parameters like
information storage, handiness of the system mainframe, and network.
Table 3. Comparison of Various SLA based Resource Scheduling Techniques
Algorithm & Technique Parameters of Tools Findings Environm
Scheduling Used ent
SLA aware application SLA violation CloudSim The heuristic design and
deployment and resource rate, implementation and present detailed
allocation in Cloud [31] Resource evaluations as a proof of concept
Utilization emphasizing the performance of the Cloud
approach
SLA based resource allocation SLA violation CloudSim Proposed solution minimizes the Saas
for software-as-a-service rate, providers cost and the number of SLA
provider (SAAS) in Cloud Cost violation in a dynamic resource
Computing [32] sharing Cloud environment
Cloud
SLA base d admission control Cost, CloudSim Simulation result shows that the
for a software-as-a-service SLA violation proposed algorithm provide substantial Cloud
provider in Cloud [33] improvement (up to 40% cost saving)
SLA based resource Cost, CloudSim The proposed algorithm reduces the Cloud
provisioning for Hosted SLA violation total cost up to 54% and the number of
software-as-a-service SLA violations up to 45%
applications [34]
Optimized SLA based QoS, CloudSim Proposed algorithm provides good
workload balancing strategy Load Balancing, response time, reduces waiting time, Cloud
[35] Resource effective utilization of resources and
Utilization achieves better load balancing among
the server
SLA based resource scheduling Cost, CloudSim Proposed solution provides the
for big data analytics as a Efficiency efficiency of the algorithm in SLA
service [36] guarantee, profit enhancement, and
cost saving Cloud
Self- governing SLA Cost, CloudSim Simulation result with extra CPU
management with resource SLA violation power of 100 MIPS have shown better
conciliation and allocation [37] rate, results the average rate of SLA
Energy efficiency violation is reduced to 10.5%, ROI is Cloud
decreased to 0.68%
Automatic service selection for Service Ranking JavaBase This approach selects best plausible set
multi Cloud environment while Simolator of services satisfying SLA parameters.
adhering to SLA claimed by It helps in maintain SLA claims of the
Saas providers [38] Saas providers

Adaptive Schedular based on SLA violation Hadoop The analytical study in Hadoop have
negotiation [39] rate delivered better resource distribution,
priority basis allocation, availability.

In [28], authors proposing SLA and cost-aware resource provisioning and task programming approach tailored for giant information
applications within the Cloud. Current approaches assume that information is pre-stored in cluster nodes before preparation of huge
information applications. additionally, their focus is only on task programming, and not virtual machine provisioning. In [29],
authors planned SLA-based involuntary resource management technique sensible through antlion optimisation algorithmic program
to maximise the resource utilization supported SLA and QoS satisfaction. The execution time, value and SLA violation rate,
objective functions computed for this framework and compare with two existing frameworks. The framework is implements in

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1221
© 2020 February 2020, Volume 7, Issue 2 www.jetir.org (ISSN-2349-5162)

CloudSim toolkit and also the results recorded the utmost performance. The experimental results make sure that value, execution
time, and resource value area unit increasing whereas SLA violation rate is increasing. In [30], authors extend SLA specification to
deal with the specificity of federation and its constraints and additionally, planned an observation model that handles the quality of
managing a Multi-level observation and planned an answer to mitigate the cascading impact thanks to SLAs observation.
observation theme has the potential of with efficiency reportage the supply of performance violations, and its propagation to all or
any dependent Cloud services. Comparison of various SLA based Resource scheduling Techniques is presented in Table3.

3. CONCLUSION
Resource scheduling forever remained associate degree active space of analysis thanks to world-wide uncontrolled growth of
datacentres to cope up with the growing demands of Cloud infrastructure. supported the literature survey, the challenges exhibit by
the cloud setting itself in terms of high-octane energy consumption of information centres, shopper satisfaction, supplier profit etc.
area unit known. moreover, an essential analysis of the present on-hand Cloud resource programming techniques on the idea of
chosen parameters from the literature is administrated. With a belief, that associate degree up-to-date review of the resource
programming literature conferred during this paper can for certain facilitate the researchers and developers in choosing the foremost
applicable techniques to manage resources in Cloud setting beneath the given constraints.

REFERENCES
1. S. Singh, I. Chana. A survey on resource scheduling in Cloud Computing: Issues andChallenges. J Grid ComputingSpringer Science+Business
Media Dordrecht. 2016, February, 217-264.
2. W. A. Elkhalik, A. Salah, I. El-Henawy. A survey on Cloud Computing scheduling Algorithms. In International journal of engineering trends
and technology (IJETT). 2018, June, 65-70.
3. Y. Demchenko, J. H. D. Van, V. Yako-Venko, C. De Laat, M. Ghijsen, M. Cristea. On-demand provisioning of Cloud and Grid based
infrastructure services for collaborative projects and groups. In Collaboration technologies and systems (CTS), International Conference, IEEE.
2011, May, 134-142.
4. R.Buyya, S.C. Yeo, S. Venugopal, J. Broberg& I. Brandic. Cloud Computing and emerging IT platforms: Vision, hype and reality for
delivering Computing as the 5th utility. Future generation Computing system. 2009, June, 599-616.
5. H. Mehta, V. K. Prasad, Dr. M. Bhavsar. Efficient resource scheduling in Cloud Computing. In International journal of advanced research in
computer science. 2017, April, 809-815.
6. B.K. Dewanagan, A. Agarwal, M. Venkatadri, A. Pasricha. Resource scheduling in Cloud: A comparative study. In International journal of
computer science and engineering (JCSE). 2018, August, 168-173.
7. S. Garg, K. Govil, B. Singh. Cost based task scheduling algorithm in Cloud Computing. In 3rd International conference on system modeling&
advancement in research trends (SMART). 2014, 411-414.
8. S. Selvarani, Dr. G. S. Sadhasivam.Improved cost-based algorithm for task scheduling in Cloud Computing in IEEE. 2010.
9. A. A. Nasar, N. A. El-Bahnasawy, G. Attiya, A. El-Sayed. Cost effective algorithm for workflow scheduling in Cloud Computing under
deadline constraint. In Arabian journal for science and engineering. 2018, December.
10. Y. Chawla, N.Bhonsle. Dynamically optimized cost-based task scheduling in Cloud Computing. In International journal of engineering trends
& technology in computer science (IJETTCS). 2013, June, 38-42.
11. D. I. G. Amalarethinam, T. L. A. Beena. Customer facilitated cost-basedscheduling (CFCSC) in Cloud. In International conference on
information and communication technologies (ICICT). 2014, 660-667.
12. C. Liu, C. Zou Pei WU. A task scheduling algorithm based on genetic algorithm and Ant
Colony optimization in Cloud Computing. In 13th International symposium on distributed Computing and applications to business,
engineering and science, IEEE. 2014, December, 68-72.
13. D. Jain, Dr. A. S. Goutam. Credit based scheduling using cost in Cloud Computing. In International journal of innovative research in computer
and communication engineering. 2017, May, 10422-10426.
14. M. A. Alwarafi, A. Dhari, A. A. Al-Hashmi, B. Darem. Cost aware task scheduling in Cloud Computing environment. In I. J. computer
network and information security. 2017, May, 52-59.
15. S. Sharma, Dr. S. Tyagi. Cost based task scheduling in Cloud Computing. In International research journal of engineering and technology
(IRJET). 2017, July, 694-699.

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1222
© 2020 February 2020, Volume 7, Issue 2 www.jetir.org (ISSN-2349-5162)

16. S. Saxena, Dr. R. K. Mishra, Dr. M. Aggarwal. A comparative study on scheduling algorithms in Cloud Computing. In International journal of
advanced research in computer engineering (IJARCET). 2018, January, 19-24.
17. M. A. Rodriguez, R. Buyya. Deadline based resource provisioning and scheduling algorithm for scientific workflows on Clouds. Cloud
Computing, IEEE Transactions on. 2014, April, 222-235.
18. M. N. Faruk, Dr. D. Sivakumar. Multi-layer QoS based task scheduling algorithm for Cloud environments. In 4th national conference on
advanced computing, applications & technologies. 2014, May, 1-7.
19. S. John, M. Mohamed. A network performance aware QoS based workflow scheduling for Grid services. In International Arab journal of
information technology. 2018, September, 894-903.
20. R. Patel, H. Mer. A. survey of various QoS based task scheduling algorithm in Cloud Computing environment. In International journal of
science & technology research. 2013, November, 109-112.
21. HEXiaoshan, X. Sun, G. V. Laszewski. QoS guided min-min heuristic for grid task scheduling. In journal of computer science and technology.
2013, May, 1-16.
22. H. Li, S. Ge, Lu. Zhang. A QoS based scheduling algorithm for instance-intensive workflows in Cloud environment. In 26th Chinese control
and becision conference (CCDC) IEEE, 2014, 4094-4099.
23. S. Potlusi, K. S. Rao. Quality of Service (QoS) based task scheduling algorithms in Cloud Computing. In International journal of electrical and
computer engineering (IJECE). 2017, April, 1088-1095.
24. S. Varshney, S. Singh. A survey on resource scheduling algorithms in Cloud Computing. In International journal of applied engineering
research. 2018, November, 6839-6845.
25. S. Kaur, P. Bagga, R. Hans, H. Kaur. Quality of Service (QoS) aware workflow scheduling (WFS) in Cloud Computing: A systematic review.
In Arabian journal for science and engineering. 2018, November, 2867-2897.
26. X. Shao, Z. Xie, Y. Xin, J. Yang. A deadline constrained scheduling algorithm for Cloud Computing system based on the driver of dynamic
essential path in journal. pone.0213234. 2019, March, 1-26., ICC. Procedia computer science.
27. M. Abdullah, M. Othman. Cost based multi-QoS job scheduling using divisible load theory in Cloud Computing. In international conference on
computational science. 2013, 928-935.
28. M. Alrokayan, A. V. Dostjerdi, R. K. Buyya. SLA-aware provisioning and scheduling of Cloud resources for big data analytics. Available at:
https://github.com/Cloudslab/CloudSimEx/tree/Master/Cloudsimex-mapreduce.
29. B. K. Dewangan, A. Agarwal, M. Venkatadri, A. Pasricha. SLA based automatic Cloud resource management framework by antlion
optimization algorithm. In International journal of innovative technology and exploring engineering (IJITEE). 2019, February, 119-123.
30. A. A. Falasi, M. A. Serhani, R. Dssouli. A model for multi-levels SLA monitoring in federated Cloud environment. In IEEE 10thinternational
conference on Ubiquitours intelligence & Computing and 10th international conference on autonomic & trusted Computing. 2013, 363-370.
31. V. C. Emeakaroha, I. Brandic, M. Maurer, I. Breskovic. SLA-aware application deployment and resource allocation in Clouds. In 35th IEEE
annual computer software and applications conferences workshops. 2011, 298-303.
32. L. Wu, S. K. Garg, R. K. Buyya. SLA based resource allocation for software-as-a-service provider (Saas) in Cloud Computing environments.
In 11th IEEE/ACM international symposium on Cluster, Cloud and Grid Computing. 2011, 195-204.
33. L. Wu, S. K. Garg, R. K. Buyya. SLA based admission control for a software-as-a-service provider in Cloud Computing environments. In
journals of computer and system sciences. 2012, December, 1280-1299.
34. L. Wu, S. K. Garg, S. Versteeg, R. K. Buyya. SLA based resource provisioning for hosted software-as-a-service applications in Cloud
Computing environments. In IEEE Transactions on services Computing
35. B. S. Rajeshwari, Dr. M. Dakshayini. Optimized service level agreement (SLA) based workload balancing strategy for Cloud environment. In
IEEE international advance Computing conference (IACC). 2015, 160-165.
36. Y. Zhao, R. N. Calheiros, G. Gange, K.Ramamohanarao, R. K. Buyya. SLA based resource scheduling for big data analytics as a service in
Cloud Computing environments. In 44th international conference on parallel processing. 2015, 510-519.
37. R. Anita, Dr. C. V. Raj. A comprehensive survey on SLA compliant energy aware resource allocation in Cloud datacentres. In international
journal of engineering research in management & technology. 2017, June, 335-349.
38. S. Farokhi, F. Jrad, I. Brandic, A. Streit. A HS4MC-Hierarchical SLA based service selection for multi Cloud environments. In: CLOSER
2014, 722-734.
39. D. Nayak, V. S. Martha, D. Threm, S. Ramaswamy, S. Prince, G. Fatimberger. Adaptive scheduling in the Cloud-SLA for Hadoop job
scheduling. In science and information conference (SAI), IEEE. 2015, July, 832-837.

JETIR2002173 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1223