Security driven dynamic level scheduling under precedence constrained tasks in IaaS cloud

High performance in large-scale heterogeneous distributed infrastructure, like cloud computing depends on effective scheduling algorithms. List-based scheduling is one of the most effective heuristic technique for allocating task graphs of fully connected heterogeneous cloud systems. However, few li...

Full description

Saved in:
Bibliographic Details
Published in:International journal of information technology (Singapore. Online) 2024-02, Vol.16 (2), p.721-729
Main Authors: Alam, Mahfooz, Shahid, Mohammad, Mustajab, Suhel, Ahmad, Faisal
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:High performance in large-scale heterogeneous distributed infrastructure, like cloud computing depends on effective scheduling algorithms. List-based scheduling is one of the most effective heuristic technique for allocating task graphs of fully connected heterogeneous cloud systems. However, few list-based scheduling algorithms used today takes into account the security needs of the applications or the security services provided by the cloud providers. The mapping of high-priority tasks onto the virtual machine satisfying the security requirements is challenging in the cloud environment. In this work, a security-driven dynamic level scheduling (SDLS) algorithm is proposed for the IaaS cloud using a dynamic level, considering the security overheads into account during the task prioritization and the virtual machine selection phases. SDLS offers more reliable virtual machines to the higher security demand tasks to reduce the risk probability. The suggested SDLS outperforms the existing algorithm in terms of makespan and risk probability, as shown in the performance study.
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-023-01523-0