Loading [a11y]/accessibility-menu.js
Redundancy Minimization and Cost Reduction for Workflows with Reliability Requirements in Cloud-Based Services | IEEE Journals & Magazine | IEEE Xplore

Redundancy Minimization and Cost Reduction for Workflows with Reliability Requirements in Cloud-Based Services


Abstract:

Reliability requirement assurance is an important quality of service (QoS) for workflow execution in cloud-based services. For a workflow with a reliability requirement, ...Show More

Abstract:

Reliability requirement assurance is an important quality of service (QoS) for workflow execution in cloud-based services. For a workflow with a reliability requirement, the enough replication for redundancy minimization (ERRM) and quantitative fault-tolerance with minimum execution cost + (QFEC+) algorithms are state-of-the-art algorithms to reduce the redundancy and cost, respectively. In this work, we define the reliability increment ratio (RIR) and propose the redundancy minimization using RIR (R_RIR) algorithm. In addition, we introduce the geometric mean and propose the cost reduction using geometric mean (C_GM) algorithm based on redundancy minimization. Experimental results show the proposed R_RIR and C_GM algorithms are superior to state-of-the-art algorithms: (1) although both R_RIR and ERRM show the same redundancy results, R_RIR is proven to generate minimal redundancy, whereas ERRM cannot; (2) R_RIR only consumes a few seconds to achieve minimal redundancy for large-scale workflows, and it has much higher time efficiency than ERRM; and (3) C_GM generates less cost than QFEC+ in a large part of cases.
Published in: IEEE Transactions on Cloud Computing ( Volume: 10, Issue: 1, 01 Jan.-March 2022)
Page(s): 633 - 647
Date of Publication: 27 August 2019

ISSN Information:

Funding Agency:


References

References is not available for this document.