A cloud computing scheduling and its evolutionary approaches

Indonesian Journal of Electrical Engineering and Computer Science
Vol. 21, No. 1, January 2021, pp. 489~496
ISSN: 2502-4752, DOI: 10.11591/ijeecs.v21.i1.pp489-496  489
Journal homepage: http://ijeecs.iaescore.com
A cloud computing scheduling and its evolutionary approaches
Ahmed Subhi Abdalkafor1
, Alaa Abdalqahar Jihad2
, Emad Tariq Allawi3
1
Career Development Center, University Of Anbar, Anbar, Iraq
2
Computer center, University Of Anbar, Anbar, Iraq
3
Sunni Endowment, Anbar, Iraq
Article Info ABSTRACT
Article history:
Received Nov 1, 2019
Revised May 7, 2020
Accepted Jul 12, 2020
Despite the increasing use of cloud computing technology because it offers
unique features to serve its customers perfectly, exploiting the full potential
is very difficult due to the many problems and challenges. Therefore,
scheduling resources are one of these challenges. Researchers are still finding
it difficult to determine which of the scheduling algorithms are appropriate
and effective and that helps increases the performance of the system to
accomplish these tasks. This paper provides a broad and detailed examination
of resource scheduling algorithms in the environment of a cloud computing
environment and highlights the advantages and disadvantages of some
algorithms to help researchers in selecting the best algorithms to schedule a
particular workload to get a satisfy a quality of service, guarantee good
utilization of the cloud resources also minimizing the make-span.
Keywords:
Cloud computing
Job scheduling
Load balancing
Task scheduling
This is an open access article under the CC BY-SA license.
Corresponding Author:
Ahmed Subhi Abdalkafor
Career Development Center
University Of Anbar, Anbar, Iraq
Email: ahmed.abdalkafor@uoanbar.edu.iq
1. INTRODUCTION
The emergence of cloud computing has expanded dramatically and is becoming increasingly
attractive as it provides services over the Internet and reduces user requirements for future planning [1, 2].
The cloud has become mutually beneficial to both the service provider and the consumers. The cloud
environment has many advantages that have made the world move strongly towards it. The cloud meets all
the business requirements as well as improving the efficiency of managing resources through scheduling by
algorithms and obtaining low cost and energy. However, the cloud environment has many challenges and
difficulties, the system bugs and the power outages adversely affect the continuity of cloud computing
working, Followed are some common examples of such problems: In the year 2007 Rackspace company
stopped the service for 3 hours due to power outages from the company center. In 2008, the service of
Google App Engine company was stopped for 6 hour due to errors in the operating system also in the year
2009 the company of Microsoft Azure discontinued 22 hours for updating an operating system [3].
In January 2018, an examination administered by the right scale company, 27% of the respondents
showed the shortage of resources or experience in this environment is a risk of cloud choosing for their works
[4]. Figure 1 shows the cloud computing challenges in worldwide from 2018. The scheduling is an important
and sensitive issue and has become an attractive topic in recent decades, in cloud computing environments
that need to be carefully studied to make it easier for researchers to assign efficiently tasks to appropriate
resources. Where it was considered as an NP-hard (nondeterministic polynomial time) problem due to large
solution space and hence, it needs a big-time to get a better way solution [5], so scheduling methods are used
to reach a high-quality service in a cloud environment. Therefore, you must meet the scheduling service

 ISSN: 2502-4752
Indonesian J Elec Eng & Comp Sci, Vol. 21, No. 1, January 2021 : 489 - 496
490
requirements of different users. There will be many requests for service on the cloud platform at the same
time. Therefore scheduling must be able to schedule multiple workflows [6].
Figure 1. Cloud computing challenges from 2018
This paper aims to provide comprehensive and extensive an examination of scheduling algorithms
in the environments of cloud computing where the highlight was in the key concepts of cloud scheduling,
state-of-the-art implementation and architectural principles also investigated in the types of scheduling
algorithms and a better understand the advantages and disadvantages of these algorithms.
The Scheduling is an NP-complete problem, by looking at a lot of problems such as keeping cost
and energy down and reducing waiting time, therefore, many research methods have been proposed by many
researchers. Despite the abundance of these studies on this hot topic, but the door is still open behind the
researchers because most they reached are not perfect and not close to the optimal solution [7]. Below are
some recent and important studies that will be used by researchers when researching in this field. Gibet T.
and El Amrani [8] give a review of cloud computing infrastructure, discuss and evaluate its importance, and
compute resources scheduling algorithms. Athokpam Bikramjit et.al [9] presented a comparative study and
analyzed the several algorithms of scheduling and notes that the current algorithms provide big throughput
and effective cost however, lack availability and reliability. S. Lakshmanan [10] presented a comparative
analysis of ABC, FIFS, RR, SJF, Priority tasks, and merits, demerits scheduling algorithms in the cloud
platform. These algorithms mainly focus on summarizing algorithm parameters, the job executes
environment, types of job, it is used to decrease the make-span time, waiting for time and complexity of the
code. Shameer A.P and A.C Subhajini [11] compared among three algorithms, round-robin (RR), Shortest
job first (SJF) and first in first out (FIFO). Mohammad Masdari et.al [12] they offered the particle swarm
optimization (PSO) algorithm based scheduling in an environment of a cloud computing, implemented a
classification via the algorithm type (PSO), also presented how this algorithm was developed and combined
to solve the problem of the task-workflow. Finally, a comprehensive comparison was provided via different
objectives of scheduling like execution time, load balancing, and the costs.
Maria A. and Rajkumar B. [13] provide a study of the algorithms for scheduling scientific
workflows. Focus on technologies considering applications formed as directed acyclic graph and the resource
form given via providers of the public cloud. The classification is performed via a large study of being
algorithms that focus on special features such as storage, network access, and VMs. Kamalpreet K. and
Kanwalvir S. [14] they compared a variety of scheduling algorithms in tabular format various parameter
making use of cloud computing environment in most of the algorithms. Simsy Xavier et.al [15] they have
scanned several scheduling of workflow algorithms found in the environment of cloud then compared with
different restrictions. Priya R. and Avinash P. [16] offers a survey of many scheduling of workflow
algorithms kinds cloud computing, and it study compares several kinds of scheduling algorithms of a
workflow. They coordinate problem of a scheduling via the environment of cloud and present a cloud
scheduling hierarchy, principally divided to system and user levels.

Indonesian J Elec Eng & Comp Sci ISSN: 2502-4752 
A cloud computing scheduling and its evolutionary approaches (Ahmed Subhi Abdalkafor)
491
1.2. Scheduling algorithm in cloud computing
Kalka and Mohit [17] they adjusted the HEFT algorithm that inefficiently distributes the workload
between the processor, reduces application rendering time based on their order and assignment of task with
the processor. They concluded that the proposed algorithm decreases task time and load balance problems
compared to the HEFT and CPOP algorithms. Ursa Sayeed et.al [18] proposed a hybrid FFA-PSO based
AMTS method to reduce total energy consumption, total cost, implementation time, and increased resource
operation. The result of the trial showed that the proposed FFA-PSO based AMTS works proficiently in a
cloud computing in minimum implementation time, energy consumption and cost. J. KOK et.al [19]
introduced by a new mechanism called modified max-min algorithm (MMax-Min), boosted by the Max-Min
Algorithm. The suggested algorithm explores a cloud with maximum completion time and minimum
completion time and assigns any of the clouds to implement according to specifications. They compared their
proposal with standard max-min and round robin algorithms.
Mehdi Sookhak et.al [20] introduced an effective far data way audit structure to validate the integrity of
the data kept via environment of cloud. They applied algebraic property data blocks that are outsourced to check
file integrity remotely and decrease computational costs in their server and client from that environment. They
planned structure of a new data that separates then subjugates the table for supportive effective data updating the
bears minimal computing plus auditor of communications expenses. Arabi E. et.al [21] proposed the use of
modified ant colony improvement in load balancing. This scheme enhances the scheduling of cloud jobs for load
balancing. Amit A. and Saloni J. [22] the GPA focuses mainly on reducing mission time, this study virtual
machines and tasks are ordered based on many instructions for each second. Results in the study were compared
with tow algorithms first, Round Robin algorithm, and second first com first services, concluded, the GPA operates
more useful than Round Robin and FCFS. M. Abu Sharkh et.al [23] introduce some internal and external factors
affecting the design of DC RA models. Models operate based on a trusted social graph, and these models differ
when compared to distributed cloud computing, grid, and classical computing models.
Ruay-Shiung Chang et.al [24] introduced the adaptive assessment function (ASJS) scheduling
algorithm for the network environment. It proposes to shorten the end time, thus improving system
productivity. This algorithm measures the computing power and transmission power for each cluster in the
network system. Further, it measures the mass score for each block that will be adjusted by implementing
local and global updates. Tasquia Mizan et.al [25] they introduced an improved the algorithm for tasking
scheduling via a bee and a greedy algorithms for acquiring perfect service on hybrid cloud environment.
Algorithms of Bee life are household to job scheduling with the greedy manner. In adjusted task scheduling,
queue tasks are handled with a non-proactive priority queue. It enters the algorithm of BLA and greedy
manner to acquire the perfect result. Machine size can be decreased with the hybrid method. Jiayin Li et.al
[26] they proposed a scheduling algorithm based on the proposed comments for preventive functions in the
cloud. The MinMin algorithm is used for scheduling jobs.
2. TYPES OF SCHEDULING
Generally, Scheduling algorithms are divided into two main parts task scheduling and job
scheduling.
2.1. Task scheduling
Scheduling tasks are considered to be the most effective and efficient techniques for selecting the
best resources in an efficient manner, a task scheduling classified into workflow, real-time scheduling, static
and dynamic cloud service scheduling, and load balancing schedules.
a) Workflow: it is a manner that manages and maps the task execution on the assigned resources. It assigns
appropriate resources to task of workflow in which the execution of the tasks can be finished to meet
objective capacities needed by users. The workflow consists of from best-effort based scheduling algorithms
and quality of service (QoS), the first one derived from a meta-heuristics based or heuristics-based approach.
The second one means several applications of the workflow need some assurance of the quality of service.
Therefore, these applications need to schedule so that they can analyze user service requirements.
b) Real-time scheduling: in general, the scheduling algorithm defines how tasks are handled by the
scheduling system. In the scheduling system algorithm in real-time each description of the task and the
deadline and the identifier are set and completed As defined according to scheduling algorithms,
Scheduling algorithms must prevent concurrent way to devices and shared resources. The problem of
scheduling of the real-time system is to set a schedule to perform tasks so that its timing constraints are
met. In simpler real-time systems where tasks and execution times are known to all may not even be a
scheduler simply perform a task (or give in to) the next. In the most complex real-time system with a
larger (but static) number, may be possible to work a fixed schedule based on the required run tasks and

 ISSN: 2502-4752
492
the time expected to be completed for each list where ensures the implementation of all tasks in a timely
manner. But for many systems in real-time the workload changes from moment to moment depending
on external events this requires dynamic scheduling. The system is said to be un-schedulable when tasks
cannot meet deadlines, the task can be classified as a periodic or non-periodic process [27].
c) Static and dynamic cloud service scheduling: there are two scheduling tasks in the cloud; Schedule
static tasks and schedule dynamic tasks. Static scheduling allows you to fetch the required data and
connect all the scheduling parameters initially scheduling a static schedule imposes a lower load at run-
time. For dynamic scheduling, the task/task modules information is unknown. Therefore, the task of
execution time may not be known and tasks are allocated quickly. The advantage of a dynamic static
schedule that the system does not have to possess the run-time conduct of the request previously
running it. An additional the dynamic scheduler is divided into a couple of types batch mode or
connected mode. In first one, the tasks are queued, grouped in a group, and then scheduling after time
interval. In second, the tasks are scheduled after they access the system [28, 29].
d) Load balancing: it is one of the best significant concepts in distributed environments. A Cloud
computing is also one of the better platforms that availability data storage at the lowest cost and can be
accessed at any time online. The basic feature of the load balancer is to improve resource utilization,
maximize productivity, reduce response time, and avert overcharging of resources [30]. The aim of load
balancing to the high level of user satisfaction and the use of the proportion of resources by ensuring a
reasonable and well done for each resource allocation of computing resources. The load balancing
application reduces the opportunity for interruptions that can simultaneously affect the services of cloud
systems. If a single system interruption is affected, the load balancer is capable of switching to another
available resource. Additionally, confirms that every processor or each node does almost equal work at
any time. There are various types of load balancing algorithms available, which can be categorized
mainly into two groups, static algorithms and dynamic algorithms.
2.2. Job scheduling algorithms
At present, cloud computing is used widely. hence, several challenges in the use of cloud computing.
The resource management challenge and one of the resource-related administration issues is the scheduling of
tasks [31]. Scheduling work is to achieve excellent performance computing and the most useful productivity
system. The principal task of scheduling algorithms in the cloud reduces the total time to complete the tasks by
obtaining the most suitable resources that will be customized to the task. The environment is a various system
and the activity of each processor varies rapidly, and the priority of the job is an important issue in scheduling
for some of the functions services must be earlier than those other functions cannot be kept for long in this
system. You should take the appropriate scheduling functions into account for the priority functions algorithm
[30]. In general, the job Scheduling algorithms is consists of two main parts, the first parts are Batch-mode-
heuristic-scheduling-algorithms which consists of several algorithms such as round robin algorithm,
randomized, max-min scheduling algorithm min–min algorithm, shortest job first algorithm, and others and
online-mode-heuristic-algorithms in the second part that mean when a task is arrived directly mapped onto a
host so this technique is more appropriate because the heterogeneous and speed of each processor changes fast
in this environment. The appropriate example for this part is the most fit task scheduling [32].
a) The round robin algorithm: specially designed for time-sharing systems. The load is distributed equally to all
resources in circular order. Run a slide function (sometimes called a quantum scheduler). The first operation of
the queue is selected from the CPU scheduler and then sets the timer to Cut off after quantum one the finally
sending the process. Do this repeatedly until the jobs are completed. If the job does not fulfill in a single custom
quantity, revert to the queue and wait for the next round. The Jobs are performed in a consecutive cycle, and a
necessity to wait for the earlier job to get full. Consequently, there is no famine problem [33].
b) Randomized algorithm: is the simplest algorithm available that uses a degree of randomness as part of
its logic? Two advantages of random distribution have simplicity and speed; this effectively reduces the
complexity of the account. The algorithm typically uses a random bit uniformly as a helper input to
direct its behavior. The performance of the algorithm will be a random variable defined by random bits,
thus either time management, or output (or both) random variables.
c) Max-min scheduling algorithm: it chooses big tasks to be implemented first. Here, we are given the
greater priority tasks on the smaller tasks, if we have one long job, Max-Min can perform several short
tasks simultaneously while Implementation a large one. Continue to work in descending order. Which
again repeats this procedure for all available functions [34-36].
d) Min-min algorithm: this algorithm determines the less expected time of tasks to be executed. This algorithm
passes through two stages, the first is to search for the less time expected to accomplish all the tasks. Then the
second step is to assign the specific task that was performed in the first step depending on the overall less

493
expected completion time to the correct resource [37, 38]. Regardless of the advantages that exist in this
algorithm of obtaining the least time where there is starvation for some of the tasks when executed.
e) Shortest job first algorithm: there are many algorithms available to schedule the CPU including the first
shorter function (SJF). A high priority is allocated to posts with minimum execution time and put first
in the queue while the lowest priority is allocated to the task with maximum implementation time,
always select the shortest function (any job takes less time) available. When the CPU is available [32].
Table 1 illustrated the advantage and disadvantage of algorithms that which were mentioned and
Figure 2 shows the types of scheduling algorithms.
On the other hand, the pattern recognition is an important and fertile topic as it has entered many
applications such as recognizing the different languages from Arabic, English, and other languages of the
world [39], so, many databases have been built to implement and test these applications [40-44], as result, the
recognition has entered a large area in many applications in the cloud environment such as Emotion of
human [45] and activity recognition [46], and face recognition [47-49].
Table 1. Pros and cons of scheduling algorithms
Name of Algorithms Advantage Disadvantage
Round Robin
Algorithm
Easier for implementing, and it is free from
famine (which means that the process does
not have the resources to complete it
permanently or after a long time. and tasks
processing without priority
The average waiting time is worse than FCFS,
and then the performance level depends on the
slice.
Randomized
Algorithm
Simplicity, Performance
-A run-time analysis or a suitable solution is
often complex.
-Improbable for Producing random number.
The result depends a large part on the quality of
the random numbers, so it needs to rely on false
random numbers
Max-Min scheduling
algorithm
Performance level depends on tasks if the
task is longer.
Priority depends on less important. They are
positive on the basis of a big task more than a
small task
Min-Min Algorithm Obtaining least time Starvation for some of the tasks when executed
Shortest Job First
Algorithm
Make waiting time for operations less
executable.
-Difficulty predicting CPU time and
implementation.
-In the event that the waiting period is
shortened, as long-term operations may wait for
a long time and may not be carried out, so they
have a problem, (starvation of large process)
famine of long-term processes.
Figure 2. The types of scheduling algorithms

 ISSN: 2502-4752
494
3. CONCLUSION
The scheduling is one of the most important matters which need to be focused to obtain efficient
performance in cloud computing. In this research, we conducted a broad, comprehensive, and intensive
examination of the scheduling of the algorithms as well as focus on the most important studies in this field.
We also discussed the advantages and disadvantages of some scheduling algorithms to be selecting the best
algorithms by researchers to achieve utilization of the resource, completion cost and time according to the
comprehensive examination of these algorithms and also the pros and cons of these algorithms.
REFERENCES
[1] Isa, A. W. M, et al., “Cloud computing adoption reference model,” Indonesian Journal of Electrical Engineering
and Computer Science, vol. 16, no. 1, pp. 395-400, October 2019.
[2] Olanrewaju, R. F., Islam, T., Khalifa, O. O., & Fajingbesi, F. E., “Data in Transit Validation for Cloud Computing
Using Cloud-Based Algorithm Detection of Injected Objects,” Indonesian Journal of Electrical Engineering and
Computer Science, vol. 10, no. 1, pp. 348-353, 2018.
[3] Qian, L., Luo, Z., Du, Y., & Guo, L., “Cloud computing: An overview,” In IEEE International Conference on
Cloud Computing, pp. 626-631, 2009.
[4] https://www.statista.com/statistics/511283/worldwide-survey-cloud-computing-risks/ accessed at 24/5/2019.
[5] Chang, Ruay-Shiung, Chih-Yuan Lin, and Chun-Fu Lin, “An adaptive scoring job scheduling algorithm for grid
computing,” Information Sciences, vol. 207, pp. 79-89, 2012.
[6] Zhou, Y., & Huang, X., “Scheduling workflow in cloud computing based on ant colony optimization algorithm,” In
Business Intelligence and Financial Engineering (BIFE), 2013 Sixth International Conference on IEEE, pp. 57-61, 2013.
[7] Choudhary, A., Gupta, I., Singh, V. & Jana, P. K., “A GSA based hybrid algorithm for bi-objective workflow
scheduling in cloud computing,” Future Generation Computer Systems, vol. 83, pp. 14-26, 2018.
[8] Gibet Tani Hicham, El Amrani Chaker, “Optimization of Task Scheduling Algorithms for Cloud Computing: A
Review,” SCAMS-SH'17, October 2017.
[9] Athokpam Bikramjit Singh, Sathyendra Bhat J., Ragesh Raju, Rio D’Souza, “A Comparative Study of Various
Scheduling Algorithms in Cloud Computing,” American Journal of Intelligent Systems, vol. 7, no. 3, pp. 68-72, 2017.
[10] S. Lakshmanan, “A Survey on Heterogeneous Resource Scheduling Algorithm in Cloud Computing,” IJSRSET,
vol. 3, no. 8, pp. 962-966, 2017.
[11] Shameer A. P., “Study on Different Scheduling Algorithm for Cloud Computing,” International Journal of
Advanced Research in Computer Science and Software Engineering, volume 6, issue 5, May 2016.
[12] M. Masdari, F. Salehi, M. Jalali, and M. Bidaki, “A Survey of PSO-Based Scheduling Algorithms in Cloud
Computing,” J. Netw. Syst. Manag., vol. 25, no. 1, pp. 122–158, Jan. 2016.
[13] Maria A. Rodriguez and Rajkumar Buyya, A Taxonomy and Survey on Scheduling Algorithms for Scientific
Workflows in IaaS Cloud Computing Environments, Concurrency and Computation: Practice and Experience
(CCPE), volume 29, no. 8, pp. 1-23, ISSN: 1532-0626, Wiley Press, New York, USA, April 25, 2017
[14] Kamalpreet Kaur, Kanwalvir Singh Dhindsa, “Comparative Study of Tools and Scheduling Algorithms of Cloud
Computing,” International Conference on Communication, Information and Computing Technology, 2015.
[15] Simsy Xavier, S.P.Jeno Lovesum, “A Survey of Various Workflow Scheduling Algorithms in Cloud Environment,”
International Journal of Scientific and Research Publications, vol. 3, no. 2, 2013.
[16] Priya R. Lodha and Avinash P. Wadhe, “Study of Different Types of Workflow Scheduling Algorithm in Cloud
Computing,” IJARCSEE, vol. 2, no. 4, April 2013.
[17] Kalka Dubey, Mohit Kumar, S.C. Sharma, “Modified HEFT Algorithm for Task Scheduling in Cloud
Environment,” Procedia Computer Science, vol. 125, pp. 725-732, 2018.
[18] Ursa Sayeed, Arshad Shareef, T Sunil, “An Optimal Task Scheduling Strategy in Cloud Computing Environment
Utilizing FFA-PSO Algorithms,” International Journal of Advance Research in Science & Engineering, 2017.
[19] J. Kok Konjaang, Fahrul Hakim Ayob, Abdullah Muhammed, “An Optimized Max-Min Scheduling Algorithm in
Cloud Computing,” Journal of Theoretical and Applied Information Technology, vol. 95, no. 9, 2017.
[20] Mehdi Sookhak, Abdullah Gani, Muhammad Khurram Khan, Rajkumar Buyya, “Dynamic remote data auditing for
securing big data storage in cloud computing,” Information Scienses, 2015.
[21] Arabi E. Keshk, Ashraf B. El-Sisi, Medhat A. Tawfeek, “Cloud Task Scheduling for Load Balancing based on
Intelligent Strategy,” I. J. Intelligent Systems and Applications, vol. 6, no. 5, pp. 25-36, 2014.
[22] Amit Agarwal, Saloni Jain, “Efficient Optimal Algorithm of Task Scheduling in Cloud Computing Environment,”
International Journal of Computer Trends and Technology, vol. 9, pp. 344-349, 2014.
[23] M. Abu Sharkh, M. Jammal, A. Shami and A. Ouda, “Resource allocation in a network-based cloud computing
environment: design challenges,” in IEEE Communications Magazine, vol. 51, no. 11, pp. 46-52, November 2013.
doi: 10.1109/MCOM.2013.6658651.
[24] Chang, Ruay-Shiung, Chih-Yuan Lin, and Chun-Fu Lin, “An adaptive scoring job scheduling algorithm for grid
computing,” Information Sciences, vol. 207, pp. 79-89, 2012.
[25] Mizan, T., Masud, S. M. R. A., Latip, R., “Modified Bees Life Algorithm for Job Scheduling in Hybrid Cloud,”
International Journal of Engineering and Technology, vol. 2, no. 6, pp. 974-979, June, 2012.
[26] Li, M. Qiu, J. Niu, W. Gao, Z. Zong and X. Qin, “Feedback Dynamic Algorithms for Preemptable Job Scheduling
in Cloud Systems," 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent
Technology, Toronto, ON, pp. 561-564, 2010. doi: 10.1109/WI-IAT.2010.30.

495
[27] S. Liu, G. Quan and S. Ren, “On-Line Scheduling of Real-Time Services for Cloud Computing,” 2010 6th World
Congress on Services, Miami, FL., pp. 459-464, 2010. doi: 10.1109/SERVICES.2010.109.
[28] Akilandeswari, P., & Srimathi, H., “Survey and analysis on Task scheduling in Cloud environment,” Indian
Journal of Science and Technology, vol. 9, no. 37, pp. 1-6, 2016.
[29] Goel, H., & Chamoli, N., “Job Scheduling Algorithms in Cloud Computing: A Survey,” International Journal of
Computer Applications, vol. 95, no. 23, pp. 19-22, 2014.
[31] Hamad, S. A., & Omara, F. A., “Genetic-based task scheduling algorithm in cloud computing environment.
International Journal of Advanced Computer Science and Applications, vol. 7, no. 4, pp. 550-556, 2016.
[32] Pandaba Pradhan, Prafulla Ku. Behera, B. N. B. Ray, “Modified Round Robin Algorithm for Resource Allocation
in Cloud Computing,” Procedia Computer Science, vol. 85, pp. 878-890, 2016.
[33] Abdalkafor, A. S., & Alheeti, K. M. A., “A hybrid approach for scheduling applications in cloud computing
environment,” International Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 4, 2019.
[34] Rawshdeh, D. Zanoon, “STASR A New Task Scheduling Algorithm For Cloud Environment,” Network Protocols
and Algorithms, vol. 7, no. 2, pp. 81-95, 2015.
[35] El Amrani, C., & Gibet Tani, H., “Smarter Round Robin Scheduling Algorithm for Cloud Computing and Big
Data,” Journal of Data Mining & Digital Humanities, vol. 7, no. 2, pp. 1943-3581, 2018.
[37] Kaur, K., Kaur, N., & Kaur, K., “A Novel Context and Load-Aware Family Genetic Algorithm Based Task
Scheduling in Cloud Computing,” In Data Engineering and Intelligent Computing, Springer, pp. 521-531, 2017.
[38] Manasrah, A. M., & Ba Ali, H., “Workflow scheduling using hybrid GA-PSO algorithm in cloud computing,”
Wireless Communications and Mobile Computing, vol. 3, pp. 1-16, 2018.
[39] S. Abdalkafor, “Designing Offline Arabic Handwritten Isolated Character Recognition System using Artificial
Neural Network Approach,” International Journal Of Technology, vol. 8, pp. 528-538, January 2017.
[40] S. Abdalkafor, “DFRS-database for fingerprint recognition system using Ink-On-Paper technique,” Journal of
Engineering and Applied Sciences, vol. 13, no. 17, pp. 7401-7407.
[41] A. S. Abdalkafor, E. T. Allawi, K. W. Al-Ani and A. M. Nassar, “A Novel Database for Arabic Handwritten
Recognition (NDAHR) System,” 2019 2nd International Conference on Computer Applications & Information
Security (ICCAIS), Riyadh, Saudi Arabia, pp. 1-6, 2019. doi: 10.1109/CAIS.2019.8769580.
[42] Abdalkafor, A. S., “Survey for Databases On Arabic Off-line Handwritten Characters Recognition System,” In 2018
1st International Conference on Computer Applications & Information Security (ICCAIS), pp. 1-6, April 2018,
[43] Abdalkafor, A. S., Awad, W. K., & Alheeti, K. M. A., “A novel comprehensive database for Arabic and English
off-line handwritten digits recognition,” Indonesian Journal of Electrical Engineering and Computer Science,
vol. 20, no. 1, pp. 145-149, 2020.
[44] Jihad, A. A., & Abdalkafor, A. S. (2019). A Framework for Sentiment Analysis in Arabic
Text. Indonesian Journal of Electrical Engineering and Computer Science, 16(3), 1482-1489.
[45] Lu, H., Wang, M., & Sangaiah, A. K., “Human Emotion Recognition Using an EEG Cloud Computing Platform,”
Mobile Networks and Applications, vol. 25, no. 3, pp. 1023-1032, 2020.
[46] Islam, N., Faheem, Y., Din, I. U., Talha, M., Guizani, M., & Khalil, M., “A blockchain-based fog computing
framework for activity recognition as an application to e-Healthcare services,” Future Generation Computer
Systems, vol. 100, pp. 569-578, 2019.
[47] T. Soyata, R. Muraleedharan, C. Funai, M. Kwon and W. Heinzelman, “Cloud-Vision: Real-time face recognition
using a mobile-cloudlet-cloud acceleration architecture,” 2012 IEEE Symposium on Computers and
Communications (ISCC), Cappadocia, pp. 000059-000066, 2012. doi: 10.1109/ISCC.2012.6249269.
[48] M. Z. Khan, S. Harous, S. U. Hassan, M. U. Ghani Khan, R. Iqbal and S. Mumtaz, “Deep Unified Model For Face
Recognition Based on Convolution Neural Network and Edge Computing,” in IEEE Access, vol. 7, pp. 72622-
72633, 2019. doi: 10.1109/ACCESS.2019.2918275.
[49] Guo, S., Xiang, T., & Li, X., “Towards efficient privacy-preserving face recognition in the cloud. Signal
Processing,” vol. 164, pp. 320-328, 2019.
BIOGRAPHIES OF AUTHORS
Ahmed Subhi Abdalkafor was born in Anbar-Iraq in 1988. He received his B.Sc. from Faculty
of Computer Science at Anbar University, Iraq in 2010. The MSc. degree from Computer
Science Department in Middle East University, Jordan in 2016. His research interests are, Image
Processing, Pattern Classification, Artificial Intelligent, Wireless Sensor Neural Network, Cloud
Computing, Machine Learning and Data Mining.

 ISSN: 2502-4752
496
Alaa Abdalqahar Jihad was born in Anbar-Iraq in 1985. He received his B.Sc. from Faculty of
Computer Science at Anbar University, Iraq in 2009. The MSc. degree Faculty of Computer
Science at Anbar University, Iraq 2012. His research interests are, Data Warehouse, Data
Mining, Artificial Intelligent, Machine Learning, Cloud Computing and Natural Language
Processing
Emad Tariq Allawi was born in Anbar-Iraq in 1982. He received his B.Sc. from Faculty of
Computer Science at Almaref University, Iraq in 2006. The MSc. degree from Computer Science
Department in Middle East University, Jordan in 2016. His research interests are Data Mining,
Image Processing and cyber Security.

A cloud computing scheduling and its evolutionary approaches

More Related Content

Similar to A cloud computing scheduling and its evolutionary approaches (20)

More from nooriasukmaningtyas (20)

Recently uploaded (20)

A cloud computing scheduling and its evolutionary approaches