A Service Framework for Scientific Workflow Management in the Cloud

Zhao, Yong; Li, Youfu; Raicu, Ioan; Lu, Shiyong; Lin, Chia-Wen; Zhang, Yanzhe; Tian, Wenhong; Xue, Ruini

doi:10.1109/tsc.2014.2341235

Cited by 35 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First stage refers to the clustering of the task by considering the correlation of task. Second stage is runtime, the distribution and redistribution algorithm look after the layout of the data [10].…”

Section: Ghafarian Et Al (2015) Devised the Technique To Placementioning

confidence: 99%

Extended Balanced Scheduler with Clustering and Rep- lication for Data Intensive Scientific Workflow Applications in Cloud Computing

Kaur¹,

Aggarwal²

2018

JERA

View full text Add to dashboard Cite

Cloud computing is an advance computing model using which several applications, data and countless IT services are provided over the Internet. Task scheduling plays a crucial role in cloud computing systems. The issue of task scheduling can be viewed as the finding or searching an optimal mapping/assignment of set of subtasks of different tasks over the available set of resources so that we can achieve the desired goals for tasks. With the enlargement of users of cloud the tasks need to be scheduled. Cloud’s performance depends on the task scheduling algorithms used. Numerous algorithms have been submitted in the past to solve the task scheduling problem for heterogeneous network of computers. The existing research work proposes different methods for data intensive applications which are energy and deadline aware task scheduling method. As scientific workflow is combination of fine grain and coarse grain task. Every task scheduled to VM has system overhead. If multiple fine grain task are executing in scientific workflow, it increase the scheduling overhead. To overcome the scheduling overhead, multiple small tasks has been combined to large task, which decrease the scheduling overhead and improve the execution time of the workflow. Horizontal clustering has been used to cluster the fine grained task further replication technique has been combined. The proposed scheduling algorithm improves the performance metrics such as execution time and cost. Further this research can be extended with improved clustering technique and replication methods.

show abstract

Section: Ghafarian Et Al (2015) Devised the Technique To Placementioning

confidence: 99%

Extended Balanced Scheduler with Clustering and Rep- lication for Data Intensive Scientific Workflow Applications in Cloud Computing

Kaur¹,

Aggarwal²

2018

JERA

View full text Add to dashboard Cite

show abstract

“…Also, some research areas related to service composition including service workflow [22], service management [23], and modeling of business flow [24] are widely studied. Nevertheless, few studies have been carried out with the consideration of QoS-based composition in the complex CMfg environment.…”

Section: Maintenancementioning

confidence: 99%

A hybrid artificial bee colony algorithm for optimal selection of QoS-based cloud manufacturing service composition

Zhou

Yao

2016

Int J Adv Manuf Technol

130

View full text Add to dashboard Cite

With the advent of cloud manufacturing (CMfg), more and more services in CMfg platforms may provide the same functionality but differ in performance. In order to insure the manufacturing cloud to match the complicated task requirements, composited CMfg service optimal selection (CCSOS) is becoming increasingly important. This study proposes a new approach for such CCSOS problems, the so-called hybrid artificial bee colony (HABC) algorithm, which employs both the probabilistic model of Archimedean copula estimation of distribution algorithm (ACEDA) and the chaos operators of global best-guided artificial bee colony to generate the offspring individuals with consideration of quality of service (QoS) and CMfg environment. Different-scale CCSOS problems are adopted to evaluate the performance of the proposed HABC. Experimental results have shown that the HABC can find better solutions compared with such algorithms as genetic algorithm, particle swarm optimization, and basic artificial bee colony algorithm.

show abstract

“…There also are other SWFMSes in other significant fields such as Kepler for physics [15], Swift for climate science, Vistrails is for earth science, and VIEW for medical science [16]. In addition, the contemporary trend usually is to merge SWFMSes into Cloud platforms and enable users to access services via their portals [17][18].…”

Section: Tavernamentioning

confidence: 99%

Integrated Automatic Workflow for Phylogenetic Tree Analysis Using Public Access and Local Web Services

Damkliang

Tandayya

Sangket

et al. 2016

Journal of Integrative Bioinformatics

View full text Add to dashboard Cite

SummaryAt the present, coding sequence (CDS) has been discovered and larger CDS is being revealed frequently. Approaches and related tools have also been developed and upgraded concurrently, especially for phylogenetic tree analysis. This paper proposes an integrated automatic Taverna workflow for the phylogenetic tree inferring analysis using public access web services at European Bioinformatics Institute (EMBL-EBI) and Swiss Institute of Bioinformatics (SIB), and our own deployed local web services. The workflow input is a set of CDS in the Fasta format. The workflow supports 1,000 to 20,000 numbers in bootstrapping replication. The workflow performs the tree inferring such as Parsimony (PARS), Distance Matrix -Neighbor Joining (DIST-NJ), and Maximum Likelihood (ML) algorithms of EMBOSS PHYLIPNEW package based on our proposed Multiple Sequence Alignment (MSA) similarity score. The local web services are implemented and deployed into two types using the Soaplab2 and Apache Axis2 deployment. There are SOAP and Java Web Service (JWS) providing WSDL endpoints to Taverna Workbench, a workflow manager. The workflow has been validated, the performance has been measured, and its results have been verified. Our workflow's execution time is less than ten minutes for inferring a tree with 10,000 replicates of the bootstrapping numbers. This paper proposes a new integrated automatic workflow which will be beneficial to the bioinformaticians with an intermediate level of knowledge and experiences. The all local services have been deployed at our portal http://bioservices.sci.psu.ac.th.

show abstract

A Service Framework for Scientific Workflow Management in the Cloud

Cited by 35 publications

References 30 publications

Extended Balanced Scheduler with Clustering and Rep- lication for Data Intensive Scientific Workflow Applications in Cloud Computing

Extended Balanced Scheduler with Clustering and Rep- lication for Data Intensive Scientific Workflow Applications in Cloud Computing

A hybrid artificial bee colony algorithm for optimal selection of QoS-based cloud manufacturing service composition

Integrated Automatic Workflow for Phylogenetic Tree Analysis Using Public Access and Local Web Services

Contact Info

Product

Resources

About