An Iterative Optimization Framework for Adaptive Workflow Management in Computational Clouds

Wang, Long; Duan, Rubing; Li, Xiaorong; Lu, Sifei; Hung, Terence; Calheiros, Rodrigo N.; Buyya, Rajkumar

doi:10.1109/trustcom.2013.128

Cited by 16 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the output of some recent approaches [33] is not only to determine the number of the VM instances but also the types of the instances. In fact, a task may prefer one machine type over another considering different metrics such as the execution time, cost, etc.…”

Section: Discussionmentioning

confidence: 99%

“…The major contribution of Wang et al [33] is a new scheduling method called Upgrade Fit algorithm that extends the existing capability of workflow management from DAG to non-DAG processing. Upgrade Fit can determine the suitable types as well as the number of the VMs to run iterative workflow tasks with dynamic resources provisioning strategy.…”

Section: ) Scheduling a Single Workflowmentioning

confidence: 99%

See 1 more Smart Citation

Workflow Scheduling in Cloud Computing: A Survey

Fakhfakh

Kacem

2014

2014 IEEE 18th International Enterprise Distributed Object Computing Conference Workshops and Demonstrations

View full text Add to dashboard Cite

Workflow systems have become a major vehicle for easy and efficient development of scientific applications. This type of systems can benefit from the resource provisioning technology offered by the cloud computing. In fact, the latter offers on-demand virtualized resources to its users. These virtual resources can be added and released dynamically. Also, users are charged on a pay-per-use basis. How to make appropriate decisions when allocating resources to the tasks and dispatching the computing tasks to resource pool has become the main issue in cloud computing. The amount of allocated resources affects the execution time of the applications and the cost incurred by the user. In fact, resource under-provisioning will necessarily affect the performance. In contrast, over-provisioning can result in idle instances and cause additional costs. Then, efficient scheduling algorithms are required for selection of best suitable resources for task execution. This paper focuses on some of the important workflow scheduling strategies. It brings out an exhaustive survey of such strategies in cloud computing and includes a detailed classification of them. Then, it presents a comparative analysis of the studied approaches. Finally, it stands out a critical challenge for further research.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: ) Scheduling a Single Workflowmentioning

confidence: 99%

Workflow Scheduling in Cloud Computing: A Survey

Fakhfakh

Kacem

2014

2014 IEEE 18th International Enterprise Distributed Object Computing Conference Workshops and Demonstrations

View full text Add to dashboard Cite

show abstract

“…The resources provisioning problem for workflow applications in the cloud has been widely studied over the recent years [13], [20], [1], [6], [18], [7], [23]. In fact, the type and …”

Section: Related Workmentioning

confidence: 99%

A Provisioning Approach of Cloud Resources for Dynamic Workflows

Fakhfakh

Kacem

2015

2015 IEEE 8th International Conference on Cloud Computing

View full text Add to dashboard Cite

Workflow technologies have become an efficient mean for the development of different applications. One wellknown challenge for executing workflows on cloud computing is the resources provisioning. The latter consists in making an appropriate decision when mapping tasks to resources considering multiple objectives that are often contradictory. The problem of resources provisioning for workflow applications in the cloud has been widely studied in the literature. However, the existing works didn't consider the change in workflow instances at runtime. This functionality has become a major requirement to deal with unusual situations and evolutions. In this paper, we present a first step towards the resources provisioning for a dynamic workflow in the cloud. In fact, we propose a provisioning algorithm which takes into account some constraints. After that, we extend it in order to support the dynamic changes of workflow. Our algorithm is evaluated using CloudSim simulator. The different experiments that we present show the efficiency of our approach in terms of financial execution cost and overhead.

show abstract

“…Through the CODA framework, the workflows could be easily composed and efficiently executed in Amazon EC2. In order to address performance and cost issues of big data processing on Clouds, Long Wang et al [15] presented a novel design of adaptive workflow management system which included a data mining based prediction model, workflow scheduler, and iteration controls to optimize the data processing via iterative workflow tasks.…”

Section: Related Workmentioning

confidence: 99%

Devising a Cloud Scientific Workflow Platform for Big Data

Zhao

et al. 2014

2014 IEEE World Congress on Services

View full text Add to dashboard Cite

Abstract-Scientificworkflow management systems (SWFMSs) are facing unprecedented challenges from big data deluge. As revising all the existing workflow applications to fit into Cloud computing paradigm is impractical, thus migrating SWFMSs into the Cloud to leverage the functionalities of both Cloud computing and SWFMSs may provide a viable approach to big data processing. In this paper, we first discuss the challenges for scientific workflow applications and the available solutions in details, and analyze the essential requirements for a scientific computing Cloud platform. Then we propose a service framework to normalize the integration of SWFMS with Cloud computing. Meanwhile, we also present our implementation experience based on the service Framework. At last, we set up a series of experiments to demonstrate the capability of our implementation and use a Montage Image Mosaic Workflow as a showcase of the implementation.

show abstract

An Iterative Optimization Framework for Adaptive Workflow Management in Computational Clouds

Cited by 16 publications

References 12 publications

Workflow Scheduling in Cloud Computing: A Survey

Workflow Scheduling in Cloud Computing: A Survey

A Provisioning Approach of Cloud Resources for Dynamic Workflows

Devising a Cloud Scientific Workflow Platform for Big Data

Contact Info

Product

Resources

About