Content uploaded by Kamal Kumar
Author content
All content in this area was uploaded by Kamal Kumar on Jul 27, 2020
Content may be subject to copyright.
DOI: 10.4018/IJDST.2018010101
Volume 9 • Issue 1 • January-March 2018
Copyright © 2018, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
1
Jyoti Thaman, Department of Computer Science and Engineering, Maharishi Markandeshwar University, Mullana,
Ambala, India
Kamal Kumar, University of Petroleum and Energy Studies, Dehradun, India
For the last decade, cloud computing has been spreading its application base from the small enterprises
to the large, from the domestic user to the professional, from buyers to sellers and from research to
implementation. Subscribers submit their jobs or workflows for executions on clouds. Workflow
scheduling is a very important aspect in cloud computing and it imitates industrial operations,
constraints and dependencies. Several approaches such as Greedy, Heuristic, Meta-heuristic and
Hybrid have been tried to reschedule workflows. This article proposes Modified HEFT (MHEFT)
and Cluster Based Modified HEFT (C-MHEFT). MHEFT modifies the mapping of ranked tasks to
the VMs. C-MHEFT is the cluster based extension of MHEFT. The simulations were performed in
WorkflowSim and were compared with existing benchmarks in planning algorithms like HEFT and
DHEFT. The proposed schemes will help industries, enterprises to model and sequence the Industrial
process which will be faster and efficient.
Dynamic Scheduling, HEFT, Performance, Task Types, WorkflowSim
Cloud computing is driving the computing everywhere. A lot of services, applications, infrastructure
and managerial tasks have been mapped on to the cloud platform, both Public and Private. Ever
increasing impact of cloud computing requires a lot of research. It should focus to improve the
performance of clouds. This would prevent drowning of clouds and establish cloud as a long-term
reality. However, increasing pace of cloud platforms has exposed several issues related to QoS
parameters of cloud platforms.
Scheduling of tasks, resource management, network management, privacy and security etc.
should be addressed so that QoS parameters agree with clients and meet to the best possible levels.
Scheduling of tasks is one of the most important challenges as client. Many scheduling and planning
algorithms have been proposed for addressing this issue. HEFT, DHEFT, Min-Min, Max-Min, Round-
Robin, SJF etc. are some well-known proposals. This paper is a proposal of the recently researched
a Modified HEFT algorithm (MHEFT) and Cluster Based Modified HEFT (C-MHEFT). This
MHEFT algorithm is using a novel task-VM mapping based on principle of reducing the difference
between task requirements and VM’s expected performance for given set of tasks. As set of tasks
are changed, VM’s performance gets tuned as per task’s characteristics. This adds to the concept of
Volume 9 • Issue 1 • January-March 2018
2
dynamic self-configuration of VM’s performance when physical characteristics were fixed for whole
length of experimentations. CMHEFT is the extension of MHEFT which modifies the HEFT by
using a clustering approach. In this paper, workflows have been considered as representing different
task types. This proposal has been organized into several sections. Introduction section introduces
the concepts and expectations from the proposal. Related Work presents the existing related work
and identifies the gaps. The Preliminary section presents a briefing of preliminaries in the form of
HEFT planning policy. The fourth section presents proposed Scheduling Approach. The fifth presents
Modified HEFT (MHEFT) planning algorithm and Cluster Based Modified HEFT (C-MHEFT). The
sixth section presents the simulation and analysis of the scheme. Finally comes the Conclusion of
the research and future work.
Recent development and marketing of cloud based solutions have opened up scheduling of task as a
novel and interesting research domain. Several remarkable scheduling algorithms including planning
algorithms have been proposed for task scheduling in literature. This section reviews few remarkable
and citable contributions in research of scheduling of independent and dependents tasks.
Authors Chen and Deelman (2012) have proposed the extension of CloudSim for inclusion
of distributed jobs which are called workflows. The management and scheduling aspects has been
analyzed in a review of workflows application (Liu et al., 2014). A useful conclusion was drawn from
the review that single cloud model is inefficient with respect to increasing scale and complexity of
workflows. Another proposal (Zhou & Garg, 2015) evaluated the performance of various existing
workflow scheduling schemes for different workflows. This work has endorsed that dynamism may
be important parameter to keep in knowledge while evaluating any workflow scheduling proposal.
Some study (Thaman & Singh, 2016a) has proposed a Robust HEFT (RHEFT) planning algorithm
by considering a novel VM-Task mapping algorithm. Authors Thaman and Singh (2016b) have
presented a simulated performance of various dynamic scheduling schemes available in WorkflowSim.
Authors (Chopra & Singh, 2013) have proposed hybrid of HEFT with a novel concept of sub-
deadline to achieve deadline constraints. Almost all the tasks were scheduled within their deadline.
A novel mechanism called Partial Deadline Constraint (PDC) was proposed which not only achieves
a better mapping but also exploits the underlying concept of elasticity (Arabnejad & Bubendorfer,
2015). Authors Thaman and Singh (2016c) have proposed a novel taxonomy for classification of
task scheduling algorithms based on the goal oriented and constraint oriented approach. This paper
presents a highly useful current perspective of scheduling approaches. Another research (Singh et al.,
2014) has presented a comparison of various scheduling algorithms on distinct aspects like suitability,
feasibility and adaptability to cloud platform. This paper also proposed a hybrid scheduling approach
which can bring better returns to cloud service providers and ensure better quality of services. A
Genetic Algorithm based load balancing approach was presented (Dasgupta et al., 2013). Authors have
discussed and proved that dynamic nature of cloud environment might be the best addressed through
adaptive scheduling schemes. The proposal claimed that un-balanced state is inevitable whereas
system might have started well in balanced state. Another Genetic Algorithm based heuristic was
proposed (Yu & Buyya, 2006) where two objectives, namely budget and deadlines were addressed.
Optimizations were achieved by either minimizing execution times while at the same time meeting
the budget and deadline constraints posed by the subscriber. Evaluation was done using both balanced
and unbalanced workflows and results show this newly proposed approach was better in handling
complex workflow structures. Authors (Sheng & Li, 2016) have proposed a new concept named
Template Based Genetic Algorithm (TBGA) where users specify QoS constraints. Based on specified
values, TBGA computes the maximal number of tasks that could be scheduled on each machine.
These computed results are known as template. These templates are used to segregate the tasks into
multiple subsets which are to be allocated to one processor each. This allocation was made considering
13 more pages are available in the full version of this
document, which may be purchased using the "Add to Cart"
button on the product's webpage:
www.igi-global.com/article/performance-aware-planning-
algorithms-for-cloud-environments/196264?camid=4v1
This title is available in InfoSci-Computer Systems and
Software Engineering eJournal Collection, InfoSci-Journals,
InfoSci-Journal Disciplines Computer Science, Security, and
Information Technology, InfoSci-Journal Disciplines
Engineering, Natural, and Physical Science, InfoSci-Select,
InfoSci-Computer Science and IT Knowledge Solutions –
Journals. Recommend this product to your librarian:
www.igi-global.com/e-resources/library-
recommendation/?id=163
Related Content
A Congestion Controlled and Load Balanced Selection Strategy for Networks
on Chip
Ashima Arora and Neeraj Kumar Shukla (2020). International Journal of Distributed
Systems and Technologies (pp. 1-14).
www.igi-global.com/article/a-congestion-controlled-and-load-balanced-
selection-strategy-for-networks-on-chip/240772?camid=4v1a
Failure Detector of Perfect P Class for Synchronous Hierarchical Distributed
Systems
Anshul Verma and K. K. Pattanaik (2016). International Journal of Distributed
Systems and Technologies (pp. 57-74).
www.igi-global.com/article/failure-detector-of-perfect-p-class-for-
synchronous-hierarchical-distributed-systems/151579?camid=4v1a
Cost Evaluation on Building and Operating Cloud Platform
Yue-Shan Chang, Yi-Kang Lee, Tong-Ying Juang and Jing-Shyang Yen (2013).
International Journal of Grid and High Performance Computing (pp. 43-53).
www.igi-global.com/article/cost-evaluation-on-building-and-operating-cloud-
platform/78895?camid=4v1a
A Fuzzy Real Option Model to Price Grid Compute Resources
David Allenotor, Ruppa K. Thulasiram, Kenneth Chiu and Sameer Tilak (2010).
Handbook of Research on Scalable Computing Technologies (pp. 471-485).
www.igi-global.com/chapter/fuzzy-real-option-model-
price/36421?camid=4v1a